class GoogleAiLabelEncoder(BaseTransformer):
def __init__(self, colname):
self.colname = colname
self.encoder = OrdinalEncoder()
def fit(self, annotations, **kwargs):
self.encoder.fit(annotations[self.colname].values)
return self
def transform(self, annotations, annotations_human_labels, **kwargs):
if annotations is not None:
annotations[self.colname] = self.encoder.transform(
annotations[self.colname].values)
annotations_human_labels[self.colname] = self.encoder.transform(
annotations_human_labels[self.colname].values)
return {
'annotations': annotations,
'annotations_human_labels': annotations_human_labels
}
else:
return {'mapping': self.encoder.category_mapping[0]['mapping']}
def load(self, filepath):
self.encoder = joblib.load(filepath)
return self
def persist(self, filepath):
joblib.dump(self.encoder, filepath)
class CategoricalTransformer(BaseEstimator, TransformerMixin):
def __init__(self,
cat_cols=None,
drop_original: bool = False,
encoder=OrdinalEncoder()):
"""
Categorical transformer. This is a wrapper for categorical encoders.
:param cat_cols:
:param drop_original:
:param encoder:
"""
self.cat_cols = cat_cols
self.drop_original = drop_original
self.encoder = encoder
self.default_encoder = OrdinalEncoder()
def fit(self, X, y=None):
if self.cat_cols is None:
kinds = np.array([dt.kind for dt in X.dtypes])
is_cat = kinds == 'O'
self.cat_cols = list(X.columns[is_cat])
self.encoder.set_params(cols=self.cat_cols)
self.default_encoder.set_params(cols=self.cat_cols)
self.encoder.fit(X[self.cat_cols], y)
self.default_encoder.fit(X[self.cat_cols], y)
return self
def transform(self, X, y=None):
data = copy.deepcopy(X)
new_cat_names = [f'{col}_encoded' for col in self.cat_cols]
encoded_data = self.encoder.transform(data[self.cat_cols])
if encoded_data.shape[1] == len(self.cat_cols):
data[new_cat_names] = encoded_data
else:
pass
if self.drop_original:
data = data.drop(self.cat_cols, axis=1)
else:
data[self.cat_cols] = self.default_encoder.transform(
data[self.cat_cols])
return data
def fit_transform(self, X, y=None, **fit_params):
data = copy.deepcopy(X)
self.fit(data)
return self.transform(data)
class HelmertEncoder(BaseEstimator, TransformerMixin):
"""
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False):
"""
:param verbose:
:param cols:
:return:
"""
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = OrdinalEncoder(verbose=verbose, cols=cols)
def fit(self, X, y=None, **kwargs):
"""
:param X:
:param y:
:param kwargs:
:return:
"""
self.ordinal_encoder = self.ordinal_encoder.fit(X)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [
x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5
]
return self
def transform(self, X):
"""
:param X:
:return:
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
if self.cols == []:
return X
X = self.ordinal_encoder.transform(X)
X = helmert_coding(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
return X
class HelmertEncoder(BaseEstimator, TransformerMixin):
"""
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False):
"""
:param verbose:
:param cols:
:return:
"""
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = OrdinalEncoder(verbose=verbose, cols=cols)
def fit(self, X, y=None, **kwargs):
"""
:param X:
:param y:
:param kwargs:
:return:
"""
self.ordinal_encoder = self.ordinal_encoder.fit(X)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""
:param X:
:return:
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
if self.cols == []:
return X
X = self.ordinal_encoder.transform(X)
X = helmert_coding(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
return X
def EncodeCategoricalData(train_df, test_df):
"""encode data with OrdinalEncoder
Parameters
----------
train_df: dataframe
training dataframe object to fit and transform
test_df: dataframe
test dataframe object to transform
Returns
-------
transformed training and test dataframe
"""
# column list to ordinal encode
ordinal_encode_cols = ["country", "province",
"region_1", "taster_name", "variety"]
# create ordinal encode object
# object assigns -1 to the first-time-seen values of the test set
ordinal_encoder = OrdinalEncoder(cols=ordinal_encode_cols,
return_df=True,
handle_unknown="value",
handle_missing="return_nan")
# fit object on the train dataset
ordinal_encoder.fit(train_df)
# transform train and test datasets
ord_encoded_train = (ordinal_encoder
.transform(train_df))
ord_encoded_test = (ordinal_encoder
.transform(test_df))
return ord_encoded_train, ord_encoded_test
class BinaryEncoder(BaseEstimator, TransformerMixin):
"""
Binary encoding encodes the integers as binary code with one column per digit.
"""
def __init__(self, verbose=0, cols=None):
"""
:param verbose:
:param cols:
:return:
"""
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = OrdinalEncoder(verbose=verbose, cols=cols)
def fit(self, X, y=None, **kwargs):
"""
:param X:
:param y:
:param kwargs:
:return:
"""
self.ordinal_encoder = self.ordinal_encoder.fit(X)
return self
def transform(self, X):
"""
:param X:
:return:
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
X = self.ordinal_encoder.transform(X)
return binary(X, cols=self.cols)
class BackwardDifferenceEncoder(BaseEstimator, TransformerMixin):
"""
"""
def __init__(self, verbose=0, cols=None):
"""
:param verbose:
:param cols:
:return:
"""
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = OrdinalEncoder(verbose=verbose, cols=cols)
def fit(self, X, y=None, **kwargs):
"""
:param X:
:param y:
:param kwargs:
:return:
"""
self.ordinal_encoder = self.ordinal_encoder.fit(X)
return self
def transform(self, X):
"""
:param X:
:return:
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
X = self.ordinal_encoder.transform(X)
return backward_difference_coding(X, cols=self.cols)
class HelmertEncoder(BaseEstimator, TransformerMixin):
"""Helmert contrast coding for encoding categorical features
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = HelmertEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 22 columns):
col_CHAS_0 506 non-null float64
col_CHAS_1 506 non-null float64
col_RAD_0 506 non-null float64
col_RAD_1 506 non-null float64
col_RAD_2 506 non-null float64
col_RAD_3 506 non-null float64
col_RAD_4 506 non-null float64
col_RAD_5 506 non-null float64
col_RAD_6 506 non-null float64
col_RAD_7 506 non-null float64
col_RAD_8 506 non-null float64
col_CRIM 506 non-null float64
col_ZN 506 non-null float64
col_INDUS 506 non-null float64
col_NOX 506 non-null float64
col_RM 506 non-null float64
col_AGE 506 non-null float64
col_DIS 506 non-null float64
col_TAX 506 non-null float64
col_PTRATIO 506 non-null float64
col_B 506 non-null float64
col_LSTAT 506 non-null float64
dtypes: float64(22)
memory usage: 87.0 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
http://www.ats.ucla.edu/stat/r/library/contrast_coding.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose,
cols=self.cols)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [
x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5
]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.helmert_coding(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
@staticmethod
def helmert_coding(X_in, cols=None):
"""
"""
X = X_in.copy(deep=True)
X.columns = ['col_' + str(x) for x in X.columns.values]
cols = ['col_' + str(x) for x in cols]
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
mod = dmatrix("C(%s, Helmert)" % (col, ), X)
for dig in range(len(mod[0])):
X[str(col) + '_%d' % (dig, )] = mod[:, dig]
bin_cols.append(str(col) + '_%d' % (dig, ))
X = X.reindex(columns=bin_cols + pass_thru)
return X
class HelmertEncoder(BaseEstimator, TransformerMixin):
"""Helmert contrast coding for encoding categorical features.
Parameters
----------
verbose: int
integer indicating verbosity of the output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_unknown: str
options are 'error', 'return_nan', 'value', and 'indicator'. The default is 'value'. Warning: if indicator is used,
an extra column will be added in if the transform matrix has unknown categories. This can cause
unexpected changes in dimension in some cases.
handle_missing: str
options are 'error', 'return_nan', 'value', and 'indicator'. The default is 'value'. Warning: if indicator is used,
an extra column will be added in if the transform matrix has nan values. This can cause
unexpected changes in dimension in some cases.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = HelmertEncoder(cols=['CHAS', 'RAD'], handle_unknown='value', handle_missing='value').fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 21 columns):
intercept 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS_0 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD_0 506 non-null float64
RAD_1 506 non-null float64
RAD_2 506 non-null float64
RAD_3 506 non-null float64
RAD_4 506 non-null float64
RAD_5 506 non-null float64
RAD_6 506 non-null float64
RAD_7 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(20), int64(1)
memory usage: 83.1 KB
None
References
----------
.. [1] Contrast Coding Systems for Categorical Variables, from
https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self,
verbose=0,
cols=None,
mapping=None,
drop_invariant=False,
return_df=True,
handle_unknown='value',
handle_missing='value'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.mapping = mapping
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.feature_names = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = util.convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value')
self.ordinal_encoder = self.ordinal_encoder.fit(X)
ordinal_mapping = self.ordinal_encoder.category_mapping
mappings_out = []
for switch in ordinal_mapping:
values = switch.get('mapping')
col = switch.get('col')
column_mapping = self.fit_helmert_coding(col, values,
self.handle_missing,
self.handle_unknown)
mappings_out.append({
'col': col,
'mapping': column_mapping,
})
self.mapping = mappings_out
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [
x for x in generated_cols if X_temp[x].var() <= 10e-5
]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# first check the type
X = util.convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError(
'Columns to be encoded can not contain new values')
X = self.helmert_coding(X, mapping=self.mapping)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
@staticmethod
def fit_helmert_coding(col, values, handle_missing, handle_unknown):
if handle_missing == 'value':
values = values[values > 0]
values_to_encode = values.get_values()
if len(values) < 2:
return pd.DataFrame(index=values_to_encode)
if handle_unknown == 'indicator':
values_to_encode = np.append(values_to_encode, -1)
helmert_contrast_matrix = Helmert().code_without_intercept(
values_to_encode)
df = pd.DataFrame(
data=helmert_contrast_matrix.matrix,
index=values_to_encode,
columns=[
str(col) + '_%d' % (i, )
for i in range(len(helmert_contrast_matrix.column_suffixes))
])
if handle_unknown == 'return_nan':
df.loc[-1] = np.nan
elif handle_unknown == 'value':
df.loc[-1] = np.zeros(len(values_to_encode) - 1)
if handle_missing == 'return_nan':
df.loc[values.loc[np.nan]] = np.nan
elif handle_missing == 'value':
df.loc[-2] = np.zeros(len(values_to_encode) - 1)
return df
@staticmethod
def helmert_coding(X_in, mapping):
"""
"""
X = X_in.copy(deep=True)
cols = X.columns.values.tolist()
X['intercept'] = pd.Series([1] * X.shape[0], index=X.index)
for switch in mapping:
col = switch.get('col')
mod = switch.get('mapping')
base_df = mod.reindex(X[col])
base_df.set_index(X.index, inplace=True)
X = pd.concat([base_df, X], axis=1)
old_column_index = cols.index(col)
cols[old_column_index:old_column_index + 1] = mod.columns
cols = ['intercept'] + cols
return X.reindex(columns=cols)
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns
-------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError(
'Must fit data first. Affected feature names are not known before.'
)
else:
return self.feature_names
class BinaryEncoder(BaseEstimator, TransformerMixin):
"""Binary encoding for categorical variables, similar to onehot, but stores categories as binary bitstrings.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
impute_missing: bool
boolean for whether or not to apply the logic for handle_unknown, will be deprecated in the future.
handle_unknown: str
options are 'error', 'ignore' and 'impute', defaults to 'impute', which will impute the category -1. Warning: if
impute is used, an extra column will be added in if the transform matrix has unknown categories. This can causes
unexpected changes in dimension in some cases.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = BinaryEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 18 columns):
CHAS_0 506 non-null int64
CHAS_1 506 non-null int64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
RAD_4 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(7)
memory usage: 71.2 KB
None
"""
def __init__(self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True,
impute_missing=True,
handle_unknown='impute'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.impute_missing = impute_missing
self.handle_unknown = handle_unknown
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.digits_per_col = {}
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
impute_missing=self.impute_missing,
handle_unknown=self.handle_unknown)
X = X.drop_duplicates(subset=self.cols) if self.cols else X
self.ordinal_encoder = self.ordinal_encoder.fit(X)
for col in self.cols:
self.digits_per_col[col] = self.calc_required_digits(X, col)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
generated_cols = get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [
x for x in generated_cols if X_temp[x].var() <= 10e-5
]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
if not self.cols:
return X if self.return_df else X.values
X = self.ordinal_encoder.transform(X)
X = self.binary(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
def inverse_transform(self, X_in):
"""
Perform the inverse transformation to encoded data.
Parameters
----------
X_in : array-like, shape = [n_samples, n_features]
Returns
-------
p: array, the same size of X_in
"""
X = X_in.copy(deep=True)
# first check the type
X = convert_input(X)
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to inverse_transform data'
)
X = self.binary_to_integer(X, self.cols)
# then make sure that it is the right size
if X.shape[1] != self._dim:
if self.drop_invariant:
raise ValueError(
"Unexpected input dimension %d, the attribute drop_invariant should "
"set as False when transform data" % (X.shape[1], ))
else:
raise ValueError('Unexpected input dimension %d, expected %d' %
(
X.shape[1],
self._dim,
))
if not self.cols:
return X if self.return_df else X.values
if self.impute_missing and self.handle_unknown == 'impute':
for col in self.cols:
if any(X[col] == 0):
raise ValueError(
"inverse_transform is not supported because transform impute "
"the unknown category -1 when encode %s" % (col, ))
for switch in self.ordinal_encoder.mapping:
col_dict = {
col_pair[1]: col_pair[0]
for col_pair in switch.get('mapping')
}
X[switch.get('col')] = X[switch.get('col')].apply(
lambda x: col_dict.get(x))
return X if self.return_df else X.values
def binary(self, X_in, cols=None):
"""
Binary encoding encodes the integers as binary code with one column per digit.
Parameters
----------
X_in: DataFrame
cols: list-like, default None
Column names in the DataFrame to be encoded
Returns
-------
dummies : DataFrame
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
output = []
bin_cols = []
for col in cols:
# get how many digits we need to represent the classes present
digits = self.digits_per_col[col]
X_unique = pd.DataFrame(index=X[col].unique())
# map the ordinal column into a list of these digits, of length digits
X_unique_to_cols = X_unique.index.map(
lambda x: self.col_transform(x, digits))
for dig in range(digits):
X_unique[str(col) + '_%d' % (dig, )] = X_unique_to_cols.map(
lambda r: int(r[dig]) if r is not None else None)
bin_cols.append(str(col) + '_%d' % (dig, ))
output.append(X[[col]].merge(X_unique,
how='left',
left_on=col,
right_index=True).drop(labels=col,
axis=1))
if pass_thru:
output.append(X[pass_thru])
X = pd.concat(output, axis=1).reindex(columns=bin_cols + pass_thru)
return X
def binary_to_integer(self, X, cols):
"""
Convert binary code as integers.
Parameters
----------
X : DataFrame
encoded data
cols : list-like
Column names in the DataFrame that be encoded
Returns
-------
numerical: DataFrame
"""
out_cols = X.columns.values
for col in cols:
col_list = [
col0 for col0 in out_cols if str(col0).startswith(str(col))
]
for col0 in col_list:
if any(X[col0].isnull()):
raise ValueError(
"inverse_transform is not supported because transform impute "
"the unknown category -1 when encode %s" % (col, ))
len0 = len(col_list)
value_array = np.array([2**(len0 - 1 - i) for i in range(len0)])
X[col] = np.dot(X[col_list].values, value_array.T)
out_cols = [col0 for col0 in out_cols if col0 not in col_list]
X = X.reindex(columns=out_cols + cols)
return X
@staticmethod
def calc_required_digits(X, col):
"""
figure out how many digits we need to represent the classes present
"""
return int(np.ceil(np.log2(len(X[col].unique())))) + 1
@staticmethod
def col_transform(col, digits):
"""
The lambda body to transform the column values
"""
if col is None or np.isnan(col) or float(col) < 0.0:
return None
else:
col = list("{0:b}".format(int(col)))
if len(col) == digits:
return col
else:
return [str(0) for _ in range(digits - len(col))] + col
class TwoHotEncoder(BaseEstimator, TransformerMixin):
def __init__(self,
cols=None,
handle_missing='value',
handle_unknown='value',
use_cat_names=False,
return_df=True):
self.cols = cols
self.handle_missing = handle_missing
self.handle_unknown = handle_unknown
self.use_cat_names = use_cat_names
self.return_df = return_df
def fit(self, X, y=None, **kwargs):
self._dim = X.shape[1]
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(cols=self.cols,
handle_unknown='value',
handle_missing='value')
self.ordinal_encoder = self.ordinal_encoder.fit(X)
self.mapping = self.generate_mapping()
X_temp = self.transform(X, override_return_df=True)
self.feature_names = list(X_temp.columns)
return self
def generate_mapping(self):
mapping = []
for switch in self.ordinal_encoder.mapping:
col = switch.get('col')
values = switch.get('mapping').copy(deep=True)
if self.handle_missing == 'value':
values = values[values > 0]
if len(values) == 0:
continue
index = []
new_columns = []
n_col_name = str(col)
for i, (cat_name, class_) in enumerate(values.iteritems()):
if self.use_cat_names:
n_col_name = '_'.join([n_col_name, str(cat_name)])
else:
n_col_name = '_'.join([n_col_name, str(class_)])
if i % 2:
new_columns.append(n_col_name)
n_col_name = str(col)
index.append(class_)
if n_col_name != str(col):
new_columns.append(n_col_name)
index = index[::2] + index[1::2]
base_matrix = np.eye(len(new_columns), dtype=np.int)
base_matrix = np.vstack(
(base_matrix, -base_matrix))[:len(index), :]
base_df = pd.DataFrame(data=base_matrix,
columns=new_columns,
index=index)
if self.handle_unknown == 'value':
base_df.loc[-1] = 0
elif self.handle_unknown == 'return_nan':
base_df.loc[-1] = np.nan
if self.handle_missing == 'return_nan':
base_df.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
base_df.loc[-2] = 0
mapping.append({'col': col, 'mapping': base_df})
return mapping
def transform(self, X, override_return_df=False):
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
if not list(self.cols):
return X if self.return_df else X.values
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError(
'Columns to be encoded can not contain new values')
X = self.get_dummies(X)
if self.return_df or override_return_df:
return X
else:
return X.values
def get_feature_names(self):
if not isinstance(self.feature_names, list):
raise ValueError(
'Must transform data first. Affected feature names are not known before.'
)
else:
return self.feature_names
def get_dummies(self, X_in):
X = X_in.copy(deep=True)
cols = X.columns.values.tolist()
for switch in self.mapping:
col = switch.get('col')
mod = switch.get('mapping')
base_df = mod.reindex(X[col])
base_df = base_df.set_index(X.index)
X = pd.concat([base_df, X], axis=1)
old_column_index = cols.index(col)
cols[old_column_index:old_column_index + 1] = mod.columns
X = X.reindex(columns=cols)
return X
class WOEEncoder(BaseEstimator, TransformerMixin):
"""Weight of Evidence coding for categorical features.
Parameters
----------
verbose: int
integer indicating verbosity of the output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_missing: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which will assume WOE=0.
handle_unknown: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which will assume WOE=0.
randomized: bool,
adds normal (Gaussian) distribution noise into training data in order to decrease overfitting (testing data are untouched).
sigma: float
standard deviation (spread or "width") of the normal distribution.
regularization: float
the purpose of regularization is mostly to prevent division by zero.
When regularization is 0, you may encounter division by zero.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target > 22.5
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = WOEEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 13 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(13)
memory usage: 51.5 KB
None
References
----------
.. [1] Weight of Evidence (WOE) and Information Value Explained, from
https://www.listendata.com/2015/03/weight-of-evidence-woe-and-information.html
"""
def __init__(self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True,
handle_unknown='value',
handle_missing='value',
random_state=None,
randomized=False,
sigma=0.05,
regularization=1.0):
self.verbose = verbose
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self._sum = None
self._count = None
self.random_state = random_state
self.randomized = randomized
self.sigma = sigma
self.regularization = regularization
self.feature_names = None
# noinspection PyUnusedLocal
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and binary y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Binary target values.
Returns
-------
self : encoder
Returns self.
"""
# Unite parameters into pandas types
X = util.convert_input(X)
y = util.convert_input_vector(y, X.index).astype(float)
# The lengths must be equal
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) +
" but length of y is " + str(y.shape[0]) + ".")
# The label must be binary with values {0,1}
unique = y.unique()
if len(unique) != 2:
raise ValueError(
"The target column y must be binary. But the target contains "
+ str(len(unique)) + " unique value(s).")
if y.isnull().any():
raise ValueError(
"The target column y must not contain missing values.")
if np.max(unique) < 1:
raise ValueError(
"The target column y must be binary with values {0, 1}. Value 1 was not found in the target."
)
if np.min(unique) > 0:
raise ValueError(
"The target column y must be binary with values {0, 1}. Value 0 was not found in the target."
)
self._dim = X.shape[1]
# If columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value')
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
# Training
self.mapping = self._train(X_ordinal, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
# Store column names with approximately constant variance on the training data
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [
x for x in generated_cols if X_temp[x].var() <= 10e-5
]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data. When the data are used for model training,
it is important to also pass the target in order to apply leave one out.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target information (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# Unite the input into pandas types
X = util.convert_input(X)
# Then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
# If we are encoding the training data, we have to check the target
if y is not None:
y = util.convert_input_vector(y, X.index).astype(float)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) +
" but length of y is " + str(y.shape[0]) +
".")
if not self.cols:
return X
# Do not modify the input argument
X = X.copy(deep=True)
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Unexpected categories found in dataframe')
# Loop over columns and replace nominal values with WOE
X = self._score(X, y)
# Postprocessing
# Note: We should not even convert these columns.
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def fit_transform(self, X, y=None, **fit_params):
"""
Encoders that utilize the target must make sure that the training data are transformed with:
transform(X, y)
and not with:
transform(X)
"""
# the interface requires 'y=None' in the signature but we need 'y'
if y is None:
raise (TypeError, 'fit_transform() missing argument: ' 'y' '')
return self.fit(X, y, **fit_params).transform(X, y)
def _train(self, X, y):
# Initialize the output
mapping = {}
# Calculate global statistics
self._sum = y.sum()
self._count = y.count()
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['sum', 'count'
]) # Count of x_{i,+} and x_i
# Create a new column with regularized WOE.
# Regularization helps to avoid division by zero.
# Pre-calculate WOEs because logarithms are slow.
nominator = (stats['sum'] + self.regularization) / (
self._sum + 2 * self.regularization)
denominator = ((stats['count'] - stats['sum']) +
self.regularization) / (self._count - self._sum +
2 * self.regularization)
woe = np.log(nominator / denominator)
# Ignore unique values. This helps to prevent overfitting on id-like columns.
woe[stats['count'] == 1] = 0
if self.handle_unknown == 'return_nan':
woe.loc[-1] = np.nan
elif self.handle_unknown == 'value':
woe.loc[-1] = 0
if self.handle_missing == 'return_nan':
woe.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
woe.loc[-2] = 0
# Store WOE for transform() function
mapping[col] = woe
return mapping
def _score(self, X, y):
for col in self.cols:
# Score the column
X[col] = X[col].map(self.mapping[col])
# Randomization is meaningful only for training data -> we do it only if y is present
if self.randomized and y is not None:
random_state_generator = check_random_state(self.random_state)
X[col] = (X[col] * random_state_generator.normal(
1., self.sigma, X[col].shape[0]))
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns
-------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError(
"Estimator has to be fitted to return feature names.")
else:
return self.feature_names
class BaseNEncoder(BaseEstimator, TransformerMixin):
"""Base-N encoder encodes the categories into arrays of their base-N representation. A base of 1 is equivalent to
one-hot encoding (not really base-1, but useful), a base of 2 is equivalent to binary encoding. N=number of actual
categories is equivalent to vanilla ordinal encoding.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = BaseNEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 16 columns):
CHAS_0 506 non-null int64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(5)
memory usage: 63.3 KB
None
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, base=2):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.base = base
self._encoded_columns = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose, cols=self.cols)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
# do a transform on the training data to get a column list
X_t = self.transform(X, override_return_df=True)
self._encoded_columns = X_t.columns.values
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.basen_encode(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
X.fillna(0.0, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def basen_encode(self, X_in, cols=None):
"""
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
# figure out how many digits we need to represent the classes present
if self.base == 1:
digits = len(X[col].unique())
else:
digits = int(np.ceil(math.log(len(X[col].unique()), self.base)))
# map the ordinal column into a list of these digits, of length digits
X[col] = X[col].map(lambda x: self.col_transform(x, digits))
for dig in range(digits):
X[str(col) + '_%d' % (dig, )] = X[col].map(lambda r: int(r[dig]) if r is not None else None)
bin_cols.append(str(col) + '_%d' % (dig, ))
if self._encoded_columns is None:
X = X.reindex(columns=bin_cols + pass_thru)
else:
X = X.reindex(columns=self._encoded_columns)
return X
def col_transform(self, col, digits):
"""
The lambda body to transform the column values
"""
if col is None or float(col) < 0.0:
return None
else:
col = self.numberToBase(int(col), self.base, digits)
if len(col) == digits:
return col
else:
return [0 for _ in range(digits - len(col))] + col
@staticmethod
def numberToBase(n, b, limit):
if b == 1:
return [0 if n != _ else 1 for _ in range(limit)]
if n == 0:
return [0 for _ in range(limit)]
digits = []
for _ in range(limit):
digits.append(int(n % b))
n, _ = divmod(n, b)
return digits[::-1]
class SumEncoder(BaseEstimator, TransformerMixin):
"""
"""
def __init__(self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True):
"""
:param verbose: (optional, default=0) integer indicating verbosity of output. 0 for none.
:param cols: (optional, default=None) a list of columns to encode, if None, all string columns will be encoded
:param drop_invariant: (optional, default=False) boolean for whether or not to drop columns with 0 variance
:param return_df: (optional, default=True) boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
:return:
"""
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
def fit(self, X, y=None, **kwargs):
"""
:param X:
:param y:
:param kwargs:
:return:
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose,
cols=self.cols)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [
x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5
]
return self
def transform(self, X):
"""
:param X:
:return:
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = sum_coding(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
test_data.columns = [str(col) for col in test_data.columns]
test_data = test_data.fillna(0)
test_data = add_datepart(test_data, 'timestamp', drop=False)
prediction = cat_model.predict(test_data) + lgb_model.predict(test_data) + xgb_model.predict(test_data)
return prediction
if __name__ == "__main__":
path = 'C:/Work/gitsrc/Kaggle/data-science-bowl-2019'
test = pd.read_csv(f'{path}/test.csv')
preprocessedData = pd.read_csv("intermediate.csv")
title_oe = OrdinalEncoder()
title_oe.fit(list(set(preprocessedData['session_title'].unique()).union(set(test['title'].unique()))))
world_oe = OrdinalEncoder()
world_oe.fit(list(set(preprocessedData['world'].unique()).union(set(test['world'].unique()))))
preprocessedData['session_title'] = title_oe.transform(preprocessedData['session_title'].values)
preprocessedData['world'] = world_oe.transform(preprocessedData['world'].values)
lgb_model, xgb_model, cat_model = train(preprocessedData)
test['title'] = title_oe.transform(test['title'].values)
test['world'] = world_oe.transform(test['world'].values)
prediction = predict(test, lgb_model, xgb_model, cat_model)
sample_submission = pd.read_csv(f'{path}/sample_submission.csv')
sample_submission['accuracy_group'] = prediction.argmax(1)
class BackwardDifferenceEncoder(BaseEstimator, TransformerMixin):
"""
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False):
"""
:param verbose:
:param cols:
:return:
"""
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = OrdinalEncoder(verbose=verbose, cols=cols)
def fit(self, X, y=None, **kwargs):
"""
Fits an ordinal encoder to produce a consistent mapping across applications and optionally finds
generally invariant columns to drop consistently.
:param X:
:param y:
:param kwargs:
:return:
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = self.ordinal_encoder.fit(X)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""
:param X:
:return:
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
if self.cols == []:
return X
X = self.ordinal_encoder.transform(X)
X = backward_difference_coding(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
return X
class BackwardDifferenceEncoder(BaseEstimator, TransformerMixin):
"""Backward difference contrast coding for encoding categorical variables.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
impute_missing: bool
boolean for whether or not to apply the logic for handle_unknown, will be deprecated in the future.
handle_unknown: str
options are 'error', 'ignore' and 'impute', defaults to 'impute', which will impute the category -1. Warning: if
impute is used, an extra column will be added in if the transform matrix has unknown categories. This can causes
unexpected changes in dimension in some cases.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = BackwardDifferenceEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 21 columns):
intercept 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS_0 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD_0 506 non-null float64
RAD_1 506 non-null float64
RAD_2 506 non-null float64
RAD_3 506 non-null float64
RAD_4 506 non-null float64
RAD_5 506 non-null float64
RAD_6 506 non-null float64
RAD_7 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(20), int64(1)
memory usage: 83.1 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self,
verbose=0,
cols=None,
mapping=None,
drop_invariant=False,
return_df=True,
impute_missing=True,
handle_unknown='impute'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.mapping = mapping
self.impute_missing = impute_missing
self.handle_unknown = handle_unknown
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.feature_names = None
def fit(self, X, y=None, **kwargs):
"""Fits an ordinal encoder to produce a consistent mapping across applications and optionally finds
generally invariant columns to drop consistently.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
X = util.convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
impute_missing=self.impute_missing,
handle_unknown=self.handle_unknown)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
ordinal_mapping = self.ordinal_encoder.category_mapping
mappings_out = []
for switch in ordinal_mapping:
values = switch.get('mapping').get_values()
column_mapping = self.fit_backward_difference_coding(values)
mappings_out.append({
'col': switch.get('col'),
'mapping': column_mapping,
})
self.mapping = mappings_out
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [
x for x in generated_cols if X_temp[x].var() <= 10e-5
]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# first check the type
X = util.convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.backward_difference_coding(X, mapping=self.mapping)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
@staticmethod
def fit_backward_difference_coding(values):
if len(values) < 2:
return pd.DataFrame()
backwards_difference_matrix = Diff().code_without_intercept(values)
df = pd.DataFrame(data=backwards_difference_matrix.matrix,
columns=backwards_difference_matrix.column_suffixes)
df.index += 1
df.loc[0] = np.zeros(len(values) - 1)
return df
@staticmethod
def backward_difference_coding(X_in, mapping):
"""
"""
X = X_in.copy(deep=True)
cols = X.columns.values.tolist()
X['intercept'] = pd.Series([1] * X.shape[0], index=X.index)
for switch in mapping:
col = switch.get('col')
mod = switch.get('mapping')
new_columns = []
for i in range(len(mod.columns)):
c = mod.columns[i]
new_col = str(col) + '_%d' % (i, )
X[new_col] = mod[c].loc[X[col]].values
new_columns.append(new_col)
old_column_index = cols.index(col)
cols[old_column_index:old_column_index + 1] = new_columns
cols = ['intercept'] + cols
X = X.reindex(columns=cols)
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns:
--------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError(
'Must fit data first. Affected feature names are not known before.'
)
else:
return self.feature_names
class JamesSteinEncoder(BaseEstimator, TransformerMixin):
"""James-Stein estimator.
For feature value i, James-Stein estimator returns a weighted average of:
1) The mean target value for the observed feature value i.
2) The mean target value (regardless of the feature value).
This can be written as:
JS_i = (1-B)*mean(y_i) + B*mean(y)
The question is, what should be the weight B?
If we put too much weight on the conditional mean value, we will overfit.
If we put too much weight on the global mean, we will underfit.
The canonical solution in machine learning is to perform cross-validation.
However, Charles Stein came with a closed-form solution to the problem.
The intuition is: If the estimate of mean(y_i) is unreliable (y_i has high variance),
we should put more weight on mean(y). Stein put it into an equation as:
B = var(y_i) / (var(y_i)+var(y))
The only remaining issue is that we do not know var(y), let alone var(y_i).
Hence, we have to estimate the variances. But how can we reliably estimate the
variances, when we already struggle with the estimation of the mean values?!
There are multiple solutions:
1) If we have the same count of observations for each feature value i and all
y_i are close to each other, we can pretend that all var(y_i) are identical.
This is called a pooled model.
2) If the observation counts are not equal, it makes sense to replace the variances
with squared standard errors, which penalize small observation counts:
SE^2 = var(y)/count(y)
This is called an independent model.
James-Stein estimator has, however, one practical limitation - it was defined
only for normal distributions. If you want to apply it for binary classification,
which allows only values {0, 1}, it is better to first convert the mean target value
from the bound interval <0,1> into an unbounded interval by replacing mean(y)
with log-odds ratio:
log-odds_ratio_i = log(mean(y_i)/mean(y_not_i))
This is called binary model. The estimation of parameters of this model is, however,
tricky and sometimes it fails fatally. In these situations, it is better to use beta
model, which generally delivers slightly worse accuracy than binary model but does
not suffer from fatal failures.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop encoded columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_missing: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns the prior probability.
handle_unknown: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns the prior probability.
model: str
options are 'pooled', 'beta', 'binary' and 'independent', defaults to 'independent'.
randomized: bool,
adds normal (Gaussian) distribution noise into training data in order to decrease overfitting (testing data are untouched).
sigma: float
standard deviation (spread or "width") of the normal distribution.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = JamesSteinEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 13 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(13)
memory usage: 51.5 KB
None
References
----------
.. [1] Parametric empirical Bayes inference: Theory and applications, equations 1.19 & 1.20, from
https://www.jstor.org/stable/2287098
.. [2] Empirical Bayes for multiple sample sizes, from
http://chris-said.io/2017/05/03/empirical-bayes-for-multiple-sample-sizes/
.. [3] Shrinkage Estimation of Log-odds Ratios for Comparing Mobility Tables, from
https://journals.sagepub.com/doi/abs/10.1177/0081175015570097
.. [4] Stein's paradox and group rationality, from
www.philos.rug.nl/~romeyn/presentation/2017_romeijn_-_Paris_Stein.pdf
.. [5] Stein's Paradox in Statistics, from
http://statweb.stanford.edu/~ckirby/brad/other/Article1977.pdf
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True,
handle_unknown='value', handle_missing='value', model='independent', random_state=None, randomized=False, sigma=0.05):
self.verbose = verbose
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self.random_state = random_state
self.randomized = randomized
self.sigma = sigma
self.model = model
self.feature_names = None
# noinspection PyUnusedLocal
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and binary y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Binary target values.
Returns
-------
self : encoder
Returns self.
"""
# Unite parameters into pandas types
X = util.convert_input(X)
y = util.convert_input_vector(y, X.index).astype(float)
# The lengths must be equal
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
self._dim = X.shape[1]
# If columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
# Training
if self.model == 'independent':
self.mapping = self._train_independent(X_ordinal, y)
elif self.model == 'pooled':
self.mapping = self._train_pooled(X_ordinal, y)
elif self.model == 'beta':
self.mapping = self._train_beta(X_ordinal, y)
elif self.model == 'binary':
# The label must be binary with values {0,1}
unique = y.unique()
if len(unique) != 2:
raise ValueError("The target column y must be binary. But the target contains " + str(len(unique)) + " unique value(s).")
if y.isnull().any():
raise ValueError("The target column y must not contain missing values.")
if np.max(unique) < 1:
raise ValueError("The target column y must be binary with values {0, 1}. Value 1 was not found in the target.")
if np.min(unique) > 0:
raise ValueError("The target column y must be binary with values {0, 1}. Value 0 was not found in the target.")
# Perform the training
self.mapping = self._train_log_odds_ratio(X_ordinal, y)
else:
raise ValueError("model='" + str(self.model) + "' is not a recognized option")
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
# Store column names with approximately constant variance on the training data
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data. When the data are used for model training,
it is important to also pass the target in order to apply leave one out.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target information (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# Unite the input into pandas types
X = util.convert_input(X)
# Then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
# If we are encoding the training data, we have to check the target
if y is not None:
y = util.convert_input_vector(y, X.index).astype(float)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
if not self.cols:
return X
# Do not modify the input argument
X = X.copy(deep=True)
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Unexpected categories found in dataframe')
# Loop over columns and replace nominal values with WOE
X = self._score(X, y)
# Postprocessing
# Note: We should not even convert these columns.
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def fit_transform(self, X, y=None, **fit_params):
"""
Encoders that utilize the target must make sure that the training data are transformed with:
transform(X, y)
and not with:
transform(X)
"""
return self.fit(X, y, **fit_params).transform(X, y)
def _train_pooled(self, X, y):
# Implemented based on reference [1]
# Initialize the output
mapping = {}
# Calculate global statistics
prior = y.mean()
target_var = y.var()
global_count = len(y)
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['mean', 'count'])
# See: Computer Age Statistical Inference: Algorithms, Evidence, and Data Science (Bradley Efron & Trevor Hastie, 2016)
# Equations 7.19 and 7.20.
# Note: The equations assume normal distribution of the label. But our label is p(y|x),
# which is definitely not normally distributed as probabilities are bound to lie on interval 0..1.
# We make this approximation because Efron does it as well.
# Equation 7.19
# Explanation of the equation:
# https://stats.stackexchange.com/questions/191444/variance-in-estimating-p-for-a-binomial-distribution
# if stats['count'].var() > 0:
# warnings.warn('The pooled model assumes that each category is observed exactly N times. This was violated in "' + str(col) +'" column. Consider comparing the accuracy of this model to "independent" model.')
# This is a parametric estimate of var(p) in the binomial distribution.
# We do not use it because we also want to support non-binary targets.
# The difference in the estimates is small.
# variance = prior * (1 - prior) / stats['count'].mean()
# This is a squared estimate of standard error of the mean:
# https://en.wikipedia.org/wiki/Standard_error
variance = target_var/(stats['count'].mean())
# Equation 7.20
SSE = ((stats['mean']-prior)**2).sum() # Sum of Squared Errors
if SSE > 0: # We have to avoid division by zero
B = ((len(stats['count'])-3)*variance) / SSE
B = B.clip(0,1)
estimate = prior + (1 - B) * (stats['mean'] - prior)
else:
estimate = stats['mean']
# Ignore unique values. This helps to prevent overfitting on id-like columns
# This works better than: estimate[stats['count'] == 1] = prior
if len(stats['mean'])==global_count:
estimate[:] = prior
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = prior
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = prior
# Store the estimate for transform() function
mapping[col] = estimate
return mapping
def _train_independent(self, X, y):
# Implemented based on reference [2]
# Initialize the output
mapping = {}
# Calculate global statistics
prior = y.mean()
global_count = len(y)
global_var = y.var()
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['mean', 'var'])
i_var = stats['var'].fillna(0) # When we do not have more than 1 sample, assume 0 variance
unique_cnt = len(X[col].unique())
# See: Parametric Empirical Bayes Inference: Theory and Applications (Morris, 1983)
# Equations 1.19 and 1.20.
# Note: The equations assume normal distribution of the label. But our label is p(y|x),
# which is definitely not normally distributed as probabilities are bound to lie on interval 0..1.
# Nevertheless, it seems to perform surprisingly well. This is in agreement with:
# Data Analysis with Stein's Estimator and Its Generalizations (Efron & Morris, 1975)
# The equations are similar to James-Stein estimator, as listed in:
# Stein's Paradox in Statistics (Efron & Morris, 1977)
# Or:
# Computer Age Statistical Inference: Algorithms, Evidence, and Data Science (Efron & Hastie, 2016)
# Equations 7.19 and 7.20.
# The difference is that they have equal count of observations per estimated variable, while we generally
# do not have that. Nice discussion about that is given at:
# http://chris-said.io/2017/05/03/empirical-bayes-for-multiple-sample-sizes/
smoothing = i_var / (global_var + i_var) * (unique_cnt-3) / (unique_cnt-1)
smoothing = 1 - smoothing
smoothing = smoothing.clip(lower=0, upper=1) # Smoothing should be in the interval <0,1>
estimate = smoothing*(stats['mean']) + (1-smoothing)*prior
# Ignore unique values. This helps to prevent overfitting on id-like columns
if len(stats['mean'])==global_count:
estimate[:] = prior
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = prior
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = prior
# Store the estimate for transform() function
mapping[col] = estimate
return mapping
def _train_log_odds_ratio(self, X, y):
# Implemented based on reference [3]
# Initialize the output
mapping = {}
# Calculate global statistics
global_sum = y.sum()
global_count = y.count()
# Iterative estimation of mu and sigma as given on page 9.
# This problem is traditionally solved with Newton-Raphson method:
# https://en.wikipedia.org/wiki/Newton%27s_method
# But we just use sklearn minimizer.
def get_best_sigma(sigma, mu_k, sigma_k, K):
global mu # Ugly. But I want to be able to read it once the optimization ends.
w_k = 1. / (sigma ** 2 + sigma_k ** 2) # Weights depends on sigma
mu = sum(w_k * mu_k) / sum(w_k) # Mu transitively depends on sigma
total = sum(w_k * (mu_k - mu) ** 2) # We want this to be close to K-1
loss = abs(total - (K - 1))
return loss
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['sum', 'count']) # Count of x_{i,+} and x_i
# Create 2x2 contingency table
crosstable = pd.DataFrame()
crosstable['E-A-'] = global_count - stats['count'] + stats['sum'] - global_sum
crosstable['E-A+'] = stats['count'] - stats['sum']
crosstable['E+A-'] = global_sum - stats['sum']
crosstable['E+A+'] = stats['sum']
index = crosstable.index.values
crosstable = np.array(crosstable, dtype=np.float32) # The argument unites the types into float
# Count of contingency tables.
K = len(crosstable)
# Ignore id-like columns. This helps to prevent overfitting.
if K == global_count:
estimate = pd.Series(0, index=values)
else:
if K>1: # We want to avoid division by zero in y_k calculation
# Estimate log-odds ratios with Yates correction as listed on page 5.
mu_k = np.log((crosstable[:, 0] + 0.5) * (crosstable[:, 3] + 0.5) / ((crosstable[:, 1] + 0.5) * (crosstable[:, 2] + 0.5)))
# Standard deviation estimate for 2x2 contingency table as given in equation 2.
# The explanation of the equation is given in:
# https://stats.stackexchange.com/questions/266098/how-do-i-calculate-the-standard-deviation-of-the-log-odds
sigma_k = np.sqrt(np.sum(1. / (crosstable + 0.5), axis=1))
# Estimate the sigma and mu. Sigma is non-negative.
result = scipy.optimize.minimize(get_best_sigma, x0=1e-4, args=(mu_k, sigma_k, K), bounds=[(0, np.inf)], method='TNC', tol=1e-12, options={'gtol': 1e-12, 'ftol': 1e-12, 'eps':1e-12})
sigma = result.x[0]
# Empirical Bayes follows equation 7.
# However, James-Stein estimator behaves perversely when K < 3. Hence, we clip the B into interval <0,1>.
# Literature reference for the clipping:
# Estimates of Income for Small Places: An Application of James-Stein Procedures to Census Data (Fay & Harriout, 1979),
# page 270.
B = (K - 3) * sigma_k ** 2 / ((K - 1) * (sigma ** 2 + sigma_k ** 2))
B = B.clip(0,1)
y_k = mu + (1 - B) * (mu_k - mu)
# Convert Numpy vector back into Series
estimate = pd.Series(y_k, index=index)
else:
estimate = pd.Series(0, index=values)
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = 0
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = 0
# Store the estimate for transform() function
mapping[col] = estimate
return mapping
def _train_beta(self, X, y):
# Implemented based on reference [4]
# Initialize the output
mapping = {}
# Calculate global statistics
prior = y.mean()
global_count = len(y)
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['mean', 'count'])
# See: Stein's paradox and group rationality (Romeijn, 2017), page 14
smoothing = stats['count'] / (stats['count'] + global_count)
estimate = smoothing*(stats['mean']) + (1-smoothing)*prior
# Ignore unique values. This helps to prevent overfitting on id-like columns
if len(stats['mean'])==global_count:
estimate[:] = prior
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = prior
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = prior
# Store the estimate for transform() function
mapping[col] = estimate
return mapping
def _score(self, X, y):
for col in self.cols:
# Score the column
X[col] = X[col].map(self.mapping[col])
# Randomization is meaningful only for training data -> we do it only if y is present
if self.randomized and y is not None:
random_state_generator = check_random_state(self.random_state)
X[col] = (X[col] * random_state_generator.normal(1., self.sigma, X[col].shape[0]))
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns:
--------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError("Estimator has to be fitted to return feature names.")
