-
Notifications
You must be signed in to change notification settings - Fork 2
/
linear_regression_advanced.py
174 lines (109 loc) · 5.69 KB
/
linear_regression_advanced.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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
##############################################################################
# IMPORT REQUIRED PACKAGES
##############################################################################
import pandas as pd
import matplotlib.pyplot as plt
import pickle
from sklearn.linear_model import LinearRegression
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split, cross_val_score, KFold
from sklearn.metrics import r2_score
from sklearn.preprocessing import OneHotEncoder
from sklearn.feature_selection import RFECV
##############################################################################
# IMPORT SAMPLE DATA
##############################################################################
# import
data_for_model = pickle.load(open("data/abc_regression_modelling.p", "rb"))
# drop necessary columns
data_for_model.drop("customer_id", axis = 1, inplace = True)
# shuffle data
data_for_model = shuffle(data_for_model, random_state = 42)
##############################################################################
# DEAL WITH MISSING VALUES
##############################################################################
data_for_model.isna().sum()
data_for_model.dropna(how = "any", inplace = True)
##############################################################################
# DEAL WITH OUTLIERS
##############################################################################
outlier_investigation = data_for_model.describe()
outlier_columns = ["distance_from_store", "total_sales", "total_items"]
# boxplot approach
for column in outlier_columns:
lower_quartile = data_for_model[column].quantile(0.25)
upper_quartile = data_for_model[column].quantile(0.75)
iqr = upper_quartile - lower_quartile
iqr_extended = iqr * 2
min_border = lower_quartile - iqr_extended
max_border = upper_quartile + iqr_extended
outliers = data_for_model[(data_for_model[column] < min_border) | (data_for_model[column] > max_border)].index
print(f"{len(outliers)} outliers detected in column {column}")
data_for_model.drop(outliers, inplace = True)
##############################################################################
# SPLIT INPUT VARIABLES & OUTPUT VARIABLES
##############################################################################
X = data_for_model.drop(["customer_loyalty_score"], axis = 1)
y = data_for_model["customer_loyalty_score"]
##############################################################################
# SPLIT OUT TRAINING & TEST SETS
##############################################################################
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 42)
##############################################################################
# DEAL WITH CATEGORICAL VALUES
##############################################################################
categorical_vars = ["gender"]
one_hot_encoder = OneHotEncoder(sparse=False, drop = "first")
X_train_encoded = one_hot_encoder.fit_transform(X_train[categorical_vars])
X_test_encoded = one_hot_encoder.transform(X_test[categorical_vars])
encoder_feature_names = one_hot_encoder.get_feature_names(categorical_vars)
X_train_encoded = pd.DataFrame(X_train_encoded, columns = encoder_feature_names)
X_train = pd.concat([X_train.reset_index(drop=True), X_train_encoded.reset_index(drop=True)], axis = 1)
X_train.drop(categorical_vars, axis = 1, inplace = True)
X_test_encoded = pd.DataFrame(X_test_encoded, columns = encoder_feature_names)
X_test = pd.concat([X_test.reset_index(drop=True), X_test_encoded.reset_index(drop=True)], axis = 1)
X_test.drop(categorical_vars, axis = 1, inplace = True)
##############################################################################
# FEATURE SELECTION
##############################################################################
regressor = LinearRegression()
feature_selector = RFECV(regressor)
fit = feature_selector.fit(X_train, y_train)
optimal_feature_count = feature_selector.n_features_
print(f"Optimal numer of features: {optimal_feature_count}")
X_train = X_train.loc[:, feature_selector.get_support()]
X_test = X_test.loc[:, feature_selector.get_support()]
plt.plot(range(1, len(fit.grid_scores_) + 1), fit.grid_scores_, marker = "o")
plt.ylabel("Model Score")
plt.xlabel("Number of Features")
plt.title(f"Feature Selection using RFE \n Optimal number of features is {optimal_feature_count} (at score of {round(max(fit.grid_scores_), 4)})")
plt.tight_layout()
plt.show()
##############################################################################
# MODEL TRAINING
##############################################################################
regressor = LinearRegression()
regressor.fit(X_train, y_train)
##############################################################################
# MODEL ASSESSMENT
##############################################################################
# predict on the test set
y_pred = regressor.predict(X_test)
# calculate r-squared
r_squared = r2_score(y_test, y_pred)
print(r_squared)
# cross validation (CV)
cv = KFold(n_splits = 4, shuffle = True, random_state = 42)
cv_scores = cross_val_score(regressor, X_train, y_train, cv = cv, scoring = "r2")
cv_scores.mean()
# calculate adjusted r-squared
num_data_points, num_input_vars = X_test.shape
adjusted_r_squared = 1 - (1 - r_squared) * (num_data_points - 1) / (num_data_points - num_input_vars - 1)
print(adjusted_r_squared)
# extract model coefficients
coefficients = pd.DataFrame(regressor.coef_)
input_variable_names = pd.DataFrame(X_train.columns)
summary_stats = pd.concat([input_variable_names, coefficients], axis = 1)
summary_stats.columns = ["input_variable", "coefficient"]
# extract model intercept
regressor.intercept_