-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathMeanEncoder.py
129 lines (110 loc) · 5.94 KB
/
MeanEncoder.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
import numpy as np
import pandas as pd
from sklearn.model_selection import StratifiedKFold
from itertools import product
from sklearn.model_selection import KFold
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)
X_train['pred_temp'] = y_train # regression
prior = X_train['pred_temp'].mean()
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'])
# col_avg_y[nf_name] = col_avg_y['beta'] * prior + (1 - col_avg_y['beta']) * col_avg_y['mean']
col_avg_y[nf_name] = 0.3 * prior + (1 - 0.3) * col_avg_y['mean']
col_avg_y.drop(['beta', 'mean'], axis=1, inplace=True)
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()
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))
self.learned_stats = {'{}_pred_{}'.format(variable, target): [] for variable, target in
product(self.categorical_features, self.target_values)}
for variable, target in product(self.categorical_features, self.target_values):
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[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))
else:
self.learned_stats = {'{}_pred'.format(variable): [] for variable in self.categorical_features}
for variable in self.categorical_features:
nf_name = '{}_pred'.format(variable)
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[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