else:
return self.feature_names
class BaseNEncoder(BaseEstimator, TransformerMixin):
"""Base-N encoder encodes the categories into arrays of their base-N representation. A base of 1 is equivalent to
one-hot encoding (not really base-1, but useful), a base of 2 is equivalent to binary encoding. N=number of actual
categories is equivalent to vanilla ordinal encoding.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = BaseNEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 16 columns):
CHAS_0 506 non-null int64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(5)
memory usage: 63.3 KB
None
"""
def __init__(self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True,
base=2):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.base = base
self._encoded_columns = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose,
cols=self.cols)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
# do a transform on the training data to get a column list
X_t = self.transform(X, override_return_df=True)
self._encoded_columns = X_t.columns.values
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [
x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5
]
return self
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.basen_encode(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
X.fillna(0.0, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def basen_encode(self, X_in, cols=None):
"""
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
# figure out how many digits we need to represent the classes present
if self.base == 1:
digits = len(X[col].unique())
else:
digits = int(np.ceil(math.log(len(X[col].unique()),
self.base)))
# map the ordinal column into a list of these digits, of length digits
X[col] = X[col].map(lambda x: self.col_transform(x, digits))
for dig in range(digits):
X[str(col) + '_%d' % (dig, )] = X[col].map(
lambda r: int(r[dig]) if r is not None else None)
bin_cols.append(str(col) + '_%d' % (dig, ))
if self._encoded_columns is None:
X = X.reindex(columns=bin_cols + pass_thru)
else:
X = X.reindex(columns=self._encoded_columns)
return X
def col_transform(self, col, digits):
"""
The lambda body to transform the column values
"""
if col is None or float(col) < 0.0:
return None
else:
col = self.numberToBase(int(col), self.base, digits)
if len(col) == digits:
return col
else:
return [0 for _ in range(digits - len(col))] + col
@staticmethod
def numberToBase(n, b, limit):
if b == 1:
return [0 if n != _ else 1 for _ in range(limit)]
if n == 0:
return [0 for _ in range(limit)]
digits = []
for _ in range(limit):
digits.append(int(n % b))
n, _ = divmod(n, b)
return digits[::-1]
class BinaryEncoder(BaseEstimator, TransformerMixin):
"""
Binary encoding encodes the integers as binary code with one column per digit.
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False):
"""
:param verbose:
:param cols:
:return:
"""
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = OrdinalEncoder(verbose=verbose, cols=cols)
def fit(self, X, y=None, **kwargs):
"""
:param X:
:param y:
:param kwargs:
:return:
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = self.ordinal_encoder.fit(X)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""
:param X:
:return:
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
if self.cols == []:
return X
X = self.ordinal_encoder.transform(X)
X = binary(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
return X
class OneHotEncoder(BaseEstimator, TransformerMixin):
"""Onehot (or dummy) coding for categorical features, produces one feature per category, each binary.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
impute_missing: bool
boolean for whether or not to apply the logic for handle_unknown, will be deprecated in the future.
handle_unknown: str
options are 'error', 'ignore' and 'impute', defaults to 'impute', which will impute the category -1. Warning: if
impute is used, an extra column will be added in if the transform matrix has unknown categories. This can causes
unexpected changes in dimension in some cases.
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = OneHotEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 22 columns):
CHAS_0 506 non-null int64
CHAS_1 506 non-null int64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
RAD_4 506 non-null int64
RAD_5 506 non-null int64
RAD_6 506 non-null int64
RAD_7 506 non-null int64
RAD_8 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(11)
memory usage: 87.0 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, impute_missing=True, handle_unknown='impute'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.impute_missing = impute_missing
self.handle_unknown = handle_unknown
@property
def category_mapping(self):
return self.ordinal_encoder.category_mapping
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
impute_missing=self.impute_missing,
handle_unknown=self.handle_unknown
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
if not self.cols:
return X if self.return_df else X.values
X = self.ordinal_encoder.transform(X)
X = self.get_dummies(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
def inverse_transform(self, Xt):
"""
Perform the inverse transformation to encoded data.
Parameters
----------
X_in : array-like, shape = [n_samples, n_features]
Returns
-------
p: array, the same size of X_in
"""
X = Xt.copy(deep=True)
# first check the type
X = convert_input(X)
if self._dim is None:
raise ValueError('Must train encoder before it can be used to inverse_transform data')
X = self.reverse_dummies(X, self.cols)
# then make sure that it is the right size
if X.shape[1] != self._dim:
if self.drop_invariant:
raise ValueError("Unexpected input dimension %d, the attribute drop_invariant should "
"set as False when transform data"%(X.shape[1],))
else:
raise ValueError('Unexpected input dimension %d, expected %d'% (X.shape[1], self._dim, ))
if not self.cols:
return X if self.return_df else X.values
if self.impute_missing and self.handle_unknown == 'impute':
for col in self.cols:
if any(X[col] == -1):
raise ValueError("inverse_transform is not supported because transform impute "
"the unknown category -1 when encode %s"%(col,))
for switch in self.ordinal_encoder.mapping:
col_dict = {col_pair[1] : col_pair[0] for col_pair in switch.get('mapping')}
X[switch.get('col')] = X[switch.get('col')].apply(lambda x:col_dict.get(x))
return X if self.return_df else X.values
def get_dummies(self, X_in, cols=None):
"""
Convert numerical variable into dummy variables
Parameters
----------
X_in: DataFrame
cols: list-like, default None
Column names in the DataFrame to be encoded
Returns
-------
dummies : DataFrame
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
col_tuples = [class_map['mapping'] for class_map in self.ordinal_encoder.mapping if class_map['col'] == col][0]
fit_classes = [col_val[1] for col_val in col_tuples]
if self.handle_unknown == 'impute':
fit_classes.append(-1)
for class_ in fit_classes:
n_col_name = str(col) + '_%s' % (class_, )
X[n_col_name] = X[col] == class_
bin_cols.append(n_col_name)
X = X.reindex(columns=bin_cols + pass_thru)
# convert all of the bools into integers.
for col in bin_cols:
X[col] = X[col].astype(int)
return X
def reverse_dummies(self, X, cols):
"""
Convert dummy variable into numerical variables
Parameters
----------
X : DataFrame
cols: list-like
Column names in the DataFrame that be encoded
Returns
-------
numerical: DataFrame
"""
out_cols = X.columns.values
for col in cols:
col_list = [col0 for col0 in out_cols if col0.startswith(col)]
value_array = np.array([int(col0.split('_')[1]) for col0 in col_list])
X[col] = np.dot(X[col_list].values, value_array.T)
out_cols = [col0 for col0 in out_cols if col0 not in col_list]
X = X.reindex(columns=out_cols + cols)
return X
class OneHotEncoder(BaseEstimator, TransformerMixin):
"""
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
Example
-------
>>> from category_encoders import OneHotEncoder
>>> from sklearn.datasets import fetch_20newsgroups_vectorized
>>> bunch = fetch_20newsgroups_vectorized(subset="all")
>>> X, y = bunch.data, bunch.target
>>> enc = OneHotEncoder(return_df=False).fit(X, y)
>>> numeric_dataset = enc.transform(X)
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
http://www.ats.ucla.edu/stat/r/library/contrast_coding.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose,
cols=self.cols)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [
x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5
]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.get_dummies(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
@staticmethod
def get_dummies(X_in, cols=None):
"""
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
classes = set(X[col].values.tolist())
for class_ in classes:
n_col_name = str(col) + '_%s' % (class_, )
X[n_col_name] = X[col] == class_
bin_cols.append(n_col_name)
X = X.reindex(columns=bin_cols + pass_thru)
# convert all of the bools into integers.
for col in bin_cols:
X[col] = X[col].astype(int)
return X
class OneHotEncoder(BaseEstimator, TransformerMixin):
"""Onehot (or dummy) coding for categorical features, produces one feature per category, each binary.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
use_cat_names: bool
if True, category values will be included in the encoded column names. Since this can result into duplicate column names, duplicates are suffixed with '#' symbol until a unique name is generated.
If False, category indices will be used instead of the category values.
handle_unknown: str
options are 'error', 'return_nan', 'value', and 'indicator'. The default is 'value'. Warning: if indicator is used,
an extra column will be added in if the transform matrix has unknown categories. This can cause
unexpected changes in dimension in some cases.
handle_missing: str
options are 'error', 'return_nan', 'value', and 'indicator'. The default is 'value'. Warning: if indicator is used,
an extra column will be added in if the transform matrix has nan values. This can cause
unexpected changes in dimension in some cases.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = OneHotEncoder(cols=['CHAS', 'RAD'], handle_unknown='indicator').fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 24 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS_1 506 non-null int64
CHAS_2 506 non-null int64
CHAS_-1 506 non-null int64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
RAD_4 506 non-null int64
RAD_5 506 non-null int64
RAD_6 506 non-null int64
RAD_7 506 non-null int64
RAD_8 506 non-null int64
RAD_9 506 non-null int64
RAD_-1 506 non-null int64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(13)
memory usage: 95.0 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True,
handle_missing='value', handle_unknown='value', use_cat_names=False):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.mapping = None
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self.use_cat_names = use_cat_names
self.feature_names = None
@property
def category_mapping(self):
return self.ordinal_encoder.category_mapping
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = util.convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
self.mapping = self.generate_mapping()
X_temp = self.transform(X, override_return_df=True)
self.feature_names = list(X_temp.columns)
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def generate_mapping(self):
mapping = []
found_column_counts = {}
for switch in self.ordinal_encoder.mapping:
col = switch.get('col')
values = switch.get('mapping').copy(deep=True)
if self.handle_missing == 'value':
values = values[values > 0]
if len(values) == 0:
continue
index = []
new_columns = []
for cat_name, class_ in values.iteritems():
if self.use_cat_names:
n_col_name = str(col) + '_%s' % (cat_name,)
found_count = found_column_counts.get(n_col_name, 0)
found_column_counts[n_col_name] = found_count + 1
n_col_name += '#' * found_count
else:
n_col_name = str(col) + '_%s' % (class_,)
index.append(class_)
new_columns.append(n_col_name)
if self.handle_unknown == 'indicator':
n_col_name = str(col) + '_%s' % (-1,)
if self.use_cat_names:
found_count = found_column_counts.get(n_col_name, 0)
found_column_counts[n_col_name] = found_count + 1
n_col_name += '#' * found_count
new_columns.append(n_col_name)
index.append(-1)
base_matrix = np.eye(N=len(index), dtype=np.int)
base_df = pd.DataFrame(data=base_matrix, columns=new_columns, index=index)
if self.handle_unknown == 'value':
base_df.loc[-1] = 0
elif self.handle_unknown == 'return_nan':
base_df.loc[-1] = np.nan
if self.handle_missing == 'return_nan':
base_df.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
base_df.loc[-2] = 0
mapping.append({'col': col, 'mapping': base_df})
return mapping
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# first check the type
X = util.convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1], self._dim, ))
if not self.cols:
return X if self.return_df else X.values
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Columns to be encoded can not contain new values')
X = self.get_dummies(X)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def inverse_transform(self, X_in):
"""
Perform the inverse transformation to encoded data.
Parameters
----------
X_in : array-like, shape = [n_samples, n_features]
Returns
-------
p: array, the same size of X_in
"""
X = X_in.copy(deep=True)
# first check the type
X = util.convert_input(X)
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to inverse_transform data')
X = self.reverse_dummies(X, self.mapping)
# then make sure that it is the right size
if X.shape[1] != self._dim:
if self.drop_invariant:
raise ValueError("Unexpected input dimension %d, the attribute drop_invariant should "
"set as False when transform data" % (X.shape[1],))
else:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1], self._dim, ))
if not self.cols:
return X if self.return_df else X.values
for switch in self.ordinal_encoder.mapping:
column_mapping = switch.get('mapping')
inverse = pd.Series(data=column_mapping.index, index=column_mapping.get_values())
X[switch.get('col')] = X[switch.get('col')].map(inverse).astype(switch.get('data_type'))
if self.handle_unknown == 'return_nan' and self.handle_missing == 'return_nan':
for col in self.cols:
if X[switch.get('col')].isnull().any():
warnings.warn("inverse_transform is not supported because transform impute "
"the unknown category nan when encode %s" % (col,))
return X if self.return_df else X.values
def get_dummies(self, X_in):
"""
Convert numerical variable into dummy variables
Parameters
----------
X_in: DataFrame
mapping: list-like
Contains mappings of column to be transformed to it's new columns and value represented
Returns
-------
dummies : DataFrame
"""
X = X_in.copy(deep=True)
cols = X.columns.values.tolist()
for switch in self.mapping:
col = switch.get('col')
mod = switch.get('mapping')
base_df = mod.reindex(X[col])
base_df = base_df.set_index(X.index)
X = pd.concat([base_df, X], axis=1)
old_column_index = cols.index(col)
cols[old_column_index: old_column_index + 1] = mod.columns
X = X.reindex(columns=cols)
return X
def reverse_dummies(self, X, mapping):
"""
Convert dummy variable into numerical variables
Parameters
----------
X : DataFrame
mapping: list-like
Contains mappings of column to be transformed to it's new columns and value represented
Returns
-------
numerical: DataFrame
"""
out_cols = X.columns.values.tolist()
mapped_columns = []
for switch in mapping:
col = switch.get('col')
mod = switch.get('mapping')
insert_at = out_cols.index(mod.columns[0])
X.insert(insert_at, col, 0)
positive_indexes = mod.index[mod.index > 0]
for i in range(positive_indexes.shape[0]):
existing_col = mod.columns[i]
val = positive_indexes[i]
X.loc[X[existing_col] == 1, col] = val
mapped_columns.append(existing_col)
X.drop(mod.columns, axis=1, inplace=True)
out_cols = X.columns.values.tolist()
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns
--------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError(
'Must transform data first. Affected feature names are not known before.')
else:
return self.feature_names
class NestedTargetEncoder(BaseEstimator, util.TransformerWithTargetMixin):
"""Estimate of likelihood for nested data.
This is a generalization of the m-probability estimate. The main difference
is that instead of using a global prior, it can use a more fine-tuned prior.
This only works for nested data. For instance, I have individuals who live
in counties, that are inside states. If I want to estimate the likelihood
encoding for a county, it is better to use as prior the estimate for the
state instead of the global estimate.
Parameters
----------
verbose: int
integer indicating verbosity of the output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop encoded columns with 0 variance.
feature_mapping: dict
dictionary representing the child - parent relationship. keys are children.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_missing: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns the prior probability.
handle_unknown: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns the prior probability.
randomized: bool,
adds normal (Gaussian) distribution noise into training data in order to decrease overfitting (testing data are untouched).
sigma: float
standard deviation (spread or "width") of the normal distribution.
m_prior: float
this is the "m" in the m-probability estimate for the global mean. Higher value of m results into stronger shrinking.
It is used whenever we estimate a likelihood using the global mean as a prior.
M is non-negative.
m_parent: float
this is the "m" in the m-probability estimate. Higher value of m results into stronger shrinking.
It is used whenever we estimate a likelihood using the parent mean as a prior.
M is non-negative.
Example
-------
>>> from sktools import NestedTargetEncoder
>>> import pandas as pd
>>> X = pd.DataFrame(
>>> {
>>> "child": ["a", "a", "b", "b", "b", "c", "c", "d", "d", "d"],
>>> "parent": ["e", "e", "e", "e", "e", "f", "f", "f", "f", "f",]
>>> }
>>> )
>>> y = pd.Series([1, 2, 3, 1, 2, 4, 4, 5, 4, 4.5])
>>> ne = NestedTargetEncoder(feature_mapping={"child": "parent"}, m_prior=0)
>>> ne.fit_transform(X, y)
child parent
0 2.016667 1.8
1 2.016667 1.8
2 2.262500 1.8
3 2.262500 1.8
4 2.262500 1.8
5 3.683333 4.3
6 3.683333 4.3
7 4.137500 4.3
8 4.137500 4.3
9 4.137500 4.3
References
----------
.. [1] Additive smoothing, from https://en.wikipedia.org/wiki/Additive_smoothing#Generalized_to_the_case_of_known_incidence_rates
"""
def __init__(
self,
verbose=0,
cols=None,
drop_invariant=False,
feature_mapping={},
return_df=True,
handle_unknown="value",
handle_missing="value",
random_state=None,
randomized=False,
sigma=0.05,
m_prior=1.0,
m_parent=1.0,
):
self.verbose = verbose
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.cols = cols
self.feature_mapping = feature_mapping
self.ordinal_encoder = None
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self._sum = None
self._count = None
self.random_state = random_state
self.randomized = randomized
self.sigma = sigma
self.m_prior = m_prior
self.m_parent = m_parent
self.feature_names = None
self.parent_cols = None
self.parent_encoder = None
# noinspection PyUnusedLocal
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and binary y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Binary target values.
Returns
-------
self : encoder
Returns self.
"""
# Create parent encoder and fit it
self.parent_cols = list(self.feature_mapping.values())
self.parent_encoder = MEstimateEncoder(
verbose=self.verbose,
cols=self.parent_cols,
drop_invariant=self.drop_invariant,
return_df=self.return_df,
handle_unknown=self.handle_unknown,
handle_missing=self.handle_missing,
random_state=self.random_state,
randomized=self.randomized,
sigma=self.sigma,
m=self.m_prior,
)
self.parent_encoder.fit(X, y)
# Unite parameters into pandas types
X = util.convert_input(X)
y = util.convert_input_vector(y, X.index).astype(float)
# The lengths must be equal
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) +
" but length of y is " + str(y.shape[0]) + ".")
self._dim = X.shape[1]
# If columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == "error":
if X[self.cols].isnull().any().any():
raise ValueError("Columns to be encoded can not contain null")
# Check that children and parents are disjoint
children = set(self.feature_mapping.keys())
parents = set(self.feature_mapping.values())
if len(children.intersection(parents)) > 0:
raise ValueError("No column should be a child and a parent")
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown="value",
handle_missing="value",
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
# Training
self.mapping = self._train(X_ordinal, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
# Store column names with approximately constant variance on the training data
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [
x for x in generated_cols if X_temp[x].var() <= 10e-5
]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data.
When the data are used for model training, it is important to also pass the target in order to apply leave one out.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target information (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == "error":
if X[self.cols].isnull().any().any():
raise ValueError("Columns to be encoded can not contain null")
if self._dim is None:
raise ValueError(
"Must train encoder before it can be used to transform data.")
