1. Import data:
import numpy as np
import pandas as pd
from category_encoders import TargetEncoder, MEstimateEncoder
import warnings
warnings. filter warnings('ignore')
data_df = pd.read_csv()#add path
data_df. head()
Since the data has no categorical variables, a new categorical variable SalePrice1 is added for testing and running through the data
data_df["SalePrice1"]=pd.DataFrame(np.random.randint(0,2,size=(data_df.shape[0], 1)),columns=['test']) data_df
2. MeanEncoder class definition code
import numpy as np
import pandas as pd
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import KFold
from itertools import product
class MeanEncoder:
def __init__(self, categorical_features, n_splits=5, target_type='classification', prior_weight_func=None):
"""
:param categorical_features: list of str, the name of the categorical columns to encode
:param n_splits: the number of splits used in mean encoding
:param target_type: str, 'regression' or 'classification'
:param prior_weight_func:
a function that takes in the number of observations, and outputs prior weight
When a dict is passed, the default exponential decay function will be used:
k: the number of observations needed for the posterior to be weighted equally as the prior
f: larger f --> smaller slope
"""
self.categorical_features = categorical_features
self.n_splits = n_splits
self. learned_stats = {}
if target_type == 'classification':
self. target_type = target_type
self. target_values = []
else:
self. target_type = 'regression'
self. target_values = None
if isinstance(prior_weight_func, dict):
self.prior_weight_func = eval('lambda x: 1 / (1 + np.exp((x - k) / f))', dict(prior_weight_func, np=np))
elif callable(prior_weight_func):
self.prior_weight_func = prior_weight_func
else:
self.prior_weight_func = lambda x: 1 / (1 + np.exp((x - 2) / 1))
@staticmethod
def mean_encode_subroutine(X_train, y_train, X_test, variable, target, prior_weight_func):
X_train = X_train[[variable]].copy()
X_test = X_test[[variable]].copy()
if target is not None:
nf_name = '{}_pred_{}'. format(variable, target)
X_train['pred_temp'] = (y_train == target).astype(int) # classification
else:
nf_name = '{}_pred'. format(variable)
#print(y_train) #LotShape_pred
X_train['pred_temp'] = y_train # regression
prior = X_train['pred_temp']. mean()
#print(prior)
##
col_avg_y = X_train.groupby(by=variable, axis=0)['pred_temp'].agg([("mean",'mean'),('beta', 'size')])
col_avg_y['beta'] = prior_weight_func(col_avg_y['beta'])
print(col_avg_y['beta'])
col_avg_y[nf_name] = col_avg_y['beta'] * prior + (1 - col_avg_y['beta']) * col_avg_y['mean']
col_avg_y.drop(['beta', 'mean'], axis=1, inplace=True)
# print(col_avg_y)
nf_train = X_train.join(col_avg_y, on=variable)[nf_name].values
nf_test = X_test.join(col_avg_y, on=variable).fillna(prior, inplace=False)[nf_name].values
return nf_train, nf_test, prior, col_avg_y
def fit_transform(self, X, y):
"""
:param X: pandas DataFrame, n_samples * n_features
:param y: pandas Series or numpy array, n_samples
:return X_new: the transformed pandas DataFrame containing mean-encoded categorical features
"""
X_new = X.copy()
print(X_new)
if self. target_type == 'classification':
skf = StratifiedKFold(self.n_splits)
else:
skf = KFold(self.n_splits)
if self. target_type == 'classification':
self. target_values = sorted(set(y))
print(self. target_values)
self.learned_stats = {'{}_pred_{}'.format(variable, target): [] for variable, target in
product(self. categorical_features, self. target_values)}
print(self. learned_stats)
for variable, target in product(self. categorical_features, self. target_values):
print(variable, target)
nf_name = '{}_pred_{}'. format(variable, target)
X_new.loc[:, nf_name] = np.nan
for large_ind, small_ind in skf.split(y, y):
nf_large, nf_small, prior, col_avg_y = MeanEncoder.mean_encode_subroutine(
X_new.iloc[large_ind], y.iloc[large_ind], X_new.iloc[small_ind], variable, target, self.prior_weight_func)
X_new.iloc[small_ind, -1] = nf_small
self.learned_stats[nf_name].append((prior, col_avg_y))
print(X_new)
else:
self.learned_stats = {'{}_pred'.format(variable): [] for variable in self.categorical_features}
for variable in self.categorical_features:
print(variable)
nf_name = '{}_pred'. format(variable)
X_new.loc[:, nf_name] = np.nan
print(skf. split(y, y))
for large_ind, small_ind in skf.split(y, y):
print(large_ind. shape, small_ind. shape)
nf_large, nf_small, prior, col_avg_y = MeanEncoder.mean_encode_subroutine(
X_new.iloc[large_ind], y.iloc[large_ind], X_new.iloc[small_ind], variable, None, self.prior_weight_func)
X_new.iloc[small_ind, -1] = nf_small
self.learned_stats[nf_name].append((prior, col_avg_y))
return X_new
def transform(self, X):
"""
:param X: pandas DataFrame, n_samples * n_features
:return X_new: the transformed pandas DataFrame containing mean-encoded categorical features
"""
X_new = X.copy()
if self. target_type == 'classification':
for variable, target in product(self. categorical_features, self. target_values):
nf_name = '{}_pred_{}'. format(variable, target)
X_new[nf_name] = 0
for prior, col_avg_y in self.learned_stats[nf_name]:
X_new[nf_name] + = X_new[[variable]].join(col_avg_y, on=variable).fillna(prior, inplace=False)[
nf_name]
X_new[nf_name] /= self.n_splits
else:
for variable in self.categorical_features:
nf_name = '{}_pred'. format(variable)
X_new[nf_name] = 0
for prior, col_avg_y in self.learned_stats[nf_name]:
X_new[nf_name] + = X_new[[variable]].join(col_avg_y, on=variable).fillna(prior, inplace=False)[
nf_name]
X_new[nf_name] /= self.n_splits
return X_new
3. Call the function and run through the fit_transform() method
data_df[“SalePrice1”] is composed of 0 and 1, which can be considered as a classification, so in the definition code of the MeanEncoder class above, target_type=’classification’
enc = MeanEncoder(['LotShape', 'SaleType']) enc=enc.fit_transform(data_df[['LotShape', 'SaleType']], data_df["SalePrice1"]) enc
The result is as follows:
data_df[“SalePrice”] consists of numerical values, which can be considered as regression, so in the definition code of the MeanEncoder class above, let target_type=’regression’
enc = MeanEncoder(['LotShape', 'SaleType']) enc=enc.fit_transform(data_df[['LotShape', 'SaleType']], data_df["SalePrice"]) enc
The result is as follows:
