def test_find_categorical_variables(dataframe_vartypes):
vars_cat = ['Name', 'City']
vars_mix = ['Age', 'Marks', 'Name']
vars_none = None
assert _find_categorical_variables(dataframe_vartypes,
vars_cat) == vars_cat
assert _find_categorical_variables(dataframe_vartypes,
vars_none) == vars_cat
with pytest.raises(TypeError):
assert _find_categorical_variables(dataframe_vartypes, vars_mix)
def test_find_categorical_variables(df_vartypes):
vars_cat = ["Name", "City"]
vars_mix = ["Age", "Marks", "Name"]
vars_none = None
assert _find_categorical_variables(df_vartypes, vars_cat) == vars_cat
assert _find_categorical_variables(df_vartypes, vars_none) == vars_cat
with pytest.raises(TypeError):
assert _find_categorical_variables(df_vartypes, vars_mix)
with pytest.raises(ValueError):
assert _find_categorical_variables(df_vartypes[["Age", "Marks"]], None)
def fit(self, X, y=None):
"""
Learns the frequent categories for each variable.
Parameters
----------
X : pandas dataframe of shape = [n_samples, n_features]
The training input samples.
Can be the entire dataframe, not just selected variables
y : None
y is not required. You can pass y or None.
Attributes
----------
encoder_dict_: dictionary
The dictionary containing the frequent categories (that will be kept)
for each variable. Categories not present in this list will be replaced
by 'Rare' or by the user defined value.
"""
# check input dataframe
X = _is_dataframe(X)
# find categorical variables or check that those entered by the user
# are of type object
self.variables = _find_categorical_variables(X, self.variables)
# check if dataset contains na
_check_contains_na(X, self.variables)
self.encoder_dict_ = {}
for var in self.variables:
if len(X[var].unique()) > self.n_categories:
# if the variable has more than the indicated number of categories
# the encoder will learn the most frequent categories
t = pd.Series(X[var].value_counts() / np.float(len(X)))
# non-rare labels:
self.encoder_dict_[var] = t[t >= self.tol].index
else:
# if the total number of categories is smaller than the indicated
# the encoder will consider all categories as frequent.
warnings.warn(
"The number of unique categories for variable {} is less than that indicated in "
"n_categories. Thus, all categories will be considered frequent"
.format(var))
self.encoder_dict_[var] = X[var].unique()
self.encoder_dict_ = _check_encoding_dictionary(self.encoder_dict_)
self.input_shape_ = X.shape
return self
def fit(self, X, y=None):
"""
Learns the unique categories per variable. If top_categories is indicated,
it will learn the most popular categories. Alternatively, it learns all
unique categories per variable.
Parameters
----------
X : pandas dataframe of shape = [n_samples, n_features]
The training input samples.
Can be the entire dataframe, not just seleted variables.
y : pandas series, default=None
Target. It is not needed in this encoded. You can pass y or
None.
Attributes
----------
encoder_dict_: dictionary
The dictionary containing the categories for which dummy variables
will be created.
"""
# check input dataframe
X = _is_dataframe(X)
# find categorical variables or check that those entered by the user
# are of type object
self.variables = _find_categorical_variables(X, self.variables)
# check if dataset contains na
_check_contains_na(X, self.variables)
self.encoder_dict_ = {}
for var in self.variables:
if not self.top_categories:
if self.drop_last:
category_ls = [x for x in X[var].unique()]
self.encoder_dict_[var] = category_ls[:-1]
else:
self.encoder_dict_[var] = X[var].unique()
else:
self.encoder_dict_[var] = [
x for x in X[var].value_counts().sort_values(
ascending=False).head(self.top_categories).index
]
self.encoder_dict_ = _check_encoding_dictionary(self.encoder_dict_)
self.input_shape_ = X.shape
return self
def fit(self, X, y=None):
""" Learns the numbers to be used to replace the categories in each
variable.
Parameters
----------
X : pandas dataframe of shape = [n_samples, n_features]
The training input samples.
Can be the entire dataframe, not just the variables to be
encoded.
y : pandas series, default=None
The Target. Can be None if encoding_method = 'arbitrary'.
Otherwise, y needs to be passed when fitting the transformer.