# Unite the input into pandas types
X = util.convert_input(X)
# Then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError("Unexpected input dimension %d, expected %d" % (
X.shape[1],
self._dim,
))
# If we are encoding the training data, we have to check the target
if y is not None:
y = util.convert_input_vector(y, X.index).astype(float)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) +
" but length of y is " + str(y.shape[0]) +
".")
if not list(self.cols):
return X
# Do not modify the input argument
X = X.copy(deep=True)
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == "error":
if X[self.cols].isin([-1]).any().any():
raise ValueError("Unexpected categories found in dataframe")
# Loop over the columns and replace the nominal values with the numbers
X = self._score(X, y)
# Postprocessing
# Note: We should not even convert these columns.
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def _train(self, X, y):
# Initialize the output
mapping = {}
# Calculate global statistics
self._sum = y.sum()
self._count = y.count()
prior = self._sum / self._count
for switch in self.ordinal_encoder.category_mapping:
col = switch.get("col")
values = switch.get("mapping")
# Easy case, the child is not in the child - parent dictionary.
# We just use the plain m-estimator with the global prior
if col not in self.feature_mapping:
stats = y.groupby(X[col]).agg(["sum", "count", "mean"])
estimate = (stats["sum"] + prior * self.m_prior) / (
stats["count"] + self.m_prior)
# Not so easy case, we have to deal with the parent
else:
parent_col = self.feature_mapping[col]
# Check son-parent unique relation
unique_parents = X.groupby([col]).agg({parent_col:
"nunique"})[parent_col]
more_1_parent = unique_parents[unique_parents > 1]
if any(unique_parents > 1) and more_1_parent.index >= 0:
raise ValueError(
f"There are children with more than one parent, {more_1_parent}"
)
# Get parent stats
te_parent = self.parent_encoder.transform(X)[parent_col]
parent_mapping = pd.DataFrame({
"te_parent": te_parent,
parent_col: X[parent_col]
}).drop_duplicates()
# Compute child statistics
stats = y.groupby(X[col]).agg(["sum", "count", "mean"])
# Relate parent and child stats
groups = X.loc[:, [parent_col, col]].drop_duplicates()
stats = stats.merge(groups, how="left",
on=col).merge(parent_mapping,
how="left",
on=parent_col)
# In case of numpy array
stats = stats.rename(columns={"key_0": col})
stats = stats.set_index(col)
# Calculate the m-probability estimate using the parent prior
estimate = (stats["sum"] + stats["te_parent"] *
self.m_parent) / (stats["count"] + self.m_parent)
# Ignore unique columns. This helps to prevent overfitting on id-like columns
if len(stats["count"]) == self._count:
estimate[:] = prior
# Column doesn't have parent - handle imputation as always
if col not in self.feature_mapping:
if self.handle_unknown == "return_nan":
estimate.loc[-1] = np.nan
elif self.handle_unknown == "value":
estimate.loc[-1] = prior
if self.handle_missing == "return_nan":
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == "value":
estimate.loc[-2] = prior
# With parents - we leave the imputation for afterwards
else:
# Unknown
estimate.loc[-1] = np.nan
# Missing
estimate.loc[values.loc[np.nan]] = np.nan
# Store the m-probability estimate for transform() function
mapping[col] = estimate
return mapping
def _score(self, X, y):
X_parents = self.parent_encoder.transform(X)
for col in self.cols:
# Easy case - not having parents (as m estimator)
if col not in self.feature_mapping:
# Score the column
X[col] = X[col].map(self.mapping[col])
# Harder case - having parents
else:
# Split missing and unknown values
unknown = X[col] == -1
missing = X[col] == -2
# Apply regular transformation
X[col] = X[col].map(self.mapping[col].drop_duplicates())
# Impute unknown with parent
parent_col = self.feature_mapping[col]
if self.handle_unknown == "value":
X[col] = X[col].mask(unknown, X_parents[parent_col])
# Impute missing with parent
if self.handle_missing == "value":
X[col] = X[col].mask(missing, X_parents[parent_col])
# Randomization is meaningful only for training data -> we do it only if y is present
if self.randomized and y is not None:
random_state_generator = check_random_state(self.random_state)
X[col] = X[col] * random_state_generator.normal(
1.0, self.sigma, X[col].shape[0])
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns
-------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError(
"Estimator has to be fitted to return feature names.")
else:
return self.feature_names
class OneHotEncoder(BaseEstimator, TransformerMixin):
"""Onehot (or dummy) coding for categorical features, produces one feature per category, each binary.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
impute_missing: bool
boolean for whether or not to apply the logic for handle_unknown, will be deprecated in the future.
handle_unknown: str
options are 'error', 'ignore' and 'impute', defaults to 'impute', which will impute the category -1. Warning: if
impute is used, an extra column will be added in if the transform matrix has unknown categories. This can causes
unexpected changes in dimension in some cases.
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = OneHotEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 22 columns):
CHAS_0 506 non-null int64
CHAS_1 506 non-null int64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
RAD_4 506 non-null int64
RAD_5 506 non-null int64
RAD_6 506 non-null int64
RAD_7 506 non-null int64
RAD_8 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(11)
memory usage: 87.0 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
http://www.ats.ucla.edu/stat/r/library/contrast_coding.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(
self, verbose=0, cols=None, drop_invariant=False, return_df=True, impute_missing=True, handle_unknown="impute"
):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.impute_missing = impute_missing
self.handle_unknown = handle_unknown
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose, cols=self.cols, impute_missing=self.impute_missing, handle_unknown=self.handle_unknown
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError("Must train encoder before it can be used to transform data.")
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError("Unexpected input dimension %d, expected %d" % (X.shape[1], self._dim))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.get_dummies(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
@staticmethod
def get_dummies(X_in, cols=None):
"""
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
classes = [x for x in set(X[col].values.tolist()) if np.isfinite(x)]
for class_ in classes:
n_col_name = str(col) + "_%s" % (class_,)
X[n_col_name] = X[col] == class_
bin_cols.append(n_col_name)
X = X.reindex(columns=bin_cols + pass_thru)
# convert all of the bools into integers.
for col in bin_cols:
X[col] = X[col].astype(int)
return X
class QuantileEncoder(BaseEstimator, util.TransformerWithTargetMixin):
"""Quantile Encoding for categorical features.
This a statistically modified version of target MEstimate encoder where selected features
are replaced the statistical quantile instead than the mean. Replacing with the
median is a particular case where self.quantile = 0.5. In comparison to MEstimateEncoder
it has two tunable parameter `m` and `quantile`
Parameters
----------
verbose: int
integer indicating verbosity of the output. 0 for none.
quantile: int
integer indicating statistical quantile. ´0.5´ for median.
m: int
integer indicating the smoothing parameter. 0 for no smoothing.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_missing: str
options are 'error', 'return_nan' and 'value', defaults to 'value', which returns the target quantile.
handle_unknown: str
options are 'error', 'return_nan' and 'value', defaults to 'value', which returns the target quantile.
Example
-------
>>> from sktools import QuantileEncoder
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = QuantileEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 13 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(13)
memory usage: 51.5 KB
None
References
----------
.. [1] Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems, https://arxiv.org/abs/2105.13783
.. [2] A Preprocessing Scheme for High-Cardinality Categorical Attributes in Classification and Prediction Problems, equation 7, from https://dl.acm.org/citation.cfm?id=507538
.. [3] On estimating probabilities in tree pruning, equation 1, from https://link.springer.com/chapter/10.1007/BFb0017010
.. [4] Additive smoothing, from https://en.wikipedia.org/wiki/Additive_smoothing#Generalized_to_the_case_of_known_incidence_rates
.. [5] Target encoding done the right way https://maxhalford.github.io/blog/target-encoding/
"""
def __init__(
self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True,
handle_missing="value",
handle_unknown="value",
quantile=0.5,
m=1.0,
):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self.feature_names = None
self.quantile = quantile
self.m = m
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# unite the input into pandas types
X = util.convert_input(X)
y = util.convert_input_vector(y, X.index)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) +
" but length of y is " + str(y.shape[0]) + ".")
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == "error":
if X[self.cols].isnull().any().any():
raise ValueError("Columns to be encoded can not contain null")
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown="value",
handle_missing="value",
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
self.mapping = self.fit_quantile_encoding(X_ordinal, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = list(X_temp.columns)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [
x for x in generated_cols if X_temp[x].var() <= 10e-5
]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def fit_quantile_encoding(self, X, y):
mapping = {}
# Calculate global statistics
prior = self._quantile = np.quantile(y, self.quantile)
self._sum = y.sum()
self._count = y.count()
for switch in self.ordinal_encoder.category_mapping:
col = switch.get("col")
values = switch.get("mapping")
# Calculate sum, count and quantile of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(
[lambda x: np.quantile(x, self.quantile), "sum", "count"])
stats.columns = ["quantile", "sum", "count"]
# Calculate the m-probability estimate of the quantile
estimate = (stats["count"] * stats["quantile"] +
prior * self.m) / (stats["count"] + self.m)
if self.handle_unknown == "return_nan":
estimate.loc[-1] = np.nan
elif self.handle_unknown == "value":
estimate.loc[-1] = prior
if self.handle_missing == "return_nan":
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == "value":
estimate.loc[-2] = prior
mapping[col] = estimate
return mapping
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target info (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == "error":
if X[self.cols].isnull().any().any():
raise ValueError("Columns to be encoded can not contain null")
if self._dim is None:
raise ValueError(
"Must train encoder before it can be used to transform data.")
# unite the input into pandas types
X = util.convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError("Unexpected input dimension %d, expected %d" % (
X.shape[1],
self._dim,
))
# if we are encoding the training data, we have to check the target
if y is not None:
y = util.convert_input_vector(y, X.index)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) +
" but length of y is " + str(y.shape[0]) +
".")
if not list(self.cols):
return X
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == "error":
if X[self.cols].isin([-1]).any().any():
raise ValueError("Unexpected categories found in dataframe")
X = self.quantile_encode(X)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def quantile_encode(self, X_in):
X = X_in.copy(deep=True)
for col in self.cols:
X[col] = X[col].map(self.mapping[col])
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns
-------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError(
"Must fit data first. Affected feature names are not known "
"before.")
else:
return self.feature_names
class SumEncoder(BaseEstimator, TransformerMixin):
"""Sum contrast coding for the encoding of categorical features.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_unknown: str
options are 'error', 'return_nan' and 'value', defaults to 'value'. Warning: if value is used,
an extra column will be added in if the transform matrix has unknown categories. This can cause
unexpected changes in the dimension in some cases.
handle_missing: str
options are 'error', 'return_nan', 'value', and 'indicator', defaults to 'indicator'. Warning: if indicator is used,
an extra column will be added in if the transform matrix has unknown categories. This can cause
unexpected changes in dimension in some cases.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = SumEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 21 columns):
intercept 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS_0 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD_0 506 non-null float64
RAD_1 506 non-null float64
RAD_2 506 non-null float64
RAD_3 506 non-null float64
RAD_4 506 non-null float64
RAD_5 506 non-null float64
RAD_6 506 non-null float64
RAD_7 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(20), int64(1)
memory usage: 83.1 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self, verbose=0, cols=None, mapping=None, drop_invariant=False, return_df=True,
handle_unknown='value', handle_missing='value'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.mapping = mapping
self.handle_unknown = handle_unknown
self.handle_missing=handle_missing
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.feature_names = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
X = util.convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
ordinal_mapping = self.ordinal_encoder.category_mapping
mappings_out = []
for switch in ordinal_mapping:
values = switch.get('mapping')
col = switch.get('col')
column_mapping = self.fit_sum_coding(col, values, self.handle_missing, self.handle_unknown)
mappings_out.append({'col': switch.get('col'), 'mapping': column_mapping, })
self.mapping = mappings_out
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = util.convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Columns to be encoded can not contain new values')
X = self.sum_coding(X, mapping=self.mapping)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
@staticmethod
def fit_sum_coding(col, values, handle_missing, handle_unknown):
if handle_missing == 'value':
values = values[values > 0]
values_to_encode = values.get_values()
if len(values) < 2:
return pd.DataFrame(index=values_to_encode)
if handle_unknown == 'indicator':
values_to_encode = np.append(values_to_encode, -1)
sum_contrast_matrix = Sum().code_without_intercept(values_to_encode.tolist())
df = pd.DataFrame(data=sum_contrast_matrix.matrix, index=values_to_encode,
columns=[str(col) + '_%d' % (i, ) for i in range(len(sum_contrast_matrix.column_suffixes))])
if handle_unknown == 'return_nan':
df.loc[-1] = np.nan
elif handle_unknown == 'value':
df.loc[-1] = np.zeros(len(values_to_encode) - 1)
if handle_missing == 'return_nan':
df.loc[values.loc[np.nan]] = np.nan
elif handle_missing == 'value':
df.loc[-2] = np.zeros(len(values_to_encode) - 1)
return df
@staticmethod
def sum_coding(X_in, mapping):
"""
"""
X = X_in.copy(deep=True)
cols = X.columns.values.tolist()
X['intercept'] = pd.Series([1] * X.shape[0], index=X.index)
for switch in mapping:
col = switch.get('col')
mod = switch.get('mapping')
base_df = mod.loc[X[col]]
base_df.set_index(X.index, inplace=True)
X = pd.concat([base_df, X], axis=1)
old_column_index = cols.index(col)
cols[old_column_index: old_column_index + 1] = mod.columns
cols = ['intercept'] + cols
return X.reindex(columns=cols)
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns:
--------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError("Estimator has to be fitted to return feature names.")
else:
return self.feature_names
class SVDEncoder(BaseEstimator, TransformerMixin):
def __init__(
self,
cols=None,
handle_missing='value',
handle_unknown='value',
use_cat_names=False,
return_df=True,
use_target=False,
n_components=1.
):
self.cols = cols
self.handle_missing = handle_missing
self.handle_unknown = handle_unknown
self.use_cat_names = use_cat_names
self.return_df = return_df
self.use_target = use_target
self.n_components = n_components
def fit(self, X, y=None):
self._dim = X.shape[1]
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
self.mapping = self.generate_mapping(X, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = list(X_temp.columns)
return self
def generate_mapping(self, X, y=None):
X = X.copy(deep=True)
if self.use_target:
X['target'] = y.values
mapping = []
for switch in self.ordinal_encoder.mapping:
col = switch.get('col')
values = switch.get('mapping').copy(deep=True)
base_df = (
X
.drop(columns=set(self.cols) - {col})
.groupby(col)
.mean()
)
if isinstance(self.n_components, float):
n_components = round(base_df.shape[1] * self.n_components)
else:
n_components = self.n_components
if n_components == 0:
continue
if n_components < base_df.shape[1]:
svd = TruncatedSVD(n_components=n_components)
base_svd = svd.fit_transform(base_df)
base_df = pd.DataFrame(
data=base_svd,
index=base_df.index,
columns=['svd_{}'.format(i) for i in range(base_svd.shape[1])]
)
base_df = (
base_df
.join(values.rename('idx'), how='right')
.set_index('idx')
)
base_df.columns = ['{}_mean_over_{}'.format(i, col) for i in base_df.columns]
if self.handle_unknown == 'value':
base_df.loc[-1] = 0
elif self.handle_unknown == 'return_nan':
base_df.loc[-1] = np.nan
if self.handle_missing == 'return_nan':
base_df.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
base_df.loc[-2] = 0
mapping.append({'col': col, 'mapping': base_df})
return mapping
def transform(self, X, override_return_df=False):
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1], self._dim, ))
if not list(self.cols):
return X if self.return_df else X.values
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Columns to be encoded can not contain new values')
X = self.get_dummies(X)
if self.return_df or override_return_df:
return X
else:
return X.values
def get_dummies(self, X_in):
X = X_in.copy(deep=True)
cols = X.columns.values.tolist()
for switch in self.mapping:
col = switch.get('col')
mod = switch.get('mapping')
base_df = mod.reindex(X[col])
base_df = base_df.set_index(X.index)
X = pd.concat([base_df, X], axis=1)
old_column_index = cols.index(col)
cols[old_column_index: old_column_index + 1] = mod.columns
X = X.reindex(columns=cols)
return X
def get_feature_names(self):
if not isinstance(self.feature_names, list):
raise ValueError(
'Must transform data first. Affected feature names are not known before.')
else:
return self.feature_names
class WOEEncoder(BaseEstimator, TransformerMixin):
"""Weight of Evidence coding for categorical features.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_unknown: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which will assume WOE=0.
randomized: bool,
adds normal (Gaussian) distribution noise into training data in order to decrease overfitting (testing data are untouched).
sigma: float
standard deviation (spread or "width") of the normal distribution.
regularization: float
the purpose of regularization is mostly to prevent division by zero.
When regularization is 0, you may encounter division by zero.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target > 22.5
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = WOEEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 13 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(13)
memory usage: 51.5 KB
None
References
----------
.. [1] Weight of Evidence (WOE) and Information Value Explained. from
https://www.listendata.com/2015/03/weight-of-evidence-woe-and-information.html.
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True,
handle_unknown='value', handle_missing='value', random_state=None, randomized=False, sigma=0.05, regularization=1.0):
self.verbose = verbose
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self._sum = None
self._count = None
self.random_state = random_state
self.randomized = randomized
self.sigma = sigma
self.regularization = regularization
self.feature_names = None
# noinspection PyUnusedLocal
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and binary y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Binary target values.
Returns
-------
self : encoder
Returns self.
"""
# Unite parameters into pandas types
X = util.convert_input(X)
y = util.convert_input_vector(y, X.index).astype(float)
# The lengths must be equal
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
# The label must be binary with values {0,1}
unique = y.unique()
if len(unique) != 2:
raise ValueError("The target column y must be binary. But the target contains " + str(len(unique)) + " unique value(s).")
if y.isnull().any():
raise ValueError("The target column y must not contain missing values.")
if np.max(unique) < 1:
raise ValueError("The target column y must be binary with values {0, 1}. Value 1 was not found in the target.")
if np.min(unique) > 0:
raise ValueError("The target column y must be binary with values {0, 1}. Value 0 was not found in the target.")
self._dim = X.shape[1]
# If columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
# Training
self.mapping = self._train(X_ordinal, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
# Store column names with approximately constant variance on the training data
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data. When the data are used for model training,
it is important to also pass the target in order to apply leave one out.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target information (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# Unite the input into pandas types
X = util.convert_input(X)
# Then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
# If we are encoding the training data, we have to check the target
if y is not None:
y = util.convert_input_vector(y, X.index).astype(float)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
if not self.cols:
return X
# Do not modify the input argument
X = X.copy(deep=True)
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Unexpected categories found in dataframe')
# Loop over columns and replace nominal values with WOE
X = self._score(X, y)
# Postprocessing
# Note: We should not even convert these columns.
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def fit_transform(self, X, y=None, **fit_params):
"""
Encoders that utilize the target must make sure that the training data are transformed with:
transform(X, y)
and not with:
transform(X)
"""
return self.fit(X, y, **fit_params).transform(X, y)
def _train(self, X, y):
# Initialize the output
mapping = {}
# Calculate global statistics
self._sum = y.sum()
self._count = y.count()
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['sum', 'count']) # Count of x_{i,+} and x_i
# Create a new column with regularized WOE.
# Regularization helps to avoid division by zero.
# Pre-calculate WOEs because logarithms are slow.
nominator = (stats['sum'] + self.regularization) / (self._sum + 2*self.regularization)
denominator = ((stats['count'] - stats['sum']) + self.regularization) / (self._count - self._sum + 2*self.regularization)
woe = np.log(nominator / denominator)
# Ignore unique values. This helps to prevent overfitting on id-like columns.
woe[stats['count'] == 1] = 0
if self.handle_unknown == 'return_nan':
woe.loc[-1] = np.nan
elif self.handle_unknown == 'value':
woe.loc[-1] = 0
if self.handle_missing == 'return_nan':
woe.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
woe.loc[-2] = 0
# Store WOE for transform() function
mapping[col] = woe
return mapping
def _score(self, X, y):
for col in self.cols:
# Score the column
X[col] = X[col].map(self.mapping[col])
# Randomization is meaningful only for training data -> we do it only if y is present
if self.randomized and y is not None:
random_state_generator = check_random_state(self.random_state)
X[col] = (X[col] * random_state_generator.normal(1., self.sigma, X[col].shape[0]))
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns:
--------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError("Estimator has to be fitted to return feature names.")
else:
return self.feature_names
class HelmertEncoder(BaseEstimator, TransformerMixin):
"""Helmert contrast coding for encoding categorical features
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = HelmertEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 22 columns):
col_CHAS_0 506 non-null float64
col_CHAS_1 506 non-null float64
col_RAD_0 506 non-null float64
col_RAD_1 506 non-null float64
col_RAD_2 506 non-null float64
col_RAD_3 506 non-null float64
col_RAD_4 506 non-null float64
col_RAD_5 506 non-null float64
col_RAD_6 506 non-null float64
col_RAD_7 506 non-null float64
col_RAD_8 506 non-null float64
col_CRIM 506 non-null float64
col_ZN 506 non-null float64
col_INDUS 506 non-null float64
col_NOX 506 non-null float64
col_RM 506 non-null float64
col_AGE 506 non-null float64
col_DIS 506 non-null float64
col_TAX 506 non-null float64
col_PTRATIO 506 non-null float64
col_B 506 non-null float64
col_LSTAT 506 non-null float64
dtypes: float64(22)
memory usage: 87.0 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
http://www.ats.ucla.edu/stat/r/library/contrast_coding.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose, cols=self.cols)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.helmert_coding(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
@staticmethod
def helmert_coding(X_in, cols=None):
"""
"""
X = X_in.copy(deep=True)
X.columns = ['col_' + str(x) for x in X.columns.values]
cols = ['col_' + str(x) for x in cols]
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
mod = dmatrix("C(%s, Helmert)" % (col, ), X)
for dig in range(len(mod[0])):
X[str(col) + '_%d' % (dig, )] = mod[:, dig]
bin_cols.append(str(col) + '_%d' % (dig, ))
X = X.reindex(columns=bin_cols + pass_thru)
return X
class MEstimateEncoder(BaseEstimator, TransformerMixin):
"""M-probability estimate of likelihood.
This is a simplified version of target encoder. In comparison to target encoder, m-probability estimate
has only one tunable parameter ('m'), while target encoder has two tunable parameters ('min_samples_leaf'
and 'smoothing').
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop encoded columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_missing: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns the prior probability.
handle_unknown: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns the prior probability.
randomized: bool,
adds normal (Gaussian) distribution noise into training data in order to decrease overfitting (testing data are untouched).
sigma: float
standard deviation (spread or "width") of the normal distribution.
m: float
this is the "m" in the m-probability estimate. Higher value of m results into stronger shrinking.
M is non-negative.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target > 22.5
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = MEstimateEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 13 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(13)
memory usage: 51.5 KB
None
References
----------
.. [1] A Preprocessing Scheme for High-Cardinality Categorical Attributes in Classification and Prediction Problems, equation 7, from
https://dl.acm.org/citation.cfm?id=507538.
..[2] Additive smoothing, from
https://en.wikipedia.org/wiki/Additive_smoothing#Generalized_to_the_case_of_known_incidence_rates
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True,
handle_unknown='value', handle_missing='value', random_state=None, randomized=False, sigma=0.05, m=1.0):
self.verbose = verbose
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self._sum = None
self._count = None
self.random_state = random_state
self.randomized = randomized
self.sigma = sigma
self.m = m
self.feature_names = None
# noinspection PyUnusedLocal
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and binary y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Binary target values.
Returns
-------
self : encoder
Returns self.
