def fit(self, data):
'''
fits the catagorical encoder, coecces to a pd data frame, save input and feature names
:param data: a pandas data frame, or list
:return: nothing, fitted encoder is saved as encoder
'''
from category_encoders import OneHotEncoder
ohe = OneHotEncoder(return_df=self.return_df, handle_unknown=self.handle_unknown)
x = self.replace_infrequent_df(data)
self.input_names = x.columns
ohe.fit(x)
self.encoder = ohe
self.feature_names_from_cat_encoder()
def categoricals(self,
model_name='onehot_model.pkl',
cols=None,
owr=False,
model_bin=None):
"""Onehot encoder on categoricals."""
self.log('Apply onehot encoder on categorical')
model_path = os.path.join(self.model_path, model_name)
if cols is None:
cols = self.data.cat_cols
if ((not os.path.isfile(model_path)) or owr) and (model_bin is None):
self.log('\nTrain model\n')
model_bin = OneHotEncoder(
cols=cols,
use_cat_names=True,
handle_unknown='error',
drop_invariant=False,
impute_missing=False)
model_bin.fit(self.data._X)
self.data._X = model_bin.transform(self.data._X)
setattr(model_bin, 'data_schema', self.data._X.columns.values)
# Save model
if self.auto_save:
joblib.dump(model_bin, model_path)
elif os.path.isfile(model_path):
# File exists/prediction:
model_bin = joblib.load(model_path)
self.data._X = model_bin.transform(self.data._X)
self.data.check_schema(model_bin, '_X')
else:
# Prediction in pipeline
self.data._X = model_bin.transform(self.data._X)
self.data.check_schema(model_bin, '_X')
return model_bin
def encode_low_cardinality_categorical_df(dataframe, fit=False):
"""
Encode low cardinality categorical features using OneHot Encoding and dropping invariant features
---
Arguments
dataframe: pd.DataFrame
Dataframe with pre-processed data (i.e. renamed features), low card. categorical features only
fit: boolean
Indicates if we should train or load an encoder
Returns
dataframe: pd.DataFrame
Dataframe with encoded data
"""
# Train or load an encoder
if fit:
encoder = OneHotEncoder(cols=dataframe.columns.values, drop_invariant=True)
encoder.fit(dataframe)
pickle_obj(encoder, 'low_card_categorical_encoder')
else:
encoder = unpickle_obj('low_card_categorical_encoder')
# transform data
return encoder.transform(dataframe)
def fit_onehot(input_df: pd.DataFrame, cols: List[str], na_value: Any = None):
"""
Creates the One-hot encoder by fitting it through the given DataFrame
NaN values and Special value specified under `na_value` in the DataFrame will be encoded as unseen value.
Args:
input_df: DataFrame used to fit the encoder
cols: List of categorical columns to be encoded
na_value: Default null value for DataFrame
Returns:
result_df: encoded input_df DataFrame
model : encoder model to be passed to `transform_onehot` method
"""
df = input_df.copy()
if na_value is not None:
for col in cols:
df[col] = df[col].replace({na_value: np.nan})
drop_cols = ["{}_nan".format(col) for col in cols]
encoder = OneHotEncoder(cols=cols, use_cat_names=True)
encoder = encoder.fit(df)
result_df = encoder.transform(df)
for drop_col in drop_cols:
if drop_col in result_df.columns:
result_df = result_df.drop(columns=[drop_col])
model = {
"encoder": encoder,
"cols": cols,
"na_value": na_value,
"drop_cols": drop_cols,
}
return result_df, model
train['type'].unique(), train['color'].unique() sns.violinplot(x='bone_length', y='type', data=train) sns.boxplot(x='hair_length', y='type', data=train) sns.pairplot(train) from category_encoders import OneHotEncoder encoder = OneHotEncoder(cols=['color'], use_cat_names=True) train = encoder.fit_transform(train) test = encoder.fit_transform(test) train.head() from sklearn.preprocessing import LabelEncoder encoder = LabelEncoder() encoder.fit(train['type']) print(encoder.classes_) train['type_no'] = encoder.transform(train['type']) train.head() sns.heatmap(train.corr(), xticklabels=list(train), yticklabels=list(train)) target = train['type_no'] # for visualizations target_string = train['type'] # for final predictions del train['type'] del train['type_no'] target.head() from sklearn.model_selection import train_test_split
class RFEncoder(BaseEstimator, TransformerMixin):
