Python_ML/bootstrapaggregating.py at master · JhPlayGround/Python_ML · GitHub

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
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data',header=None)
df_wine.columns = ['Class label', 'Alcohol', 'Malic acid', 'Ash',
                   'Alcalinity of ash', 'Magnesium', 'Total phenols',
                   'Flavanoids', 'Nonflavanoid phenols', 'Proanthocyanins',
                   'Color intensity', 'Hue', 'OD280/OD315 of diluted wines',
                   'Proline']

df_wine = df_wine[df_wine['Class label'] != 1]
y = df_wine['Class label'].values
X = df_wine[['Alcohol', 'OD280/OD315 of diluted wines']].values

X_train, X_test, y_train, y_test =train_test_split(X, y, test_size=0.3, random_state=1, stratify=y)

tree = DecisionTreeClassifier(criterion='entropy', random_state=1, max_depth=None)

bag = BaggingClassifier(base_estimator=tree, n_estimators=500, max_samples=1.0, max_features=1.0, bootstrap=True, bootstrap_features=False, n_jobs=1, random_state=1)

tree = tree.fit(X_train, y_train)
y_train_pred = tree.predict(X_train)
y_test_pred = tree.predict(X_test)

tree_train = accuracy_score(y_train, y_train_pred)
tree_test = accuracy_score(y_test, y_test_pred)
print('결정 트리의 훈련 정확도/테스트 정확도 %.3f/%.3f' %(tree_train, tree_test))

bag = bag.fit(X_train, y_train)
y_train_pred = bag.predict(X_train)
y_test_pred = bag.predict(X_test)

bag_train = accuracy_score(y_train, y_train_pred)
bag_test = accuracy_score(y_test, y_test_pred)
print('배깅의 훈련 정확도/테스트 정확도 %.3f/%.3f' % (bag_train, bag_test))

x_min = X_train[:, 0].min() - 1
x_max = X_train[:, 0].max() + 1
y_min = X_train[:, 1].min() - 1
y_max = X_train[:, 1].max() + 1

xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),
                     np.arange(y_min, y_max, 0.1))

f, axarr = plt.subplots(nrows=1, ncols=2,
                        sharex='col',
                        sharey='row',
                        figsize=(8, 3))


for idx, clf, tt in zip([0, 1],
                        [tree, bag],
                        ['Decision tree', 'Bagging']):
    clf.fit(X_train, y_train)

    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)

    axarr[idx].contourf(xx, yy, Z, alpha=0.3)
    axarr[idx].scatter(X_train[y_train == 0, 0],
                       X_train[y_train == 0, 1],
                       c='blue', marker='^')

    axarr[idx].scatter(X_train[y_train == 1, 0],
                       X_train[y_train == 1, 1],
                       c='green', marker='o')

    axarr[idx].set_title(tt)

axarr[0].set_ylabel('Alcohol', fontsize=12)
plt.text(10.2, -0.5,
         s='OD280/OD315 of diluted wines',
         ha='center', va='center', fontsize=12)

plt.tight_layout()
plt.show()