"""
# Unite parameters into pandas types
X = util.convert_input(X)
y = util.convert_input_vector(y, X.index).astype(float)
# The lengths must be equal
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
self._dim = X.shape[1]
# If columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
# Training
self.mapping = self._train(X_ordinal, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
# Store column names with approximately constant variance on the training data
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data. When the data are used for model training,
it is important to also pass the target in order to apply leave one out.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target information (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# Unite the input into pandas types
X = util.convert_input(X)
# Then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
# If we are encoding the training data, we have to check the target
if y is not None:
y = util.convert_input_vector(y, X.index).astype(float)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
if not self.cols:
return X
# Do not modify the input argument
X = X.copy(deep=True)
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Unexpected categories found in dataframe')
# Loop over columns and replace nominal values with WOE
X = self._score(X, y)
# Postprocessing
# Note: We should not even convert these columns.
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def fit_transform(self, X, y=None, **fit_params):
"""
Encoders that utilize the target must make sure that the training data are transformed with:
transform(X, y)
and not with:
transform(X)
"""
return self.fit(X, y, **fit_params).transform(X, y)
def _train(self, X, y):
# Initialize the output
mapping = {}
# Calculate global statistics
self._sum = y.sum()
self._count = y.count()
prior = self._sum/self._count
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['sum', 'count']) # Count of x_{i,+} and x_i
# Calculate the m-probability estimate
estimate = (stats['sum'] + prior * self.m) / (self._sum + self.m)
# Ignore unique values. This helps to prevent overfitting on id-like columns
if len(stats['count'])==self._count:
estimate[:] = prior
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = prior
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = prior
# Store the m-probability estimate for transform() function
mapping[col] = estimate
return mapping
def _score(self, X, y):
for col in self.cols:
# Score the column
X[col] = X[col].map(self.mapping[col])
# Randomization is meaningful only for training data -> we do it only if y is present
if self.randomized and y is not None:
random_state_generator = check_random_state(self.random_state)
X[col] = (X[col] * random_state_generator.normal(1., self.sigma, X[col].shape[0]))
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns:
--------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError("Estimator has to be fitted to return feature names.")
else:
return self.feature_names
class GLMMEncoder(BaseEstimator, util.TransformerWithTargetMixin):
"""Generalized linear mixed model.
This is a supervised encoder similar to TargetEncoder or MEstimateEncoder, but there are some advantages:
1) Solid statistical theory behind the technique. Mixed effects models are a mature branch of statistics.
2) No hyper-parameters to tune. The amount of shrinkage is automatically determined through the estimation process.
In short, the less observations a category has and/or the more the outcome varies for a category
then the higher the regularization towards "the prior" or "grand mean".
3) The technique is applicable for both continuous and binomial targets. If the target is continuous,
the encoder returns regularized difference of the observation's category from the global mean.
If the target is binomial, the encoder returns regularized log odds per category.
In comparison to JamesSteinEstimator, this encoder utilizes generalized linear mixed models from statsmodels library.
Note: This is an alpha implementation. The API of the method may change in the future.
Parameters
----------
verbose: int
integer indicating verbosity of the output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop encoded columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_missing: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns 0.
handle_unknown: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns 0.
randomized: bool,
adds normal (Gaussian) distribution noise into training data in order to decrease overfitting (testing data are untouched).
sigma: float
standard deviation (spread or "width") of the normal distribution.
binomial_target: bool
if True, the target must be binomial with values {0, 1} and Binomial mixed model is used.
If False, the target must be continuous and Linear mixed model is used.
If None (the default), a heuristic is applied to estimate the target type.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target > 22.5
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = GLMMEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 13 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(13)
memory usage: 51.5 KB
None
References
----------
.. [1] Data Analysis Using Regression and Multilevel/Hierarchical Models, page 253, from
https://faculty.psau.edu.sa/filedownload/doc-12-pdf-a1997d0d31f84d13c1cdc44ac39a8f2c-original.pdf
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, handle_unknown='value', handle_missing='value', random_state=None, randomized=False, sigma=0.05, binomial_target=None):
self.verbose = verbose
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self.random_state = random_state
self.randomized = randomized
self.sigma = sigma
self.binomial_target = binomial_target
self.feature_names = None
# noinspection PyUnusedLocal
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and binary y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Binary target values.
Returns
-------
self : encoder
Returns self.
"""
# Unite parameters into pandas types
X = util.convert_input(X)
y = util.convert_input_vector(y, X.index).astype(float)
# The lengths must be equal
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
self._dim = X.shape[1]
# If columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
# Training
self.mapping = self._train(X_ordinal, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
# Store column names with approximately constant variance on the training data
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data.
When the data are used for model training, it is important to also pass the target in order to apply leave one out.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target information (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# Unite the input into pandas types
X = util.convert_input(X)
# Then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
# If we are encoding the training data, we have to check the target
if y is not None:
y = util.convert_input_vector(y, X.index).astype(float)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
if not list(self.cols):
return X
# Do not modify the input argument
X = X.copy(deep=True)
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Unexpected categories found in dataframe')
# Loop over the columns and replace the nominal values with the numbers
X = self._score(X, y)
# Postprocessing
# Note: We should not even convert these columns.
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def _train(self, X, y):
# Initialize the output
mapping = {}
# Estimate target type, if necessary
if self.binomial_target is None:
if len(y.unique()) <= 2:
binomial_target = True
else:
binomial_target = False
else:
binomial_target = self.binomial_target
# The estimation does not have to converge -> at least converge to the same value.
np.random.seed(2001)
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
data = self._rename_and_merge(X, y, col)
try:
with warnings.catch_warnings():
warnings.filterwarnings("ignore")
if binomial_target:
# Classification, returns (regularized) log odds per category as stored in vc_mean
# Note: md.predict() returns: output = fe_mean + vcp_mean + vc_mean[category]
md = bgmm.from_formula('target ~ 1', {'a': '0 + C(feature)'}, data).fit_vb()
index_names = [int(float(re.sub(r'C\(feature\)\[(\S+)\]', r'\1', index_name))) for index_name in md.model.vc_names]
estimate = pd.Series(md.vc_mean, index=index_names)
else:
# Regression, returns (regularized) mean deviation of the observation's category from the global mean
md = smf.mixedlm('target ~ 1', data, groups=data['feature']).fit()
tmp = dict()
for key, value in md.random_effects.items():
tmp[key] = value[0]
estimate = pd.Series(tmp)
except np.linalg.LinAlgError:
# Singular matrix -> just return all zeros
estimate = pd.Series(np.zeros(len(values)), index=values)
# Ignore unique columns. This helps to prevent overfitting on id-like columns
if len(X[col].unique()) == len(y):
estimate[:] = 0
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = 0
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = 0
mapping[col] = estimate
return mapping
def _score(self, X, y):
for col in self.cols:
# Score the column
X[col] = X[col].map(self.mapping[col])
# Randomization is meaningful only for training data -> we do it only if y is present
if self.randomized and y is not None:
random_state_generator = check_random_state(self.random_state)
X[col] = (X[col] * random_state_generator.normal(1., self.sigma, X[col].shape[0]))
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns
-------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError("Estimator has to be fitted to return feature names.")
else:
return self.feature_names
def _rename_and_merge(self, X, y, col):
"""
Statsmodels requires:
1) unique column names
2) non-numeric columns names
Solution: internally rename the columns.
"""
merged = pd.DataFrame()
merged['feature'] = X[col]
merged['target'] = y
return merged
class JamesSteinEncoder(BaseEstimator, TransformerMixin):
"""James-Stein estimator.
For feature value `i`, James-Stein estimator returns a weighted average of:
1. The mean target value for the observed feature value `i`.
2. The mean target value (regardless of the feature value).
This can be written as::
JS_i = (1-B)*mean(y_i) + B*mean(y)
The question is, what should be the weight `B`?
If we put too much weight on the conditional mean value, we will overfit.
If we put too much weight on the global mean, we will underfit.
The canonical solution in machine learning is to perform cross-validation.
However, Charles Stein came with a closed-form solution to the problem.
The intuition is: If the estimate of `mean(y_i)` is unreliable (`y_i` has high variance),
we should put more weight on `mean(y)`. Stein put it into an equation as::
B = var(y_i) / (var(y_i)+var(y))
The only remaining issue is that we do not know `var(y)`, let alone `var(y_i)`.
Hence, we have to estimate the variances. But how can we reliably estimate the
variances, when we already struggle with the estimation of the mean values?!
There are multiple solutions:
1. If we have the same count of observations for each feature value `i` and all
`y_i` are close to each other, we can pretend that all `var(y_i)` are identical.
This is called a pooled model.
2. If the observation counts are not equal, it makes sense to replace the variances
with squared standard errors, which penalize small observation counts::
SE^2 = var(y)/count(y)
This is called an independent model.
James-Stein estimator has, however, one practical limitation - it was defined
only for normal distributions. If you want to apply it for binary classification,
which allows only values {0, 1}, it is better to first convert the mean target value
from the bound interval <0,1> into an unbounded interval by replacing mean(y)
with log-odds ratio::
log-odds_ratio_i = log(mean(y_i)/mean(y_not_i))
This is called binary model. The estimation of parameters of this model is, however,
tricky and sometimes it fails fatally. In these situations, it is better to use beta
model, which generally delivers slightly worse accuracy than binary model but does
not suffer from fatal failures.
Parameters
----------
verbose: int
integer indicating verbosity of the output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop encoded columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_missing: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns the prior probability.
handle_unknown: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns the prior probability.
model: str
options are 'pooled', 'beta', 'binary' and 'independent', defaults to 'independent'.
randomized: bool,
adds normal (Gaussian) distribution noise into training data in order to decrease overfitting (testing data are untouched).
sigma: float
standard deviation (spread or "width") of the normal distribution.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = JamesSteinEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 13 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(13)
memory usage: 51.5 KB
None
References
----------
.. [1] Parametric empirical Bayes inference: Theory and applications, equations 1.19 & 1.20, from
https://www.jstor.org/stable/2287098
.. [2] Empirical Bayes for multiple sample sizes, from
http://chris-said.io/2017/05/03/empirical-bayes-for-multiple-sample-sizes/
.. [3] Shrinkage Estimation of Log-odds Ratios for Comparing Mobility Tables, from
https://journals.sagepub.com/doi/abs/10.1177/0081175015570097
.. [4] Stein's paradox and group rationality, from
http://www.philos.rug.nl/~romeyn/presentation/2017_romeijn_-_Paris_Stein.pdf
.. [5] Stein's Paradox in Statistics, from
http://statweb.stanford.edu/~ckirby/brad/other/Article1977.pdf
"""
def __init__(self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True,
handle_unknown='value',
handle_missing='value',
model='independent',
random_state=None,
randomized=False,
sigma=0.05):
self.verbose = verbose
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self.random_state = random_state
self.randomized = randomized
self.sigma = sigma
self.model = model
self.feature_names = None
# noinspection PyUnusedLocal
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and binary y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Binary target values.
Returns
-------
self : encoder
Returns self.
"""
# Unite parameters into pandas types
X = util.convert_input(X)
y = util.convert_input_vector(y, X.index).astype(float)
# The lengths must be equal
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) +
" but length of y is " + str(y.shape[0]) + ".")
self._dim = X.shape[1]
# If columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value')
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
# Training
if self.model == 'independent':
self.mapping = self._train_independent(X_ordinal, y)
elif self.model == 'pooled':
self.mapping = self._train_pooled(X_ordinal, y)
elif self.model == 'beta':
self.mapping = self._train_beta(X_ordinal, y)
elif self.model == 'binary':
# The label must be binary with values {0,1}
unique = y.unique()
if len(unique) != 2:
raise ValueError(
"The target column y must be binary. But the target contains "
+ str(len(unique)) + " unique value(s).")
if y.isnull().any():
raise ValueError(
"The target column y must not contain missing values.")
if np.max(unique) < 1:
raise ValueError(
"The target column y must be binary with values {0, 1}. Value 1 was not found in the target."
)
if np.min(unique) > 0:
raise ValueError(
"The target column y must be binary with values {0, 1}. Value 0 was not found in the target."
)
# Perform the training
self.mapping = self._train_log_odds_ratio(X_ordinal, y)
else:
raise ValueError("model='" + str(self.model) +
"' is not a recognized option")
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
# Store column names with approximately constant variance on the training data
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [
x for x in generated_cols if X_temp[x].var() <= 10e-5
]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data. When the data are used for model training,
it is important to also pass the target in order to apply leave one out.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target information (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# Unite the input into pandas types
X = util.convert_input(X)
# Then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
# If we are encoding the training data, we have to check the target
if y is not None:
y = util.convert_input_vector(y, X.index).astype(float)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) +
" but length of y is " + str(y.shape[0]) +
".")
if not self.cols:
return X
# Do not modify the input argument
X = X.copy(deep=True)
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Unexpected categories found in dataframe')
# Loop over columns and replace nominal values with WOE
X = self._score(X, y)
# Postprocessing
# Note: We should not even convert these columns.
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def fit_transform(self, X, y=None, **fit_params):
"""
Encoders that utilize the target must make sure that the training data are transformed with:
transform(X, y)
and not with:
transform(X)
"""
# the interface requires 'y=None' in the signature but we need 'y'
if y is None:
raise (TypeError, 'fit_transform() missing argument: ' 'y' '')
return self.fit(X, y, **fit_params).transform(X, y)
def _train_pooled(self, X, y):
# Implemented based on reference [1]
# Initialize the output
mapping = {}
# Calculate global statistics
prior = y.mean()
target_var = y.var()
global_count = len(y)
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['mean', 'count'])
# See: Computer Age Statistical Inference: Algorithms, Evidence, and Data Science (Bradley Efron & Trevor Hastie, 2016)
# Equations 7.19 and 7.20.
# Note: The equations assume normal distribution of the label. But our label is p(y|x),
# which is definitely not normally distributed as probabilities are bound to lie on interval 0..1.
# We make this approximation because Efron does it as well.
# Equation 7.19
# Explanation of the equation:
# https://stats.stackexchange.com/questions/191444/variance-in-estimating-p-for-a-binomial-distribution
# if stats['count'].var() > 0:
# warnings.warn('The pooled model assumes that each category is observed exactly N times. This was violated in "' + str(col) +'" column. Consider comparing the accuracy of this model to "independent" model.')
# This is a parametric estimate of var(p) in the binomial distribution.
# We do not use it because we also want to support non-binary targets.
# The difference in the estimates is small.
# variance = prior * (1 - prior) / stats['count'].mean()
# This is a squared estimate of standard error of the mean:
# https://en.wikipedia.org/wiki/Standard_error
variance = target_var / (stats['count'].mean())
# Equation 7.20
SSE = ((stats['mean'] - prior)**2).sum() # Sum of Squared Errors
if SSE > 0: # We have to avoid division by zero
B = ((len(stats['count']) - 3) * variance) / SSE
B = B.clip(0, 1)
estimate = prior + (1 - B) * (stats['mean'] - prior)
else:
estimate = stats['mean']
# Ignore unique values. This helps to prevent overfitting on id-like columns
# This works better than: estimate[stats['count'] == 1] = prior
if len(stats['mean']) == global_count:
estimate[:] = prior
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = prior
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = prior
# Store the estimate for transform() function
mapping[col] = estimate
return mapping
def _train_independent(self, X, y):
# Implemented based on reference [2]
# Initialize the output
mapping = {}
# Calculate global statistics
prior = y.mean()
global_count = len(y)
global_var = y.var()
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['mean', 'var'])
i_var = stats['var'].fillna(
0) # When we do not have more than 1 sample, assume 0 variance
unique_cnt = len(X[col].unique())
# See: Parametric Empirical Bayes Inference: Theory and Applications (Morris, 1983)
# Equations 1.19 and 1.20.
# Note: The equations assume normal distribution of the label. But our label is p(y|x),
# which is definitely not normally distributed as probabilities are bound to lie on interval 0..1.
# Nevertheless, it seems to perform surprisingly well. This is in agreement with:
# Data Analysis with Stein's Estimator and Its Generalizations (Efron & Morris, 1975)
# The equations are similar to James-Stein estimator, as listed in:
# Stein's Paradox in Statistics (Efron & Morris, 1977)
# Or:
# Computer Age Statistical Inference: Algorithms, Evidence, and Data Science (Efron & Hastie, 2016)
# Equations 7.19 and 7.20.
# The difference is that they have equal count of observations per estimated variable, while we generally
# do not have that. Nice discussion about that is given at:
# http://chris-said.io/2017/05/03/empirical-bayes-for-multiple-sample-sizes/
smoothing = i_var / (global_var + i_var) * (unique_cnt -
3) / (unique_cnt - 1)
smoothing = 1 - smoothing
smoothing = smoothing.clip(
lower=0, upper=1) # Smoothing should be in the interval <0,1>
estimate = smoothing * (stats['mean']) + (1 - smoothing) * prior
# Ignore unique values. This helps to prevent overfitting on id-like columns
if len(stats['mean']) == global_count:
estimate[:] = prior
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = prior
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = prior
# Store the estimate for transform() function
mapping[col] = estimate
return mapping
def _train_log_odds_ratio(self, X, y):
# Implemented based on reference [3]
# Initialize the output
mapping = {}
# Calculate global statistics
global_sum = y.sum()
global_count = y.count()
# Iterative estimation of mu and sigma as given on page 9.
# This problem is traditionally solved with Newton-Raphson method:
# https://en.wikipedia.org/wiki/Newton%27s_method
# But we just use sklearn minimizer.
def get_best_sigma(sigma, mu_k, sigma_k, K):
global mu # Ugly. But I want to be able to read it once the optimization ends.
w_k = 1. / (sigma**2 + sigma_k**2) # Weights depends on sigma
mu = sum(w_k * mu_k) / sum(w_k) # Mu transitively depends on sigma
total = sum(w_k *
(mu_k - mu)**2) # We want this to be close to K-1
loss = abs(total - (K - 1))
return loss
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['sum', 'count'
]) # Count of x_{i,+} and x_i
# Create 2x2 contingency table
crosstable = pd.DataFrame()
crosstable['E-A-'] = global_count - stats['count'] + stats[
'sum'] - global_sum
crosstable['E-A+'] = stats['count'] - stats['sum']
crosstable['E+A-'] = global_sum - stats['sum']
crosstable['E+A+'] = stats['sum']
index = crosstable.index.values
crosstable = np.array(
crosstable,
dtype=np.float32) # The argument unites the types into float
# Count of contingency tables.
K = len(crosstable)
# Ignore id-like columns. This helps to prevent overfitting.
if K == global_count:
estimate = pd.Series(0, index=values)
else:
if K > 1: # We want to avoid division by zero in y_k calculation
# Estimate log-odds ratios with Yates correction as listed on page 5.
mu_k = np.log(
(crosstable[:, 0] + 0.5) * (crosstable[:, 3] + 0.5) /
((crosstable[:, 1] + 0.5) * (crosstable[:, 2] + 0.5)))
# Standard deviation estimate for 2x2 contingency table as given in equation 2.
# The explanation of the equation is given in:
# https://stats.stackexchange.com/questions/266098/how-do-i-calculate-the-standard-deviation-of-the-log-odds
sigma_k = np.sqrt(np.sum(1. / (crosstable + 0.5), axis=1))
# Estimate the sigma and mu. Sigma is non-negative.
result = scipy.optimize.minimize(get_best_sigma,
x0=1e-4,
args=(mu_k, sigma_k, K),
bounds=[(0, np.inf)],
method='TNC',
tol=1e-12,
options={
'gtol': 1e-12,
'ftol': 1e-12,
'eps': 1e-12
})
sigma = result.x[0]
# Empirical Bayes follows equation 7.
# However, James-Stein estimator behaves perversely when K < 3. Hence, we clip the B into interval <0,1>.
# Literature reference for the clipping:
# Estimates of Income for Small Places: An Application of James-Stein Procedures to Census Data (Fay & Harriout, 1979),
# page 270.
B = (K - 3) * sigma_k**2 / ((K - 1) *
(sigma**2 + sigma_k**2))
B = B.clip(0, 1)
y_k = mu + (1 - B) * (mu_k - mu)
# Convert Numpy vector back into Series
estimate = pd.Series(y_k, index=index)
else:
estimate = pd.Series(0, index=values)
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = 0
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = 0
# Store the estimate for transform() function
mapping[col] = estimate
return mapping
def _train_beta(self, X, y):
# Implemented based on reference [4]
# Initialize the output
mapping = {}
# Calculate global statistics
prior = y.mean()
global_count = len(y)
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['mean', 'count'])
# See: Stein's paradox and group rationality (Romeijn, 2017), page 14
smoothing = stats['count'] / (stats['count'] + global_count)
estimate = smoothing * (stats['mean']) + (1 - smoothing) * prior
# Ignore unique values. This helps to prevent overfitting on id-like columns
if len(stats['mean']) == global_count:
estimate[:] = prior
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = prior
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = prior
# Store the estimate for transform() function
mapping[col] = estimate
return mapping
def _score(self, X, y):
for col in self.cols:
# Score the column
X[col] = X[col].map(self.mapping[col])
# Randomization is meaningful only for training data -> we do it only if y is present
if self.randomized and y is not None:
random_state_generator = check_random_state(self.random_state)
X[col] = (X[col] * random_state_generator.normal(
1., self.sigma, X[col].shape[0]))
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns
-------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError(
"Estimator has to be fitted to return feature names.")
else:
return self.feature_names
class BinaryEncoder(BaseEstimator, TransformerMixin):
"""
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
Example
-------
>>> from category_encoders import BinaryEncoder
>>> from sklearn.datasets import fetch_20newsgroups_vectorized
>>> bunch = fetch_20newsgroups_vectorized(subset="all")
>>> X, y = bunch.data, bunch.target
>>> enc = BinaryEncoderr(return_df=False).fit(X, y)
>>> numeric_dataset = enc.transform(X)
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
if not isinstance(X, pd.DataFrame):
if isinstance(X, list):
X = pd.DataFrame(np.array(X))
elif isinstance(X, (np.generic, np.ndarray)):
X = pd.DataFrame(X)
else:
raise ValueError('Unexpected input type: %s' % (str(type(X))))
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose, cols=self.cols)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
if not isinstance(X, pd.DataFrame):
if isinstance(X, list):
X = pd.DataFrame(np.array(X))
elif isinstance(X, (np.generic, np.ndarray)):
X = pd.DataFrame(X)
else:
raise ValueError('Unexpected input type: %s' % (str(type(X))))
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.binary(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
def binary(self, X_in, cols=None):
"""
Binary encoding encodes the integers as binary code with one column per digit.
