-
Notifications
You must be signed in to change notification settings - Fork 2
/
classification_tree_advanced.py
178 lines (111 loc) · 5.77 KB
/
classification_tree_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
175
176
177
178
##############################################################################
# IMPORT REQUIRED PACKAGES
##############################################################################
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import pickle
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split, cross_val_score, KFold
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score
from sklearn.preprocessing import OneHotEncoder
##############################################################################
# IMPORT SAMPLE DATA
##############################################################################
# import
data_for_model = pickle.load(open("data/abc_classification_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)
# class balance
data_for_model["signup_flag"].value_counts(normalize = True)
##############################################################################
# DEAL WITH MISSING VALUES
##############################################################################
data_for_model.isna().sum()
data_for_model.dropna(how = "any", inplace = True)
##############################################################################
# SPLIT INPUT VARIABLES & OUTPUT VARIABLES
##############################################################################
X = data_for_model.drop(["signup_flag"], axis = 1)
y = data_for_model["signup_flag"]
##############################################################################
# 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, stratify = y)
##############################################################################
# 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)
##############################################################################
# MODEL TRAINING
##############################################################################
clf = DecisionTreeClassifier(random_state = 42, max_depth = 5)
clf.fit(X_train, y_train)
##############################################################################
# MODEL ASSESSMENT
##############################################################################
y_pred_class = clf.predict(X_test)
y_pred_prob = clf.predict_proba(X_test)[:,1]
##############################################################################
# CONFUSION MATRIX
##############################################################################
conf_matrix = confusion_matrix(y_test, y_pred_class)
plt.style.use("seaborn-poster")
plt.matshow(conf_matrix, cmap = "coolwarm")
plt.gca().xaxis.tick_bottom()
plt.title("Confusion Matrix")
plt.ylabel("Actual Class")
plt.xlabel("Predicted Class")
for (i, j), corr_value in np.ndenumerate(conf_matrix):
plt.text(j, i, corr_value, ha = "center", va = "center", fontsize = 20)
plt.show()
# accuracy (the number of correct classifications out of all attempted classifications)
accuracy_score(y_test, y_pred_class)
# precision (of all observations that were predicted as positive, how many were actually positive)
precision_score(y_test, y_pred_class)
# recall (of all positive observations, how many did we predict as positive)
recall_score(y_test, y_pred_class)
# f1-score (harmonic mean of precision and recall)
f1_score(y_test, y_pred_class)
##############################################################################
# FINDING THE BEST MAX DEPTH
##############################################################################
max_depth_list = list(range(1,15))
accuracy_scores = []
for depth in max_depth_list:
clf = DecisionTreeClassifier(max_depth = depth, random_state = 42)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = f1_score(y_test, y_pred)
accuracy_scores.append(accuracy)
max_accuracy = max(accuracy_scores)
max_accuracy_idx = accuracy_scores.index(max_accuracy)
opitmal_depth = max_depth_list[max_accuracy_idx]
# plot of max depths
plt.plot(max_depth_list, accuracy_scores)
plt.scatter(opitmal_depth, max_accuracy, marker = "x", color = "red")
plt.title(f"Accuracy (F1 Score) by Max Depth \n Optimal Tree Depth: {opitmal_depth} (Accuracy: {round(max_accuracy, 4)}")
plt.xlabel("Max Depth of Decision Tree")
plt.ylabel("Accuracy (F1 Score)")
plt.tight_layout()
plt.show()
# plot our model
plt.figure(figsize=(25,15))
tree = plot_tree(clf,
feature_names = X.columns,
filled = True,
rounded = True,
fontsize = 16)