def __init__(self,
cols=None,
handle_missing='value',
handle_unknown='value',
use_cat_names=False,
return_df=True,
max_subsets=None,
max_depth=3,
n_estimators=100,
min_count=1,
n_jobs=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.max_subsets = max_subsets
self.max_depth = max_depth
self.n_estimators = n_estimators
self.n_jobs = n_jobs
self.min_count = min_count
def fit(self, X, y=None):
self._dim = X.shape[1]
if self.cols is None:
self.cols = get_obj_cols(X)
self.dummy_encoder = OneHotEncoder(cols=self.cols,
handle_unknown='value',
handle_missing='value')
self.dummy_encoder = self.dummy_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):
X = self.dummy_encoder.transform(X.copy(deep=True))
y = y.copy(deep=True)
mapping = []
for switch in self.dummy_encoder.mapping:
col = switch.get('col')
values = switch.get('mapping').copy(deep=True)
if isinstance(self.max_depth, int):
max_depth = self.max_depth
elif isinstance(self.max_depth, float):
max_depth = round(self.max_depth * values.shape[1])
else:
max_depth = min(self.max_depth[1],
round(self.max_depth[0] * values.shape[1]))
if max_depth == 0:
continue
forest = RandomForestClassifier(
max_depth=max_depth,
n_estimators=self.n_estimators,
n_jobs=self.n_jobs,
)
forest.fit(X[values.columns], y)
subsets = self.get_subsets(forest.decision_path(values))
subset_df = pd.DataFrame(data=subsets,
index=values.index,
columns=[
'{col}_subset_{i}'.format(col=col,
i=i)
for i in range(subsets.shape[1])
])
base_df = values.join(subset_df)
mapping.append({'col': col, 'mapping': base_df})
return mapping
def get_subsets(self, decision_path):
subset_sizes = np.asarray(decision_path[0].sum(axis=0))[0]
subsets = decision_path[0][:, subset_sizes != 1].toarray()
subsets, count = np.unique(subsets, return_counts=True, axis=1)
subsets = subsets[:, count >= self.min_count]
count = count[count >= self.min_count]
subsets = subsets[:, np.argsort(-count)]
subset_sizes = subsets.sum(axis=0)
subsets = subsets[:, np.argsort(subset_sizes)]
if self.max_subsets is not None:
subsets = subsets[:, :self.max_subsets]
return subsets
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.dummy_encoder.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
review_desc= X.review_description # seperating review before encoding
X=X.drop("review_description",axis=1)
# In[248]:
X.head()
# In[249]:
one_hot= OneHotEncoder(cols=["user_name","country","hint_variety"],use_cat_names=True) # OneHotEncoder from category_encoders package
one_hot.fit(X)
# In[250]:
X=one_hot.transform(X)
# In[253]:
X.columns
# #### Word2vec implementation -
class OneHotEncoder():
"""Maps each categorical value to several columns using one-hot encoding.
Parameters:
cols: [str]
list of column names to encode.
top_n: int
number of unique category values to encode (determines the number of resulting columns)
selects based off of number of occurences of value
defaults to 15
'None' will result in all unique values being encoded.
"""
name = 'one_hot'
def __init__(self, cols=None, top_n=15):
self.encoder = OneHot(cols=cols)
self.matrix = None
self.top_n = top_n
def fit(self, X, features, y=None):
"""Fits encoder to data table.
returns self
"""
self.encoder.fit(X, y=None)
self.features = self.encode_features_list(X, features)
return self
def transform(self, X):
"""Encodes matrix and updates features accordingly.
returns encoded matrix (dataframe)
"""
assert (self.matrix is not None), "Check that the encoder is fitted."
return self.matrix
def fit_transform(self, X, features=None, y=None):
"""First fits, then transforms matrix.
returns encoded matrix (dataframe)
"""
return self.fit(X, features, y).transform(X)
def get_mapping(self, category):
"""Gets the mapping for the one-hot encoder.
returns mapping (dict)
"""
if isinstance(category, str):
for map in self.encoder.mapping:
if map['col'] == category:
return map['mapping']
return self.encoder.mapping[category]['mapping']
def encode_features_list(self, X, features):
X_new = X.copy()
feature_list = []
for f in features:
if f.number_output_features > 1:
logger.warning(
"Feature %s has multiple columns. One-Hot Encoder may not properly encode."