:param X:
:return:
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
# figure out how many digits we need to represent the classes present
digits = int(np.ceil(np.log2(len(X[col].unique()))))
# map the ordinal column into a list of these digits, of length digits
X[col] = X[col].map(lambda x: self.col_transform(x, digits))
for dig in range(digits):
X[col + '_%d' % (dig, )] = X[col].map(lambda x: int(x[dig]) if x is not None else None)
bin_cols.append(col + '_%d' % (dig, ))
X = X.reindex(columns=bin_cols + pass_thru)
return X
@staticmethod
def col_transform(col, digits):
"""
The lambda body to transform the column values
:param col:
:return:
"""
if col is None or float(col) < 0.0:
return None
else:
col = list("{0:b}".format(int(col)))
if len(col) == digits:
return col
else:
return [0 for _ in range(digits - len(col))] + col
class OneHotEncoder(BaseEstimator, TransformerMixin):
"""Onehot (or dummy) coding for categorical features, produces one feature per category, each binary.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
impute_missing: bool
boolean for whether or not to apply the logic for handle_unknown, will be deprecated in the future.
handle_unknown: str
options are 'error', 'ignore' and 'impute', defaults to 'impute', which will impute the category -1. Warning: if
impute is used, an extra column will be added in if the transform matrix has unknown categories. This can causes
unexpected changes in dimension in some cases.
use_cat_names: bool
if True, category values will be included in the encoded column names. otherwise category
indices will be used.
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = OneHotEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 22 columns):
CHAS_0 506 non-null int64
CHAS_1 506 non-null int64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
RAD_4 506 non-null int64
RAD_5 506 non-null int64
RAD_6 506 non-null int64
RAD_7 506 non-null int64
RAD_8 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(11)
memory usage: 87.0 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, impute_missing=True, handle_unknown='impute', use_cat_names=False):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.impute_missing = impute_missing
self.handle_unknown = handle_unknown
self.use_cat_names = use_cat_names
@property
def category_mapping(self):
return self.ordinal_encoder.category_mapping
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
impute_missing=self.impute_missing,
handle_unknown=self.handle_unknown
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
if not self.cols:
return X if self.return_df else X.values
X = self.ordinal_encoder.transform(X)
X = self.get_dummies(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
def inverse_transform(self, Xt):
"""
Perform the inverse transformation to encoded data.
Parameters
----------
X_in : array-like, shape = [n_samples, n_features]
Returns
-------
p: array, the same size of X_in
"""
X = Xt.copy(deep=True)
# first check the type
X = convert_input(X)
if self._dim is None:
raise ValueError('Must train encoder before it can be used to inverse_transform data')
X = self.reverse_dummies(X, self.cols)
# then make sure that it is the right size
if X.shape[1] != self._dim:
if self.drop_invariant:
raise ValueError("Unexpected input dimension %d, the attribute drop_invariant should "
"set as False when transform data"%(X.shape[1],))
else:
raise ValueError('Unexpected input dimension %d, expected %d'% (X.shape[1], self._dim, ))
if not self.cols:
return X if self.return_df else X.values
if self.impute_missing and self.handle_unknown == 'impute':
for col in self.cols:
if any(X[col] == 0):
raise ValueError("inverse_transform is not supported because transform impute "
"the unknown category -1 when encode %s"%(col,))
if not self.use_cat_names:
for switch in self.ordinal_encoder.mapping:
col_dict = {col_pair[1] : col_pair[0] for col_pair in switch.get('mapping')}
X[switch.get('col')] = X[switch.get('col')].apply(lambda x:col_dict.get(x))
return X if self.return_df else X.values
def get_dummies(self, X_in, cols=None):
"""
Convert numerical variable into dummy variables
Parameters
----------
X_in: DataFrame
cols: list-like, default None
Column names in the DataFrame to be encoded
Returns
-------
dummies : DataFrame
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
col_tuples = copy.deepcopy([class_map['mapping'] for class_map in self.ordinal_encoder.mapping if class_map['col'] == col][0])
if self.handle_unknown == 'impute':
col_tuples.append(('-1', -1))
for col_tuple in col_tuples:
class_ = col_tuple[1]
cat_name = col_tuple[0]
if self.use_cat_names:
n_col_name = str(col) + '_%s' % (cat_name, )
else:
n_col_name = str(col) + '_%s' % (class_, )
X[n_col_name] = X[col] == class_
bin_cols.append(n_col_name)
X = X.reindex(columns=bin_cols + pass_thru)
# convert all of the bools into integers.
for col in bin_cols:
X[col] = X[col].astype(int)
return X
def reverse_dummies(self, X, cols):
"""
Convert dummy variable into numerical variables
Parameters
----------
X : DataFrame
cols: list-like
Column names in the DataFrame that be encoded
Returns
-------
numerical: DataFrame
"""
out_cols = X.columns.values
for col in cols:
col_list = [col0 for col0 in out_cols if col0.startswith(col)]
if self.use_cat_names:
X[col] = 0
for tran_col in col_list:
val = tran_col.split('_')[1]
X.loc[X[tran_col] == 1, col] = val
else:
value_array = np.array([int(col0.split('_')[1]) for col0 in col_list])
X[col] = np.dot(X[col_list].values, value_array.T)
out_cols = [col0 for col0 in out_cols if col0 not in col_list]
X = X.reindex(columns=out_cols + cols)
return X
class HelmertEncoder(BaseEstimator, TransformerMixin):
"""
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
Example
-------
>>> from category_encoders import HelmertEncoder
>>> from sklearn.datasets import fetch_20newsgroups_vectorized
>>> bunch = fetch_20newsgroups_vectorized(subset="all")
>>> X, y = bunch.data, bunch.target
>>> enc = HelmertEncoder(return_df=False).fit(X, y)
>>> numeric_dataset = enc.transform(X)
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
http://www.ats.ucla.edu/stat/r/library/contrast_coding.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
if not isinstance(X, pd.DataFrame):
if isinstance(X, list):
X = pd.DataFrame(np.array(X))
elif isinstance(X, (np.generic, np.ndarray)):
X = pd.DataFrame(X)
else:
raise ValueError('Unexpected input type: %s' % (str(type(X))))
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose, cols=self.cols)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
if not isinstance(X, pd.DataFrame):
if isinstance(X, list):
X = pd.DataFrame(np.array(X))
elif isinstance(X, (np.generic, np.ndarray)):
X = pd.DataFrame(X)
else:
raise ValueError('Unexpected input type: %s' % (str(type(X))))
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.helmert_coding(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
@staticmethod
def helmert_coding(X_in, cols=None):
"""
:param X:
:return:
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
mod = dmatrix("C(%s, Helmert)" % (col, ), X)
for dig in range(len(mod[0])):
X[col + '_%d' % (dig, )] = mod[:, dig]
bin_cols.append(col + '_%d' % (dig, ))
X = X.reindex(columns=bin_cols + pass_thru)
return X
class TargetEncoder(BaseEstimator, TransformerMixin):
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, handle_missing='value',
handle_unknown='value', min_samples_leaf=1, smoothing=1.0):
"""Target encoding for categorical features.
For the case of categorical target: features are replaced with a blend of posterior probability of the target
given particular categorical value and prior probability of the target over all the training data.
For the case of continuous target: features are replaced with a blend of expected value of the target
given particular categorical value and expected value of the target over all the training data.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_unknown: str
options are 'error', 'return_nan' and 'value', defaults to 'value', which will impute the target mean.
min_samples_leaf: int
minimum samples to take category average into account.
smoothing: float
smoothing effect to balance categorical average vs prior. Higher value means stronger regularization.
The value must be strictly bigger than 0.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = TargetEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 13 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(13)
memory usage: 51.5 KB
None
References
----------
.. [1] A Preprocessing Scheme for High-Cardinality Categorical Attributes in Classification and Prediction Problems. from
https://kaggle2.blob.core.windows.net/forum-message-attachments/225952/7441/high%20cardinality%20categoricals.pdf.
"""
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self.min_samples_leaf = min_samples_leaf
self.smoothing = float(smoothing) # Make smoothing a float so that python 2 does not treat as integer division
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing=handle_missing
self._mean = None
self.feature_names = None
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = util.convert_input(X)
if isinstance(y, pd.DataFrame):
y = y.iloc[:, 0]
else:
y = pd.Series(y, name='target', index=X.index)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
self.mapping = self.fit_target_encoding(X_ordinal, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = list(X_temp.columns)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def fit_target_encoding(self, X, y):
mapping = {}
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
prior = self._mean = y.mean()
stats = y.groupby(X[col]).agg(['count', 'mean'])
smoove = 1 / (1 + np.exp(-(stats['count'] - self.min_samples_leaf) / self.smoothing))
smoothing = prior * (1 - smoove) + stats['mean'] * smoove
smoothing[stats['count'] == 1] = prior
if self.handle_unknown == 'return_nan':
smoothing.loc[-1] = np.nan
elif self.handle_unknown == 'value':
smoothing.loc[-1] = prior
if self.handle_missing == 'return_nan':
smoothing.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
smoothing.loc[-2] = prior
mapping[col] = smoothing
return mapping
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target info (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = util.convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
# if we are encoding the training data, we have to check the target
if y is not None:
if isinstance(y, pd.DataFrame):
y = y.iloc[:, 0]
else:
y = pd.Series(y, name='target')
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Unexpected categories found in dataframe')
X = self.target_encode(X)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def fit_transform(self, X, y=None, **fit_params):
"""
Encoders that utilize the target must make sure that the training data are transformed with:
transform(X, y)
and not with:
transform(X)
"""
return self.fit(X, y, **fit_params).transform(X, y)
def target_encode(self, X_in):
X = X_in.copy(deep=True)
for col in self.cols:
X[col] = X[col].map(self.mapping[col])
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns:
--------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError('Must fit data first. Affected feature names are not known before.')
else:
return self.feature_names
class InformativeEncoder(BaseEstimator, TransformerMixin):
def __init__(self,
cols=None,
handle_missing='value',
handle_unknown='value',
return_df=True,
max_subset_size=None,
max_subsets=None,
criterion='gini'):
self.cols = cols
self.handle_missing = handle_missing
self.handle_unknown = handle_unknown
self.return_df = return_df
self.max_subset_size = max_subset_size
self.max_subsets = max_subsets
self.criterion = criterion
def fit(self, X, y=None, **kwargs):
self._dim = X.shape[1]
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(cols=self.cols,
handle_unknown='value',
handle_missing='value')
self.ordinal_encoder = self.ordinal_encoder.fit(X)
self.mapping = self.generate_mapping(X, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = list(X_temp.columns)
return self
def generate_mapping(self, X=None, y=None):
mapping = []
if self.max_subsets is not None:
X = self.ordinal_encoder.transform(X)
for switch in self.ordinal_encoder.mapping:
col = switch.get('col')
values = switch.get('mapping').copy(deep=True)
if self.handle_missing == 'value':
values = values[values > 0]
if len(values) == 0:
continue
index = values.values
base_matrix = np.eye(len(values), dtype=np.int)
base_matrix = self.get_subsets(base_matrix)
new_columns = [
'{col}_{i}'.format(col=col, i=i)
for i in range(base_matrix.shape[1])
]
base_df = pd.DataFrame(data=base_matrix,
columns=new_columns,
index=index)
if self.max_subsets is not None:
y_sum = y.groupby(X[col]).sum().reindex(index).values
y_count = X.groupby(col).size().reindex(index).values
info = self.cut_info(base_df.values, y_sum, y_count)
if isinstance(self.max_subsets, float):
max_subsets = round(self.max_subsets * base_df.shape[0])
else:
max_subsets = self.max_subsets
base_matrix = base_matrix[:, np.argsort(info)][:, :max_subsets]
new_columns = [
'{col}_{i}'.format(col=col, i=i)
for i in range(base_matrix.shape[1])
]
base_df = pd.DataFrame(data=base_matrix,
columns=new_columns,
index=index)
if self.handle_unknown == 'value':
base_df.loc[-1] = 0
elif self.handle_unknown == 'return_nan':
base_df.loc[-1] = np.nan
if self.handle_missing == 'return_nan':
base_df.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
base_df.loc[-2] = 0
mapping.append({'col': col, 'mapping': base_df})
return mapping
def get_subsets(self, base_matrix):
max_subset_size = self.max_subset_size or base_matrix.shape[1]
subsets = base_matrix
for _ in range(1, max_subset_size):
subsets = base_matrix[:, :, np.newaxis] + subsets[:, np.newaxis, :]
subsets = np.unique(subsets.clip(0, 1).reshape(
base_matrix.shape[0], -1),
axis=1)
return subsets
def cut_info(self, subsets, y_sum, y_count):
sum_l = np.sum(subsets * y_sum[:, np.newaxis], axis=0)
count_l = np.sum(subsets * y_count[:, np.newaxis], axis=0)
p_l = sum_l / count_l
sum_r = np.sum((1 - subsets) * y_sum[:, np.newaxis], axis=0)
count_r = np.sum((1 - subsets) * y_count[:, np.newaxis], axis=0)
p_r = sum_r / count_r
crit_l, crit_r = self.compute_criterion(p_l, p_r)
return count_l * crit_l + count_r * crit_r
def compute_criterion(self, p_l, p_r):
if self.criterion == 'gini':
crit_l = 1. - p_l**2 - (1 - p_l)**2
crit_r = 1. - p_r**2 - (1 - p_r)**2
elif self.criterion == 'entropy':
crit_l = -(entropy(p_l) + entropy(1 - p_l))
crit_r = -(entropy(p_r) + entropy(1 - p_r))
else:
raise ValueError
return crit_l, crit_r
def transform(self, X, override_return_df=False):
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
if not list(self.cols):
return X if self.return_df else X.values
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError(
'Columns to be encoded can not contain new values')
X = self.get_dummies(X)
if self.return_df or override_return_df:
return X
else:
return X.values
def get_feature_names(self):
if not isinstance(self.feature_names, list):
raise ValueError(
'Must transform data first. Affected feature names are not known before.'
)
else:
return self.feature_names
def get_dummies(self, X_in):
X = X_in.copy(deep=True)
cols = X.columns.values.tolist()
for switch in self.mapping:
col = switch.get('col')
mod = switch.get('mapping')
base_df = mod.reindex(X[col])
base_df = base_df.set_index(X.index)
X = pd.concat([base_df, X], axis=1)
old_column_index = cols.index(col)
cols[old_column_index:old_column_index + 1] = mod.columns
X = X.reindex(columns=cols)
return X
class BinaryEncoder(BaseEstimator, TransformerMixin):
"""Binary encoding for categorical variables, similar to onehot, but stores categories as binary bitstrings.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
impute_missing: bool
boolean for whether or not to apply the logic for handle_unknown, will be deprecated in the future.
handle_unknown: str
options are 'error', 'ignore' and 'impute', defaults to 'impute', which will impute the category -1. Warning: if
impute is used, an extra column will be added in if the transform matrix has unknown categories. This can causes
unexpected changes in dimension in some cases.
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = BinaryEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 16 columns):
CHAS_0 506 non-null int64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(5)
memory usage: 63.3 KB
None
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, impute_missing=True, handle_unknown='impute'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.impute_missing = impute_missing
self.handle_unknown = handle_unknown
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.digits_per_col = {}
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
impute_missing=self.impute_missing,
handle_unknown=self.handle_unknown
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
for col in self.cols:
self.digits_per_col[col] = self.calc_required_digits(X, col)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.binary(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
def binary(self, X_in, cols=None):
"""
Binary encoding encodes the integers as binary code with one column per digit.
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
# get how many digits we need to represent the classes present
digits = self.digits_per_col[col]
# map the ordinal column into a list of these digits, of length digits
X[col] = X[col].map(lambda x: self.col_transform(x, digits))
for dig in range(digits):
X[str(col) + '_%d' % (dig, )] = X[col].map(lambda r: int(r[dig]) if r is not None else None)
bin_cols.append(str(col) + '_%d' % (dig, ))
X = X.reindex(columns=bin_cols + pass_thru)
return X
@staticmethod
def calc_required_digits(X, col):
"""
figure out how many digits we need to represent the classes present
"""
return int( np.ceil(np.log2(len(X[col].unique()))) )
@staticmethod
def col_transform(col, digits):
"""
The lambda body to transform the column values
"""
if col is None or float(col) < 0.0:
return None
else:
col = list("{0:b}".format(int(col)))
if len(col) == digits:
return col
else:
return [0 for _ in range(digits - len(col))] + col
class BinaryEncoder(BaseEstimator, TransformerMixin):
"""
Binary encoding encodes the integers as binary code with one column per digit.
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False):
"""
:param verbose:
:param cols:
:return:
"""
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = OrdinalEncoder(verbose=verbose, cols=cols)
def fit(self, X, y=None, **kwargs):
"""
:param X:
:param y:
:param kwargs:
:return:
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = self.ordinal_encoder.fit(X)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [
x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5
]
return self
def transform(self, X):
"""
:param X:
:return:
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
if self.cols == []:
return X
X = self.ordinal_encoder.transform(X)
X = binary(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
return X
class MEstimateEncoder(BaseEstimator, TransformerMixin):
"""M-probability estimate of likelihood.
This is a simplified version of target encoder, which goes under names like m-probability estimate or
additive smoothing with known incidence rates. In comparison to target encoder, m-probability estimate
has only one tunable parameter (`m`), while target encoder has two tunable parameters (`min_samples_leaf`
and `smoothing`).
Parameters
----------
verbose: int
integer indicating verbosity of the output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop encoded columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_missing: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns the prior probability.
handle_unknown: str
options are 'return_nan', 'error' and 'value', defaults to 'value', which returns the prior probability.
randomized: bool,
adds normal (Gaussian) distribution noise into training data in order to decrease overfitting (testing data are untouched).
sigma: float
standard deviation (spread or "width") of the normal distribution.
m: float
this is the "m" in the m-probability estimate. Higher value of m results into stronger shrinking.
M is non-negative.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target > 22.5
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = MEstimateEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 13 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(13)
memory usage: 51.5 KB
None
References
----------
.. [1] A Preprocessing Scheme for High-Cardinality Categorical Attributes in Classification and Prediction Problems, equation 7, from
https://dl.acm.org/citation.cfm?id=507538
.. [2] On estimating probabilities in tree pruning, equation 1, from
https://link.springer.com/chapter/10.1007/BFb0017010
.. [3] Additive smoothing, from
https://en.wikipedia.org/wiki/Additive_smoothing#Generalized_to_the_case_of_known_incidence_rates
"""
def __init__(self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True,
handle_unknown='value',
handle_missing='value',
random_state=None,
randomized=False,
sigma=0.05,
m=1.0):
self.verbose = verbose
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self._sum = None
self._count = None
self.random_state = random_state
self.randomized = randomized
self.sigma = sigma
self.m = m
self.feature_names = None
# noinspection PyUnusedLocal
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and binary y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Binary target values.
Returns
-------
self : encoder
Returns self.
"""
# Unite parameters into pandas types
X = util.convert_input(X)
y = util.convert_input_vector(y, X.index).astype(float)
# The lengths must be equal
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) +
" but length of y is " + str(y.shape[0]) + ".")
self._dim = X.shape[1]
# If columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value')
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
# Training
self.mapping = self._train(X_ordinal, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = X_temp.columns.tolist()
# Store column names with approximately constant variance on the training data
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [
x for x in generated_cols if X_temp[x].var() <= 10e-5
]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data.
When the data are used for model training, it is important to also pass the target in order to apply leave one out.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target information (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().any():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# Unite the input into pandas types
X = util.convert_input(X)
# Then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
# If we are encoding the training data, we have to check the target
if y is not None:
y = util.convert_input_vector(y, X.index).astype(float)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) +
" but length of y is " + str(y.shape[0]) +
".")
if not list(self.cols):
return X
# Do not modify the input argument
X = X.copy(deep=True)
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Unexpected categories found in dataframe')
# Loop over the columns and replace the nominal values with the numbers
X = self._score(X, y)
# Postprocessing
# Note: We should not even convert these columns.
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def fit_transform(self, X, y=None, **fit_params):
"""
Encoders that utilize the target must make sure that the training data are transformed with:
transform(X, y)
and not with:
transform(X)
"""
# the interface requires 'y=None' in the signature but we need 'y'
if y is None:
raise (TypeError, 'fit_transform() missing argument: ' 'y' '')
return self.fit(X, y, **fit_params).transform(X, y)
def _train(self, X, y):
# Initialize the output
mapping = {}
# Calculate global statistics
self._sum = y.sum()
self._count = y.count()
prior = self._sum / self._count
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
# Calculate sum and count of the target for each unique value in the feature col
stats = y.groupby(X[col]).agg(['sum', 'count'
]) # Count of x_{i,+} and x_i
# Calculate the m-probability estimate
estimate = (stats['sum'] + prior * self.m) / (stats['count'] +
self.m)
# Ignore unique columns. This helps to prevent overfitting on id-like columns
if len(stats['count']) == self._count:
estimate[:] = prior
if self.handle_unknown == 'return_nan':
estimate.loc[-1] = np.nan
elif self.handle_unknown == 'value':
estimate.loc[-1] = prior
if self.handle_missing == 'return_nan':
estimate.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
estimate.loc[-2] = prior
# Store the m-probability estimate for transform() function
mapping[col] = estimate
return mapping
def _score(self, X, y):
for col in self.cols:
# Score the column
X[col] = X[col].map(self.mapping[col])
# Randomization is meaningful only for training data -> we do it only if y is present
if self.randomized and y is not None:
random_state_generator = check_random_state(self.random_state)
X[col] = (X[col] * random_state_generator.normal(
1., self.sigma, X[col].shape[0]))
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns
-------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError(
"Estimator has to be fitted to return feature names.")
else:
return self.feature_names
class OneHotEncoder(BaseEstimator, TransformerMixin):
"""Onehot (or dummy) coding for categorical features, produces one feature per category, each binary.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
impute_missing: bool
boolean for whether or not to apply the logic for handle_unknown, will be deprecated in the future.
handle_unknown: str
options are 'error', 'ignore' and 'impute', defaults to 'impute', which will impute the category -1. Warning: if
impute is used, an extra column will be added in if the transform matrix has unknown categories. This can causes
unexpected changes in dimension in some cases.