"""
# check input dataframe
X = _is_dataframe(X)
# find categorical variables or check that those entered by the user
# are of type object
self.variables = _find_categorical_variables(X, self.variables)
# check if dataset contains na
_check_contains_na(X, self.variables)
# join target to predictor variables
if self.encoding_method == 'ordered':
if y is None:
raise ValueError(
'Please provide a target y for this encoding method')
temp = pd.concat([X, y], axis=1)
temp.columns = list(X.columns) + ['target']
# find mappings
self.encoder_dict_ = {}
for var in self.variables:
if self.encoding_method == 'ordered':
t = temp.groupby(
[var])['target'].mean().sort_values(ascending=True).index
elif self.encoding_method == 'arbitrary':
t = X[var].unique()
self.encoder_dict_[var] = {k: i for i, k in enumerate(t, 0)}
self.encoder_dict_ = _check_encoding_dictionary(self.encoder_dict_)
self.input_shape_ = X.shape
return self
def _check_fit_input_and_variables(self, X: pd.DataFrame) -> pd.DataFrame:
# check input dataframe
X = _is_dataframe(X)
# find categorical variables or check variables entered by user are object
self.variables = _find_categorical_variables(X, self.variables)
# check if dataset contains na
_check_contains_na(X, self.variables)
return X
def fit(self, X, y=None):
"""
Learns the most frequent category if the imputation method is set to frequent.
Parameters
----------
X : pandas dataframe of shape = [n_samples, n_features]
The training input samples.
Can be the entire dataframe, not just the selected variables.
y : None
y is not needed in this imputation. You can pass None or y.
Attributes
----------
imputer_dict_: dictionary
The dictionary mapping each variable to the most frequent category, or to
the value 'Missing' depending on the imputation_method. The most frequent
category is calculated when fitting the transformer.
"""
# check input dataframe
X = _is_dataframe(X)
# find or check for categorical variables
self.variables = _find_categorical_variables(X, self.variables)
if self.imputation_method == "missing":
self.imputer_dict_ = {
var: self.fill_value
for var in self.variables
}
elif self.imputation_method == "frequent":
self.imputer_dict_ = {}
for var in self.variables:
mode_vals = X[var].mode()
# careful: some variables contain multiple modes
if len(mode_vals) == 1:
self.imputer_dict_[var] = mode_vals[0]
else:
raise ValueError(
"Variable {} contains multiple frequent categories.".
format(var))
self.input_shape_ = X.shape
return self
def fit(self, X, y=None):
"""
Learns the counts or frequencies which will be used to replace the categories.
Parameters
----------
X : pandas dataframe of shape = [n_samples, n_features]
The training input samples.
The user can pass the entire dataframe.
y : None
y is not needed in this encoder. You can pass y or None.
Attributes
----------
encoder_dict_: dictionary
Dictionary containing the {category: count / frequency} pairs for
each variable.
"""
# check input dataframe
X = _is_dataframe(X)
# find categorical variables or check that those entered by the user
# are of type object
self.variables = _find_categorical_variables(X, self.variables)
# check if dataset contains na
_check_contains_na(X, self.variables)
self.encoder_dict_ = {}
# learn encoding maps
for var in self.variables:
if self.encoding_method == 'count':
self.encoder_dict_[var] = X[var].value_counts().to_dict()
elif self.encoding_method == 'frequency':
n_obs = np.float(len(X))
self.encoder_dict_[var] = (X[var].value_counts() /
n_obs).to_dict()
self.encoder_dict_ = _check_encoding_dictionary(self.encoder_dict_)
self.input_shape_ = X.shape
return self
def fit(self, X, y):
"""
Learns the mean value of the target for each category of the variable.
Parameters
----------
X : pandas dataframe of shape = [n_samples, n_features]
The training input samples.
Can be the entire dataframe, not just the variables to be encoded.
y : pandas series
The target.
Attributes
----------
encoder_dict_: dictionary
The dictionary containing the {category: target mean} pairs used
to replace categories in every variable.
"""
# check input dataframe
X = _is_dataframe(X)
# find categorical variables or check that those entered by the user
# are of type object
self.variables = _find_categorical_variables(X, self.variables)
# check if dataset contains na
_check_contains_na(X, self.variables)
if y is None:
raise ValueError(
'Please provide a target y for this encoding method')
temp = pd.concat([X, y], axis=1)
temp.columns = list(X.columns) + ['target']
self.encoder_dict_ = {}
for var in self.variables:
self.encoder_dict_[var] = temp.groupby(
var)['target'].mean().to_dict()
self.encoder_dict_ = _check_encoding_dictionary(self.encoder_dict_)
self.input_shape_ = X.shape
return self
def fit(self, X, y=None):
"""
Learns the numbers that should be used to replace the categories in each
variable.