"Consider using another encoding method or the `encoder` property value assigned "
"to this OneHotEncoder class instance." % (f))
if f.get_name() in self.encoder.cols:
val_counts = X[f.get_name()].value_counts().to_frame()
val_counts.sort_values(f.get_name(), ascending=False)
if self.top_n is None:
self.top_n = len(val_counts)
unique = val_counts.head(self.top_n).index.tolist()
index = X_new.columns.get_loc(f.get_name())
for label in unique:
add = ft.Feature([f], primitive=OneHotEnc(label))
feature_list.append(add)
X_new.insert(index,
add.get_name(),
(X_new[f.get_name()] == label).astype(int),
allow_duplicates=True)
index += 1
has_unknown = X[f.get_name()].isnull().values.any()
if has_unknown:
unknown = ft.Feature([f], primitive=OneHotEnc(np.nan))
feature_list.append(unknown)
X_new.insert(
index,
unknown.get_name(),
(~X_new[f.get_name()].isin(unique)).astype(int),
allow_duplicates=True)
X_new.drop([f.get_name()], axis=1, inplace=True)
else:
feature_list.append(f)
self.matrix = X_new
return feature_list
def get_features(self):
return self.features
def get_name(self):
return self.name
df['bathrooms_text'].value_counts()
df = df[df['bathrooms_text'] != '']
df[['host_is_superhost', 'bathrooms_text', 'has_availability', 'instant_bookable']].astype(float)
df.head
pip install category_encoders
# Instantiate transformer - one hot encoder
from category_encoders import OneHotEncoder
transformer = OneHotEncoder(use_cat_names=True)
# Transform to fit training data
transformer.fit(df)
# Transform our training data
df = transformer.transform(df)
X = df.drop('price', axis=1)
y= df['price']
X = X.astype(float)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
from keras.layers import BatchNormalization, Dropout
import keras
model = Sequential([
import pandas as pd
data = pd.read_csv('139394485_T_T100D_MARKET_ALL_CARRIER.csv')
# Define col names for the parameters of the network
pred_vars = ['MONTH', 'ORIGIN', 'DEST', 'DISTANCE']
target_var = 'PASSENGERS'
keep = pred_vars
keep.append(target_var)
# Subset only what's needed
data = data[keep]
# Encode the source and target nodes using a catagory encoder
from category_encoders import OneHotEncoder
ce = OneHotEncoder()
ce.fit(data)
# transform the encoded data
data_encoded = ce.transform(data)
labels = data[target_var]
data_encoded.drop(target_var, 1, inplace=True)
# split out a final eval set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(data_encoded,
labels,
random_state=0,
test_size=.25)
# convert to xgb data format
import xgboost as xgb
def get_score(model, X, y, X_test, y_test):
model.fit(X, y)
y_pred = model.predict_proba(X_test)[:, 1]
score = roc_auc_score(y_test, y_pred)
return score
######### Creating objects for 2 classification models.
logit = LogisticRegression(random_state=SEED)
rf = RandomForestClassifier(random_state=SEED)
###################################################################################################
######### Apply One Hot Encoding
from category_encoders import OneHotEncoder
onehot_enc = OneHotEncoder(cols=X_Columns)
onehot_enc.fit(X_train, y_train)
print('Original number of features: \n', X_train.shape[1], "\n")
data_ohe_train = onehot_enc.fit_transform(X_train)
data_ohe_test = onehot_enc.transform(X_test)
print('Features after OHE: \n', data_ohe_train.shape[1])
######### Logistic Regression
onehot_logit_score = get_score(logit, data_ohe_train, y_train, data_ohe_test,
y_test)
print('Logistic Regression score with One hot encoding:', onehot_logit_score)
######### Random Forest
onehot_rf_score = get_score(rf, data_ohe_train, y_train, data_ohe_test, y_test)
print('Random Forest score with One hot encoding:', onehot_logit_score)