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = OneHotEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 22 columns):
CHAS_0 506 non-null int64
CHAS_1 506 non-null int64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
RAD_4 506 non-null int64
RAD_5 506 non-null int64
RAD_6 506 non-null int64
RAD_7 506 non-null int64
RAD_8 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(11)
memory usage: 87.0 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
http://www.ats.ucla.edu/stat/r/library/contrast_coding.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, impute_missing=True, handle_unknown='impute'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.impute_missing = impute_missing
self.handle_unknown = handle_unknown
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
impute_missing=self.impute_missing,
handle_unknown=self.handle_unknown
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.get_dummies(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
@staticmethod
def get_dummies(X_in, cols=None):
"""
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
classes = [x for x in set(X[col].values.tolist()) if np.isfinite(x)]
for class_ in classes:
n_col_name = str(col) + '_%s' % (class_, )
X[n_col_name] = X[col] == class_
bin_cols.append(n_col_name)
X = X.reindex(columns=bin_cols + pass_thru)
# convert all of the bools into integers.
for col in bin_cols:
X[col] = X[col].astype(int)
return X
class BaseNEncoder(BaseEstimator, TransformerMixin):
"""Base-N encoder encodes the categories into arrays of their base-N representation. A base of 1 is equivalent to
one-hot encoding (not really base-1, but useful), a base of 2 is equivalent to binary encoding. N=number of actual
categories is equivalent to vanilla ordinal encoding.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
impute_missing: bool
boolean for whether or not to apply the logic for handle_unknown, will be deprecated in the future.
handle_unknown: str
options are 'error', 'ignore' and 'impute', defaults to 'impute', which will impute the category -1. Warning: if
impute is used, an extra column will be added in if the transform matrix has unknown categories. This can causes
unexpected changes in dimension in some cases.
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = BaseNEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 16 columns):
CHAS_0 506 non-null int64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(5)
memory usage: 63.3 KB
None
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, base=2, impute_missing=True,
handle_unknown='impute'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.impute_missing = impute_missing
self.handle_unknown = handle_unknown
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.base = base
self._encoded_columns = None
self.digits_per_col = {}
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
impute_missing=self.impute_missing,
handle_unknown=self.handle_unknown
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
for col in self.cols:
self.digits_per_col[col] = self.calc_required_digits(X, col)
# do a transform on the training data to get a column list
X_t = self.transform(X, override_return_df=True)
self._encoded_columns = X_t.columns.values
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.basen_encode(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
X.fillna(0.0, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def inverse_transform(self, Xt):
"""
Perform the inverse transformation to encoded data.
Parameters
----------
X_in : array-like, shape = [n_samples, n_features]
Returns
-------
p: array, the same size of X_in
"""
warnings.warn('Inverse transform in basen is a currently experimental feature, please be careful')
X = Xt.copy(deep=True)
# first check the type
X = convert_input(X)
if self._dim is None:
raise ValueError('Must train encoder before it can be used to inverse_transform data')
X = self.basen_to_interger(X, self.cols, self.base)
# then make sure that it is the right size
if X.shape[1] != self._dim:
if self.drop_invariant:
raise ValueError("Unexpected input dimension %d, the attribute drop_invariant should "
"set as False when transform data" % (X.shape[1],))
else:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
if not self.cols:
return X if self.return_df else X.values
if self.impute_missing and self.handle_unknown == 'impute':
for col in self.cols:
if any(X[col] == -1):
raise ValueError("inverse_transform is not supported because transform impute "
"the unknown category -1 when encode %s" % (col,))
for switch in self.ordinal_encoder.mapping:
col_dict = {col_pair[1]: col_pair[0] for col_pair in switch.get('mapping')}
X[switch.get('col')] = X[switch.get('col')].apply(lambda x: col_dict.get(x))
return X if self.return_df else X.values
def calc_required_digits(self, X, col):
# figure out how many digits we need to represent the classes present
if self.base == 1:
digits = len(X[col].unique())
else:
digits = int(np.ceil(math.log(len(X[col].unique()), self.base)))
return digits
def basen_encode(self, X_in, cols=None):
"""
Basen encoding encodes the integers as basen code with one column per digit.
Parameters
----------
X_in: DataFrame
cols: list-like, default None
Column names in the DataFrame to be encoded
Returns
-------
dummies : DataFrame
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
# get how many digits we need to represent the classes present
digits = self.calc_required_digits(X, col)
# map the ordinal column into a list of these digits, of length digits
X[col] = X[col].map(lambda x: self.col_transform(x, digits))
for dig in range(digits):
X[str(col) + '_%d' % (dig,)] = X[col].map(lambda r: int(r[dig]) if r is not None else None)
bin_cols.append(str(col) + '_%d' % (dig,))
if self._encoded_columns is None:
X = X.reindex(columns=bin_cols + pass_thru)
else:
X = X.reindex(columns=self._encoded_columns)
return X
def basen_to_interger(self, X, cols, base):
"""
Convert basen code as integers.
Parameters
----------
X : DataFrame
encoded data
cols : list-like
Column names in the DataFrame that be encoded
base : int
The base of transform
Returns
-------
numerical: DataFrame
"""
out_cols = X.columns.values
for col in cols:
col_list = [col0 for col0 in out_cols if col0.startswith(col)]
for col0 in col_list:
if any(X[col0].isnull()):
raise ValueError("inverse_transform is not supported because transform impute"
"the unknown category -1 when encode %s" % (col,))
if base == 1:
value_array = np.array([int(col0.split('_')[1]) for col0 in col_list])
else:
len0 = len(col_list)
value_array = np.array([base ** (len0 - 1 - i) for i in range(len0)])
X[col] = np.dot(X[col_list].values, value_array.T)
out_cols = [col0 for col0 in out_cols if col0 not in col_list]
X = X.reindex(columns=out_cols + cols)
return X
def col_transform(self, col, digits):
"""
The lambda body to transform the column values
"""
if col is None or float(col) < 0.0:
return None
else:
col = self.numberToBase(int(col), self.base, digits)
if len(col) == digits:
return col
else:
return [0 for _ in range(digits - len(col))] + col
@staticmethod
def numberToBase(n, b, limit):
if b == 1:
return [0 if n != _ else 1 for _ in range(limit)]
if n == 0:
return [0 for _ in range(limit)]
digits = []
for _ in range(limit):
digits.append(int(n % b))
n, _ = divmod(n, b)
return digits[::-1]
class BackwardDifferenceEncoder(BaseEstimator, TransformerMixin):
"""Backward difference contrast coding for encoding categorical variables.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
impute_missing: bool
boolean for whether or not to apply the logic for handle_unknown, will be deprecated in the future.
handle_unknown: str
options are 'error', 'ignore' and 'impute', defaults to 'impute', which will impute the category -1. Warning: if
impute is used, an extra column will be added in if the transform matrix has unknown categories. This can causes
unexpected changes in dimension in some cases.
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = BackwardDifferenceEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 22 columns):
col_CHAS_0 506 non-null float64
col_CHAS_1 506 non-null float64
col_RAD_0 506 non-null float64
col_RAD_1 506 non-null float64
col_RAD_2 506 non-null float64
col_RAD_3 506 non-null float64
col_RAD_4 506 non-null float64
col_RAD_5 506 non-null float64
col_RAD_6 506 non-null float64
col_RAD_7 506 non-null float64
col_RAD_8 506 non-null float64
col_CRIM 506 non-null float64
col_ZN 506 non-null float64
col_INDUS 506 non-null float64
col_NOX 506 non-null float64
col_RM 506 non-null float64
col_AGE 506 non-null float64
col_DIS 506 non-null float64
col_TAX 506 non-null float64
col_PTRATIO 506 non-null float64
col_B 506 non-null float64
col_LSTAT 506 non-null float64
dtypes: float64(22)
memory usage: 87.0 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True,
impute_missing=True,
handle_unknown='impute'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.impute_missing = impute_missing
self.handle_unknown = handle_unknown
self.cols = cols
self.ordinal_encoder = None
self._dim = None
def fit(self, X, y=None, **kwargs):
"""Fits an ordinal encoder to produce a consistent mapping across applications and optionally finds
generally invariant columns to drop consistently.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
impute_missing=self.impute_missing,
handle_unknown=self.handle_unknown)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [
x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5
]
return self
def transform(self, X):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.backward_difference_coding(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
@staticmethod
def backward_difference_coding(X_in, cols=None):
"""
"""
X = X_in.copy(deep=True)
X.columns = ['col_' + str(x) for x in X.columns.values]
cols = ['col_' + str(x) for x in cols]
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
mod = dmatrix("C(%s, Diff)" % (col, ), X)
for dig in range(len(mod[0])):
X[str(col) + '_%d' % (dig, )] = mod[:, dig]
bin_cols.append(str(col) + '_%d' % (dig, ))
X = X.reindex(columns=bin_cols + pass_thru)
X.fillna(0.0)
return X
class SumEncoder(BaseEstimator, TransformerMixin):
"""
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True):
"""
:param verbose: (optional, default=0) integer indicating verbosity of output. 0 for none.
:param cols: (optional, default=None) a list of columns to encode, if None, all string columns will be encoded
:param drop_invariant: (optional, default=False) boolean for whether or not to drop columns with 0 variance
:param return_df: (optional, default=True) boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
:return:
"""
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
def fit(self, X, y=None, **kwargs):
"""
:param X:
:param y:
:param kwargs:
:return:
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(verbose=self.verbose, cols=self.cols)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5]
return self
def transform(self, X):
"""
:param X:
:return:
"""
if not isinstance(X, pd.DataFrame):
X = pd.DataFrame(X)
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = sum_coding(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df:
return X
else:
return X.values
class BaseNEncoder(BaseEstimator, TransformerMixin):
"""Base-N encoder encodes the categories into arrays of their base-N representation. A base of 1 is equivalent to
one-hot encoding (not really base-1, but useful), a base of 2 is equivalent to binary encoding. N=number of actual
categories is equivalent to vanilla ordinal encoding.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
base: int
when the downstream model copes well with nonlinearities (like decision tree), use higher base.
handle_unknown: str
options are 'error', 'return_nan' and 'value', defaults to 'value'. Warning: if value is used,
an extra column will be added in if the transform matrix has unknown categories. This can cause
unexpected changes in dimension in some cases.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = BaseNEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 18 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS_0 506 non-null int64
CHAS_1 506 non-null int64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
RAD_4 506 non-null int64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(7)
memory usage: 71.2 KB
None
"""
def __init__(self, verbose=0, cols=None, mapping=None, drop_invariant=False, return_df=True, base=2,
handle_unknown='value', handle_missing='value'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self.cols = cols
self.mapping = mapping
self.ordinal_encoder = None
self._dim = None
self.base = base
self._encoded_columns = None
self.feature_names = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
X = util.convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
self.mapping = self.fit_base_n_encoding(X)
# do a transform on the training data to get a column list
X_temp = self.transform(X, override_return_df=True)
self._encoded_columns = X_temp.columns.values
self.feature_names = list(X_temp.columns)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def fit_base_n_encoding(self, X):
mappings_out = []
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
if self.handle_missing == 'value':
values = values[values > 0]
if self.handle_unknown == 'indicator':
values = np.append(values, -1)
digits = self.calc_required_digits(values)
X_unique = pd.DataFrame(index=values,
columns=[str(col) + '_%d' % x for x in range(digits)],
data=np.array([self.col_transform(x, digits) for x in range(1, len(values) + 1)]))
if self.handle_unknown == 'return_nan':
X_unique.loc[-1] = np.nan
elif self.handle_unknown == 'value':
X_unique.loc[-1] = 0
if self.handle_missing == 'return_nan':
X_unique.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
X_unique.loc[-2] = 0
mappings_out.append({'col': col, 'mapping': X_unique})
return mappings_out
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = util.convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
if not self.cols:
return X
X_out = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X_out[self.cols].isin([-1]).any().any():
raise ValueError('Columns to be encoded can not contain new values')
X_out = self.basen_encode(X_out, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X_out.drop(col, 1, inplace=True)
# impute missing values only in the generated columns
# generated_cols = util.get_generated_cols(X, X_out, self.cols)
# X_out[generated_cols] = X_out[generated_cols].fillna(value=0.0)
if self.return_df or override_return_df:
return X_out
else:
return X_out.values
def inverse_transform(self, X_in):
"""
Perform the inverse transformation to encoded data.
Parameters
----------
X_in : array-like, shape = [n_samples, n_features]
Returns
-------
p: array, the same size of X_in
"""
X = X_in.copy(deep=True)
# first check the type
X = util.convert_input(X)
if self._dim is None:
raise ValueError('Must train encoder before it can be used to inverse_transform data')
X = self.basen_to_integer(X, self.cols, self.base)
# then make sure that it is the right size
if X.shape[1] != self._dim:
if self.drop_invariant:
raise ValueError("Unexpected input dimension %d, the attribute drop_invariant should "
"set as False when transform data" % (X.shape[1],))
else:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
if not self.cols:
return X if self.return_df else X.values
for switch in self.ordinal_encoder.mapping:
column_mapping = switch.get('mapping')
inverse = pd.Series(data=column_mapping.index, index=column_mapping.get_values())
X[switch.get('col')] = X[switch.get('col')].map(inverse).astype(switch.get('data_type'))
if self.handle_unknown == 'return_nan' and self.handle_missing == 'return_nan':
for col in self.cols:
if X[switch.get('col')].isnull().any():
warnings.warn("inverse_transform is not supported because transform impute "
"the unknown category nan when encode %s" % (col,))
return X if self.return_df else X.values
def calc_required_digits(self, values):
# figure out how many digits we need to represent the classes present
if self.base == 1:
digits = len(values) + 1
else:
digits = int(np.ceil(math.log(len(values), self.base))) + 1
return digits
def basen_encode(self, X_in, cols=None):
"""
Basen encoding encodes the integers as basen code with one column per digit.
Parameters
----------
X_in: DataFrame
cols: list-like, default None
Column names in the DataFrame to be encoded
Returns
-------
dummies : DataFrame
"""
X = X_in.copy(deep=True)
cols = X.columns.values.tolist()
for switch in self.mapping:
col = switch.get('col')
mod = switch.get('mapping')
base_df = mod.loc[X[col]]
base_df.set_index(X.index, inplace=True)
X = pd.concat([base_df, X], axis=1)
old_column_index = cols.index(col)
cols[old_column_index: old_column_index + 1] = mod.columns
return X.reindex(columns=cols)
def basen_to_integer(self, X, cols, base):
"""
Convert basen code as integers.
Parameters
----------
X : DataFrame
encoded data
cols : list-like
Column names in the DataFrame that be encoded
base : int
The base of transform
Returns
-------
numerical: DataFrame
"""
out_cols = X.columns.values
for col in cols:
col_list = [col0 for col0 in out_cols if str(col0).startswith(str(col))]
if base == 1:
value_array = np.array([int(col0.split('_')[-1]) for col0 in col_list])
else:
len0 = len(col_list)
value_array = np.array([base ** (len0 - 1 - i) for i in range(len0)])
X[col] = np.dot(X[col_list].values, value_array.T)
out_cols = [col0 for col0 in out_cols if col0 not in col_list]
X = X.reindex(columns=out_cols + cols)
return X
def col_transform(self, col, digits):
"""
The lambda body to transform the column values
"""
if col is None or float(col) < 0.0:
return None
else:
col = self.numberToBase(int(col), self.base, digits)
if len(col) == digits:
return col
else:
return [0 for _ in range(digits - len(col))] + col
@staticmethod
def numberToBase(n, b, limit):
if b == 1:
return [0 if n != _ else 1 for _ in range(limit)]
if n == 0:
return [0 for _ in range(limit)]
digits = []
for _ in range(limit):
digits.append(int(n % b))
n, _ = divmod(n, b)
return digits[::-1]
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns:
--------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError('Must fit data first. Affected feature names are not known before.')
else:
return self.feature_names
class BaseNEncoder(BaseEstimator, TransformerMixin):
"""Base-N encoder encodes the categories into arrays of their base-N representation. A base of 1 is equivalent to
one-hot encoding (not really base-1, but useful), a base of 2 is equivalent to binary encoding. N=number of actual
categories is equivalent to vanilla ordinal encoding.
Parameters
----------
verbose: int
integer indicating verbosity of the output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
base: int
when the downstream model copes well with nonlinearities (like decision tree), use higher base.
handle_unknown: str
options are 'error', 'return_nan', 'value', and 'indicator'. The default is 'value'. Warning: if indicator is used,
an extra column will be added in if the transform matrix has unknown categories. This can cause
unexpected changes in dimension in some cases.
handle_missing: str
options are 'error', 'return_nan', 'value', and 'indicator'. The default is 'value'. Warning: if indicator is used,
an extra column will be added in if the transform matrix has nan values. This can cause
unexpected changes in dimension in some cases.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = BaseNEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 18 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS_0 506 non-null int64
CHAS_1 506 non-null int64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
RAD_4 506 non-null int64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(7)
memory usage: 71.2 KB
None
"""
def __init__(self, verbose=0, cols=None, mapping=None, drop_invariant=False, return_df=True, base=2,
handle_unknown='value', handle_missing='value'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self.cols = cols
self.mapping = mapping
self.ordinal_encoder = None
self._dim = None
self.base = base
self._encoded_columns = None
self.feature_names = None
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
X = util.convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
self.mapping = self.fit_base_n_encoding(X)
# do a transform on the training data to get a column list
X_temp = self.transform(X, override_return_df=True)
self._encoded_columns = X_temp.columns.values
self.feature_names = list(X_temp.columns)
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def fit_base_n_encoding(self, X):
mappings_out = []
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
if self.handle_missing == 'value':
values = values[values > 0]
if self.handle_unknown == 'indicator':
values = np.append(values, -1)
digits = self.calc_required_digits(values)
X_unique = pd.DataFrame(index=values,
columns=[str(col) + '_%d' % x for x in range(digits)],
data=np.array([self.col_transform(x, digits) for x in range(1, len(values) + 1)]))
if self.handle_unknown == 'return_nan':
X_unique.loc[-1] = np.nan
elif self.handle_unknown == 'value':
X_unique.loc[-1] = 0
if self.handle_missing == 'return_nan':
X_unique.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
X_unique.loc[-2] = 0
mappings_out.append({'col': col, 'mapping': X_unique})
return mappings_out
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# first check the type
X = util.convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
if not self.cols:
return X
X_out = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X_out[self.cols].isin([-1]).any().any():
raise ValueError('Columns to be encoded can not contain new values')
X_out = self.basen_encode(X_out, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X_out.drop(col, 1, inplace=True)
# impute missing values only in the generated columns
# generated_cols = util.get_generated_cols(X, X_out, self.cols)
# X_out[generated_cols] = X_out[generated_cols].fillna(value=0.0)
if self.return_df or override_return_df:
return X_out
else:
return X_out.values
def inverse_transform(self, X_in):
"""
Perform the inverse transformation to encoded data.
Parameters
----------
X_in : array-like, shape = [n_samples, n_features]
Returns
-------
p: array, the same size of X_in
"""
# fail fast
if self._dim is None:
raise ValueError('Must train encoder before it can be used to inverse_transform data')
# unite the type into pandas dataframe (it makes the input size detection code easier...) and make deep copy
X = util.convert_input(X_in, columns=self.feature_names, deep=True)
X = self.basen_to_integer(X, self.cols, self.base)
# make sure that it is the right size
if X.shape[1] != self._dim:
if self.drop_invariant:
raise ValueError("Unexpected input dimension %d, the attribute drop_invariant should "
"be False when transforming the data" % (X.shape[1],))
else:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
if not self.cols:
return X if self.return_df else X.values
for switch in self.ordinal_encoder.mapping:
column_mapping = switch.get('mapping')
inverse = pd.Series(data=column_mapping.index, index=column_mapping.get_values())
X[switch.get('col')] = X[switch.get('col')].map(inverse).astype(switch.get('data_type'))
if self.handle_unknown == 'return_nan' and self.handle_missing == 'return_nan':
for col in self.cols:
if X[switch.get('col')].isnull().any():
warnings.warn("inverse_transform is not supported because transform impute "
"the unknown category nan when encode %s" % (col,))
return X if self.return_df else X.values
def calc_required_digits(self, values):
# figure out how many digits we need to represent the classes present
if self.base == 1:
digits = len(values) + 1
else:
digits = int(np.ceil(math.log(len(values), self.base))) + 1
return digits
def basen_encode(self, X_in, cols=None):
"""
Basen encoding encodes the integers as basen code with one column per digit.
