rafor 0.3.0

Fast Random Forest library.
Documentation 
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

import pandas as pd
import sys

from sklearn import tree
from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
from sklearn.metrics import f1_score, mean_squared_error
from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor

def classifier_accuracy(u, v):
    u = list(u)
    v = list(v)
    assert len(u) == len(v)
    return sum(x == y for x, y in zip(u, v)) / len(u)


def decision_tree_classifier_overfit_self():
    print(sys._getframe().f_code.co_name, end='. ')
    df = pd.read_csv('../datasets/winequality-red.csv', sep=';')
    X = df.iloc[:, :-1]
    y = df.iloc[:, -1]
    clf = DecisionTreeClassifier(random_state=42)
    clf.fit(X, y)
    y_pred = clf.predict(X)
    print("Accuracy:", classifier_accuracy(y, y_pred))


def random_forest_classifier_depth10_self():
    print(sys._getframe().f_code.co_name, end='. ')
    df = pd.read_csv('../datasets/winequality-red.csv', sep=';')
    X = df.iloc[:, :-1]
    y = df.iloc[:, -1]
    clf = RandomForestClassifier(random_state=42, max_depth=10, n_estimators=100)
    clf.fit(X, y)
    y_pred = clf.predict(X)
    print("Accuracy:", classifier_accuracy(y, y_pred))


def random_forest_classifier_overfit_self():
    print(sys._getframe().f_code.co_name, end='. ')
    df = pd.read_csv('../datasets/winequality-red.csv', sep=';')
    X = df.iloc[:, :-1]
    y = df.iloc[:, -1]
    clf = RandomForestClassifier(random_state=42, max_depth=100, n_estimators=100)
    clf.fit(X, y)
    y_pred = clf.predict(X)
    print("Accuracy:", classifier_accuracy(y, y_pred))


def split_dataset(X, y):
    SPLIT_STEP = 5
    X_train = X.loc[X.index % SPLIT_STEP != 0]
    X_pred = X.loc[X.index % SPLIT_STEP == 0]
    y_train = y.loc[y.index % SPLIT_STEP != 0]
    y_ref = y.loc[y.index % SPLIT_STEP == 0]
    return X_train, y_train, X_pred, y_ref


def read_wine_dataset():
    df = pd.read_csv('../datasets/winequality-red.csv', sep=';')
    X = df.iloc[:, :-1]
    y = df.iloc[:, -1]
    return X, y


def decision_tree_classifier_depth10():
    print(sys._getframe().f_code.co_name, end='. ')
    X_train, y_train, X_pred, y_ref = split_dataset(*read_wine_dataset())
    clf = DecisionTreeClassifier(random_state=42, max_depth=10)
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_pred)
    print("Accuracy:", classifier_accuracy(y_ref, y_pred))


def random_forest_classifier_depth10():
    print(sys._getframe().f_code.co_name, end='. ')
    X_train, y_train, X_pred, y_ref = split_dataset(*read_wine_dataset())
    clf = RandomForestClassifier(random_state=42, max_depth=10, n_estimators=100)
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_pred)
    print("Accuracy:", classifier_accuracy(y_ref, y_pred))


def random_forest_binary_classification():
    print(sys._getframe().f_code.co_name, end='. ')
    df = pd.read_csv('../datasets/magic04.data')
    X = df.iloc[:, :-1]
    y = df.iloc[:, -1]
    X_train, y_train, X_pred, y_ref = split_dataset(X, y)
    clf = RandomForestClassifier(random_state=42, max_depth=10, n_estimators=100)
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_pred)
    print("F1-score:", f1_score(y_ref, y_pred, pos_label='h'))


def decision_tree_regressor_overfit_self():
    print(sys._getframe().f_code.co_name, end='. ')
    df = pd.read_csv('../datasets/Folds5x2_pp.csv')
    X = df.iloc[:, :-1]
    y = df.iloc[:, -1]
    clf = DecisionTreeRegressor(max_depth=1000)
    clf.fit(X, y)
    y_pred = clf.predict(X)
    print("Error:", mean_squared_error(y, y_pred))



def decision_tree_regressor():
    print(sys._getframe().f_code.co_name, end='. ')
    df = pd.read_csv('../datasets/Folds5x2_pp.csv')
    X = df.iloc[:, :-1]
    y = df.iloc[:, -1]
    X_train, y_train, X_pred, y_ref = split_dataset(X, y)
    clf = DecisionTreeRegressor(max_depth=10)
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_pred)
    print("Error:", mean_squared_error(y_ref, y_pred))



def random_forest_regressor_overfit_self():
    print(sys._getframe().f_code.co_name, end='. ')
    df = pd.read_csv('../datasets/Folds5x2_pp.csv')
    X = df.iloc[:, :-1]
    y = df.iloc[:, -1]
    clf = RandomForestRegressor(n_estimators=25, max_depth=1000)
    clf.fit(X, y)
    y_pred = clf.predict(X)
    print("Error:", mean_squared_error(y, y_pred))



def random_forest_regressor(max_depth):
    df = pd.read_csv('../datasets/Folds5x2_pp.csv')
    X = df.iloc[:, :-1]
    y = df.iloc[:, -1]
    X_train, y_train, X_pred, y_ref = split_dataset(X, y)
    clf = RandomForestRegressor(max_depth=max_depth, n_estimators=100)
    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_pred)
    print("Error:", mean_squared_error(y_ref, y_pred))


def random_forest_regressor_depth5():
    print(sys._getframe().f_code.co_name, end='. ')
    random_forest_regressor(max_depth=5)


def random_forest_regressor_depth10():
    print(sys._getframe().f_code.co_name, end='. ')
    random_forest_regressor(max_depth=10)


def run_tests():
    decision_tree_classifier_overfit_self()
    decision_tree_classifier_depth10()

    random_forest_binary_classification()

    random_forest_classifier_overfit_self()
    random_forest_classifier_depth10()
    random_forest_classifier_depth10_self()

    decision_tree_regressor_overfit_self()
    decision_tree_regressor()

    random_forest_regressor_overfit_self()
    random_forest_regressor_depth5()
    random_forest_regressor_depth10()


if __name__ == "__main__":
    run_tests()