Parameters
----------
X : pandas dataframe of shape = [n_samples, n_features]
The training input samples.
Can be the entire dataframe, not just the categorical variables.
y : pandas series.
The target variable. Required to train the decision tree and for
ordered ordinal encoding.
"""
# check input dataframe
X = _is_dataframe(X)
# find categorical variables or check that those entered by the user
# are of type object
self.variables = _find_categorical_variables(X, self.variables)
# check if dataset contains na
_check_contains_na(X, self.variables)
# initialize categorical encoder
cat_encoder = OrdinalCategoricalEncoder(encoding_method=self.encoding_method,
variables=self.variables)
# initialize decision tree discretiser
tree_discretiser = DecisionTreeDiscretiser(cv=self.cv, scoring=self.scoring,
variables=self.variables, param_grid=self.param_grid,
regression=self.regression, random_state=self.random_state)
# pipeline for the encoder
self.encoder_ = Pipeline([('categorical_encoder', cat_encoder),
('tree_discretiser', tree_discretiser)])
self.encoder_.fit(X, y)
self.input_shape_ = X.shape
return self
def fit(self, X, y):
"""
Learns the numbers that should be used to replace the categories in each
variable. That is the WoE or ratio of probability.
Parameters
----------
X : pandas dataframe of shape = [n_samples, n_features]
The training input samples.
Can be the entire dataframe, not just the categorical variables.
y : pandas series.
Target, must be binary [0,1].
Attributes
----------
encoder_dict_: dictionary
The dictionary containing the {category: WoE / ratio} pairs per variable.
"""
# check input dataframe
X = _is_dataframe(X)
# find categorical variables or check that those entered by the user
# are of type object
self.variables = _find_categorical_variables(X, self.variables)
# check if dataset contains na
_check_contains_na(X, self.variables)
if y is None:
raise ValueError(
'Please provide a target y for this encoding method')
# check that y is binary
if len([x for x in y.unique() if x not in [0, 1]]) > 0:
raise ValueError(
"This encoder is only designed for binary classification, values of y can be only 0 or 1"
)
temp = pd.concat([X, y], axis=1)
temp.columns = list(X.columns) + ['target']
self.encoder_dict_ = {}
if self.encoding_method == 'woe':
total_pos = temp['target'].sum()
total_neg = len(temp) - total_pos
temp['non_target'] = np.where(temp['target'] == 1, 0, 1)
for var in self.variables:
pos = temp.groupby([var])['target'].sum() / total_pos
neg = temp.groupby([var])['non_target'].sum() / total_neg
t = pd.concat([pos, neg], axis=1)
t['woe'] = np.log(t['target'] / t['non_target'])
if not t.loc[t['target'] == 0, :].empty or not t.loc[
t['non_target'] == 0, :].empty:
raise ValueError(
"The proportion of 1 of the classes for a category in variable {} is zero, and log of zero is "
"not defined".format(var))
self.encoder_dict_[var] = t['woe'].to_dict()
else:
for var in self.variables:
t = temp.groupby(var)['target'].mean()
t = pd.concat([t, 1 - t], axis=1)
t.columns = ['p1', 'p0']
if self.encoding_method == 'log_ratio':
if not t.loc[t['p0'] == 0, :].empty or not t.loc[
t['p1'] == 0, :].empty:
raise ValueError(
"p(0) or p(1) for a category in variable {} is zero, log of zero is not defined"
.format(var))
else:
self.encoder_dict_[var] = (np.log(t.p1 /
t.p0)).to_dict()
elif self.encoding_method == 'ratio':
if not t.loc[t['p0'] == 0, :].empty:
raise ValueError(
"p(0) for a category in variable {} is zero, division by 0 is not defined"
.format(var))
else:
self.encoder_dict_[var] = (t.p1 / t.p0).to_dict()
self.encoder_dict_ = _check_encoding_dictionary(self.encoder_dict_)
self.input_shape_ = X.shape
return self