Parameters
----------
X_in: DataFrame
cols: list-like, default None
Column names in the DataFrame to be encoded
Returns
-------
dummies : DataFrame
"""
X = X_in.copy(deep=True)
cols = X.columns.values.tolist()
for switch in self.mapping:
col = switch.get('col')
mod = switch.get('mapping')
base_df = mod.reindex(X[col])
base_df.set_index(X.index, inplace=True)
X = pd.concat([base_df, X], axis=1)
old_column_index = cols.index(col)
cols[old_column_index: old_column_index + 1] = mod.columns
return X.reindex(columns=cols)
def basen_to_integer(self, X, cols, base):
"""
Convert basen code as integers.
Parameters
----------
X : DataFrame
encoded data
cols : list-like
Column names in the DataFrame that be encoded
base : int
The base of transform
Returns
-------
numerical: DataFrame
"""
out_cols = X.columns.values.tolist()
for col in cols:
col_list = [col0 for col0 in out_cols if str(col0).startswith(str(col))]
insert_at = out_cols.index(col_list[0])
if base == 1:
value_array = np.array([int(col0.split('_')[-1]) for col0 in col_list])
else:
len0 = len(col_list)
value_array = np.array([base ** (len0 - 1 - i) for i in range(len0)])
X.insert(insert_at, col, np.dot(X[col_list].values, value_array.T))
X.drop(col_list, axis=1, inplace=True)
out_cols = X.columns.values.tolist()
return X
def col_transform(self, col, digits):
"""
The lambda body to transform the column values
"""
if col is None or float(col) < 0.0:
return None
else:
col = self.number_to_base(int(col), self.base, digits)
if len(col) == digits:
return col
else:
return [0 for _ in range(digits - len(col))] + col
@staticmethod
def number_to_base(n, b, limit):
if b == 1:
return [0 if n != _ else 1 for _ in range(limit)]
if n == 0:
return [0 for _ in range(limit)]
digits = []
for _ in range(limit):
digits.append(int(n % b))
n, _ = divmod(n, b)
return digits[::-1]
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns
-------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError('Must fit data first. Affected feature names are not known before.')
else:
return self.feature_names
class TargetEncoder(BaseEstimator, TransformerMixin):
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, handle_missing='value',
handle_unknown='value', min_samples_leaf=1, smoothing=1.0):
"""Target encoding for categorical features.
For the case of categorical target: features are replaced with a blend of posterior probability of the target
given particular categorical value and prior probability of the target over all the training data.
For the case of continuous target: features are replaced with a blend of expected value of the target
given particular categorical value and expected value of the target over all the training data.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_unknown: str
options are 'error', 'return_nan' and 'value', defaults to 'value', which will impute the target mean.
min_samples_leaf: int
minimum samples to take category average into account.
smoothing: float
smoothing effect to balance categorical average vs prior. Higher value means stronger regularization.
The value must be strictly bigger than 0.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = TargetEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 13 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(13)
memory usage: 51.5 KB
None
References
----------
.. [1] A Preprocessing Scheme for High-Cardinality Categorical Attributes in Classification and Prediction Problems. from
https://kaggle2.blob.core.windows.net/forum-message-attachments/225952/7441/high%20cardinality%20categoricals.pdf.
"""
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self.min_samples_leaf = min_samples_leaf
self.smoothing = float(smoothing) # Make smoothing a float so that python 2 does not treat as integer division
self._dim = None
self.mapping = None
self.handle_unknown = handle_unknown
self.handle_missing=handle_missing
self._mean = None
self.feature_names = None
def fit(self, X, y, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# unite the input into pandas types
X = util.convert_input(X)
y = util.convert_input_vector(y, X.index)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
X_ordinal = self.ordinal_encoder.transform(X)
self.mapping = self.fit_target_encoding(X_ordinal, y)
X_temp = self.transform(X, override_return_df=True)
self.feature_names = list(X_temp.columns)
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def fit_target_encoding(self, X, y):
mapping = {}
for switch in self.ordinal_encoder.category_mapping:
col = switch.get('col')
values = switch.get('mapping')
prior = self._mean = y.mean()
stats = y.groupby(X[col]).agg(['count', 'mean'])
smoove = 1 / (1 + np.exp(-(stats['count'] - self.min_samples_leaf) / self.smoothing))
smoothing = prior * (1 - smoove) + stats['mean'] * smoove
smoothing[stats['count'] == 1] = prior
if self.handle_unknown == 'return_nan':
smoothing.loc[-1] = np.nan
elif self.handle_unknown == 'value':
smoothing.loc[-1] = prior
if self.handle_missing == 'return_nan':
smoothing.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
smoothing.loc[-2] = prior
mapping[col] = smoothing
return mapping
def transform(self, X, y=None, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
y : array-like, shape = [n_samples] when transform by leave one out
None, when transform without target info (such as transform test set)
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError('Must train encoder before it can be used to transform data.')
# unite the input into pandas types
X = util.convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
# if we are encoding the training data, we have to check the target
if y is not None:
y = util.convert_input_vector(y, X.index)
if X.shape[0] != y.shape[0]:
raise ValueError("The length of X is " + str(X.shape[0]) + " but length of y is " + str(y.shape[0]) + ".")
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Unexpected categories found in dataframe')
X = self.target_encode(X)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def fit_transform(self, X, y=None, **fit_params):
"""
Encoders that utilize the target must make sure that the training data are transformed with:
transform(X, y)
and not with:
transform(X)
"""
return self.fit(X, y, **fit_params).transform(X, y)
def target_encode(self, X_in):
X = X_in.copy(deep=True)
for col in self.cols:
X[col] = X[col].map(self.mapping[col])
return X
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns:
--------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError('Must fit data first. Affected feature names are not known before.')
else:
return self.feature_names
class BaseNEncoder(BaseEstimator, TransformerMixin):
"""Base-N encoder encodes the categories into arrays of their base-N representation. A base of 1 is equivalent to
one-hot encoding (not really base-1, but useful), a base of 2 is equivalent to binary encoding. N=number of actual
categories is equivalent to vanilla ordinal encoding.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array)
impute_missing: bool
boolean for whether or not to apply the logic for handle_unknown, will be deprecated in the future.
handle_unknown: str
options are 'error', 'ignore' and 'impute', defaults to 'impute', which will impute the category -1. Warning: if
impute is used, an extra column will be added in if the transform matrix has unknown categories. This can causes
unexpected changes in dimension in some cases.
Example
-------
>>>from category_encoders import *
>>>import pandas as pd
>>>from sklearn.datasets import load_boston
>>>bunch = load_boston()
>>>y = bunch.target
>>>X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>>enc = BaseNEncoder(cols=['CHAS', 'RAD']).fit(X, y)
>>>numeric_dataset = enc.transform(X)
>>>print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 16 columns):
CHAS_0 506 non-null int64
RAD_0 506 non-null int64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(5)
memory usage: 63.3 KB
None
"""
def __init__(self,
verbose=0,
cols=None,
drop_invariant=False,
return_df=True,
base=2,
impute_missing=True,
handle_unknown='impute'):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.verbose = verbose
self.impute_missing = impute_missing
self.handle_unknown = handle_unknown
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.base = base
self._encoded_columns = None
self.digits_per_col = {}
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# if the input dataset isn't already a dataframe, convert it to one (using default column names)
# first check the type
X = convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = get_obj_cols(X)
# train an ordinal pre-encoder
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
impute_missing=self.impute_missing,
handle_unknown=self.handle_unknown)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
for col in self.cols:
self.digits_per_col[col] = self.calc_required_digits(X, col)
# do a transform on the training data to get a column list
X_t = self.transform(X, override_return_df=True)
self._encoded_columns = X_t.columns.values
# drop all output columns with 0 variance.
if self.drop_invariant:
self.drop_cols = []
X_temp = self.transform(X)
self.drop_cols = [
x for x in X_temp.columns.values if X_temp[x].var() <= 10e-5
]
return self
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# first check the type
X = convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1],
self._dim,
))
if not self.cols:
return X
X = self.ordinal_encoder.transform(X)
X = self.basen_encode(X, cols=self.cols)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
X.fillna(0.0, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def inverse_transform(self, Xt):
"""
Perform the inverse transformation to encoded data.
Parameters
----------
X_in : array-like, shape = [n_samples, n_features]
Returns
-------
p: array, the same size of X_in
"""
warnings.warn(
'Inverse transform in basen is a currently experimental feature, please be careful'
)
X = Xt.copy(deep=True)
# first check the type
X = convert_input(X)
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to inverse_transform data'
)
X = self.basen_to_interger(X, self.cols, self.base)
# then make sure that it is the right size
if X.shape[1] != self._dim:
if self.drop_invariant:
raise ValueError(
"Unexpected input dimension %d, the attribute drop_invariant should "
"set as False when transform data" % (X.shape[1], ))
else:
raise ValueError('Unexpected input dimension %d, expected %d' %
(
X.shape[1],
self._dim,
))
if not self.cols:
return X if self.return_df else X.values
if self.impute_missing and self.handle_unknown == 'impute':
for col in self.cols:
if any(X[col] == -1):
raise ValueError(
"inverse_transform is not supported because transform impute "
"the unknown category -1 when encode %s" % (col, ))
for switch in self.ordinal_encoder.mapping:
col_dict = {
col_pair[1]: col_pair[0]
for col_pair in switch.get('mapping')
}
X[switch.get('col')] = X[switch.get('col')].apply(
lambda x: col_dict.get(x))
return X if self.return_df else X.values
def calc_required_digits(self, X, col):
# figure out how many digits we need to represent the classes present
if self.base == 1:
digits = len(X[col].unique()) + 1
else:
digits = int(np.ceil(math.log(len(X[col].unique()),
self.base))) + 1
return digits
def basen_encode(self, X_in, cols=None):
"""
Basen encoding encodes the integers as basen code with one column per digit.
Parameters
----------
X_in: DataFrame
cols: list-like, default None
Column names in the DataFrame to be encoded
Returns
-------
dummies : DataFrame
"""
X = X_in.copy(deep=True)
if cols is None:
cols = X.columns.values
pass_thru = []
else:
pass_thru = [col for col in X.columns.values if col not in cols]
bin_cols = []
for col in cols:
# get how many digits we need to represent the classes present
digits = self.calc_required_digits(X, col)
# map the ordinal column into a list of these digits, of length digits
X[col] = X[col].map(lambda x: self.col_transform(x, digits))
for dig in range(digits):
X[str(col) + '_%d' % (dig, )] = X[col].map(
lambda r: int(r[dig]) if r is not None else None)
bin_cols.append(str(col) + '_%d' % (dig, ))
if self._encoded_columns is None:
X = X.reindex(columns=bin_cols + pass_thru)
else:
X = X.reindex(columns=self._encoded_columns)
return X
def basen_to_interger(self, X, cols, base):
"""
Convert basen code as integers.
Parameters
----------
X : DataFrame
encoded data
cols : list-like
Column names in the DataFrame that be encoded
base : int
The base of transform
Returns
-------
numerical: DataFrame
"""
out_cols = X.columns.values
for col in cols:
col_list = [col0 for col0 in out_cols if col0.startswith(col)]
for col0 in col_list:
if any(X[col0].isnull()):
raise ValueError(
"inverse_transform is not supported because transform impute"
"the unknown category -1 when encode %s" % (col, ))
if base == 1:
value_array = np.array(
[int(col0.split('_')[1]) for col0 in col_list])
else:
len0 = len(col_list)
value_array = np.array(
[base**(len0 - 1 - i) for i in range(len0)])
X[col] = np.dot(X[col_list].values, value_array.T)
out_cols = [col0 for col0 in out_cols if col0 not in col_list]
X = X.reindex(columns=out_cols + cols)
return X
def col_transform(self, col, digits):
"""
The lambda body to transform the column values
"""
if col is None or float(col) < 0.0:
return None
else:
col = self.numberToBase(int(col), self.base, digits)
if len(col) == digits:
return col
else:
return [0 for _ in range(digits - len(col))] + col
@staticmethod
def numberToBase(n, b, limit):
if b == 1:
return [0 if n != _ else 1 for _ in range(limit)]
if n == 0:
return [0 for _ in range(limit)]
digits = []
for _ in range(limit):
digits.append(int(n % b))
n, _ = divmod(n, b)
return digits[::-1]
class OneHotEncoder(BaseEstimator, TransformerMixin):
"""Onehot (or dummy) coding for categorical features, produces one feature per category, each binary.
Parameters
----------
verbose: int
integer indicating verbosity of output. 0 for none.
cols: list
a list of columns to encode, if None, all string columns will be encoded.
drop_invariant: bool
boolean for whether or not to drop columns with 0 variance.
return_df: bool
boolean for whether to return a pandas DataFrame from transform (otherwise it will be a numpy array).
handle_unknown: str
options are 'error', 'return_nan' and 'value', defaults to 'value'. Warning: if value is used,
an extra column will be added in if the transform matrix has unknown categories. This can cause
unexpected changes in the dimension in some cases.
use_cat_names: bool
if True, category values will be included in the encoded column names. Since this can result into duplicate column names, duplicates are suffixed with '#' symbol until a unique name is generated.
If False, category indices will be used instead of the category values.
Example
-------
>>> from category_encoders import *
>>> import pandas as pd
>>> from sklearn.datasets import load_boston
>>> bunch = load_boston()
>>> y = bunch.target
>>> X = pd.DataFrame(bunch.data, columns=bunch.feature_names)
>>> enc = OneHotEncoder(cols=['CHAS', 'RAD'], handle_unknown='indicator').fit(X, y)
>>> numeric_dataset = enc.transform(X)
>>> print(numeric_dataset.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 24 columns):
CRIM 506 non-null float64
ZN 506 non-null float64
INDUS 506 non-null float64
CHAS_1 506 non-null int64
CHAS_2 506 non-null int64
CHAS_-1 506 non-null int64
NOX 506 non-null float64
RM 506 non-null float64
AGE 506 non-null float64
DIS 506 non-null float64
RAD_1 506 non-null int64
RAD_2 506 non-null int64
RAD_3 506 non-null int64
RAD_4 506 non-null int64
RAD_5 506 non-null int64
RAD_6 506 non-null int64
RAD_7 506 non-null int64
RAD_8 506 non-null int64
RAD_9 506 non-null int64
RAD_-1 506 non-null int64
TAX 506 non-null float64
PTRATIO 506 non-null float64
B 506 non-null float64
LSTAT 506 non-null float64
dtypes: float64(11), int64(13)
memory usage: 95.0 KB
None
References
----------
.. [1] Contrast Coding Systems for categorical variables. UCLA: Statistical Consulting Group. from
https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/.
.. [2] Gregory Carey (2003). Coding Categorical Variables, from
http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
"""
def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True,
handle_missing='value', handle_unknown='value', use_cat_names=False):
self.return_df = return_df
self.drop_invariant = drop_invariant
self.drop_cols = []
self.mapping = None
self.verbose = verbose
self.cols = cols
self.ordinal_encoder = None
self._dim = None
self.handle_unknown = handle_unknown
self.handle_missing = handle_missing
self.use_cat_names = use_cat_names
self.feature_names = None
@property
def category_mapping(self):
return self.ordinal_encoder.category_mapping
def fit(self, X, y=None, **kwargs):
"""Fit encoder according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : encoder
Returns self.
"""
# first check the type
X = util.convert_input(X)
self._dim = X.shape[1]
# if columns aren't passed, just use every string column
if self.cols is None:
self.cols = util.get_obj_cols(X)
else:
self.cols = util.convert_cols_to_list(self.cols)
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
self.ordinal_encoder = OrdinalEncoder(
verbose=self.verbose,
cols=self.cols,
handle_unknown='value',
handle_missing='value'
)
self.ordinal_encoder = self.ordinal_encoder.fit(X)
self.mapping = self.generate_mapping()
X_temp = self.transform(X, override_return_df=True)
self.feature_names = list(X_temp.columns)
if self.drop_invariant:
self.drop_cols = []
generated_cols = util.get_generated_cols(X, X_temp, self.cols)
self.drop_cols = [x for x in generated_cols if X_temp[x].var() <= 10e-5]
try:
[self.feature_names.remove(x) for x in self.drop_cols]
except KeyError as e:
if self.verbose > 0:
print("Could not remove column from feature names."
"Not found in generated cols.\n{}".format(e))
return self
def generate_mapping(self):
mapping = []
found_column_counts = {}
for switch in self.ordinal_encoder.mapping:
col = switch.get('col')
values = switch.get('mapping').copy(deep=True)
if self.handle_missing == 'value':
values = values[values > 0]
if len(values) == 0:
continue
index = []
new_columns = []
for cat_name, class_ in values.iteritems():
if self.use_cat_names:
n_col_name = str(col) + '_%s' % (cat_name,)
found_count = found_column_counts.get(n_col_name, 0)
found_column_counts[n_col_name] = found_count + 1
n_col_name += '#' * found_count
else:
n_col_name = str(col) + '_%s' % (class_,)
index.append(class_)
new_columns.append(n_col_name)
if self.handle_unknown == 'indicator':
n_col_name = str(col) + '_%s' % (-1,)
if self.use_cat_names:
found_count = found_column_counts.get(n_col_name, 0)
found_column_counts[n_col_name] = found_count + 1
n_col_name += '#' * found_count
new_columns.append(n_col_name)
index.append(-1)
base_matrix = np.eye(N=len(index), dtype=np.int)
base_df = pd.DataFrame(data=base_matrix, columns=new_columns, index=index)
if self.handle_unknown == 'value':
base_df.loc[-1] = 0
elif self.handle_unknown == 'return_nan':
base_df.loc[-1] = np.nan
if self.handle_missing == 'return_nan':
base_df.loc[values.loc[np.nan]] = np.nan
elif self.handle_missing == 'value':
base_df.loc[-2] = 0
mapping.append({'col': col, 'mapping': base_df})
return mapping
def transform(self, X, override_return_df=False):
"""Perform the transformation to new categorical data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples, n_numeric + N]
Transformed values with encoding applied.
"""
if self.handle_missing == 'error':
if X[self.cols].isnull().any().bool():
raise ValueError('Columns to be encoded can not contain null')
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to transform data.')
# first check the type
X = util.convert_input(X)
# then make sure that it is the right size
if X.shape[1] != self._dim:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1], self._dim, ))
if not self.cols:
return X if self.return_df else X.values
X = self.ordinal_encoder.transform(X)
if self.handle_unknown == 'error':
if X[self.cols].isin([-1]).any().any():
raise ValueError('Columns to be encoded can not contain new values')
X = self.get_dummies(X)
if self.drop_invariant:
for col in self.drop_cols:
X.drop(col, 1, inplace=True)
if self.return_df or override_return_df:
return X
else:
return X.values
def inverse_transform(self, X_in):
"""
Perform the inverse transformation to encoded data.
Parameters
----------
X_in : array-like, shape = [n_samples, n_features]
Returns
-------
p: array, the same size of X_in
"""
X = X_in.copy(deep=True)
# first check the type
X = util.convert_input(X)
if self._dim is None:
raise ValueError(
'Must train encoder before it can be used to inverse_transform data')
X = self.reverse_dummies(X, self.mapping)
# then make sure that it is the right size
if X.shape[1] != self._dim:
if self.drop_invariant:
raise ValueError("Unexpected input dimension %d, the attribute drop_invariant should "
"set as False when transform data" % (X.shape[1],))
else:
raise ValueError('Unexpected input dimension %d, expected %d' % (
X.shape[1], self._dim, ))
if not self.cols:
return X if self.return_df else X.values
for switch in self.ordinal_encoder.mapping:
column_mapping = switch.get('mapping')
inverse = pd.Series(data=column_mapping.index, index=column_mapping.get_values())
X[switch.get('col')] = X[switch.get('col')].map(inverse).astype(switch.get('data_type'))
if self.handle_unknown == 'return_nan' and self.handle_missing == 'return_nan':
for col in self.cols:
if X[switch.get('col')].isnull().any():
warnings.warn("inverse_transform is not supported because transform impute "
"the unknown category nan when encode %s" % (col,))
return X if self.return_df else X.values
def get_dummies(self, X_in):
"""
Convert numerical variable into dummy variables
Parameters
----------
X_in: DataFrame
mapping: list-like
Contains mappings of column to be transformed to it's new columns and value represented
Returns
-------
dummies : DataFrame
"""
X = X_in.copy(deep=True)
cols = X.columns.values.tolist()
for switch in self.mapping:
col = switch.get('col')
mod = switch.get('mapping')
base_df = mod.reindex(X[col])
base_df = base_df.set_index(X.index)
X = pd.concat([base_df, X], axis=1)
old_column_index = cols.index(col)
cols[old_column_index: old_column_index + 1] = mod.columns
X = X.reindex(columns=cols)
return X
def reverse_dummies(self, X, mapping):
"""
Convert dummy variable into numerical variables
Parameters
----------
X : DataFrame
mapping: list-like
Contains mappings of column to be transformed to it's new columns and value represented
Returns
-------
numerical: DataFrame
"""
out_cols = X.columns.values
cols = []
mapped_columns = []
for switch in mapping:
col = switch.get('col')
mod = switch.get('mapping')
cols.append(col)
X[col] = 0
positive_indexes = mod.index[mod.index > 0]
for i in range(positive_indexes.shape[0]):
existing_col = mod.columns[i]
val = positive_indexes[i]
X.loc[X[existing_col] == 1, col] = val
mapped_columns.append(existing_col)
out_cols = [col0 for col0 in out_cols if col0 not in mapped_columns]
return X.reindex(columns=out_cols + cols)
def get_feature_names(self):
"""
Returns the names of all transformed / added columns.
Returns
--------
feature_names: list
A list with all feature names transformed or added.
Note: potentially dropped features are not included!
"""
if not isinstance(self.feature_names, list):
raise ValueError(
'Must transform data first. Affected feature names are not known before.')
else:
return self.feature_names
