3.2 决策树可视化_features = ['age', 'work', 'house', 'credit']

作者：一键难忘520 | 2024-06-23 19:03:05

踩

features = ['age', 'work', 'house', 'credit']

文章目录

引言

以下show函数决定生成图片还是pdf

1.生成图片

import numpy as np
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn import tree
import pydotplus
import matplotlib as mpl

# 加载数据
def loaddata():
    features = ["age", "work", "house", "credit"]
    x_train = pd.DataFrame([
        ["青年", "否", "否", "一般"],
        ["青年", "否", "否", "好"],
        ["青年", "是", "否", "好"],
        ["青年", "是", "是", "一般"],
        ["青年", "否", "否", "一般"],
        ["中年", "否", "否", "一般"],
        ["中年", "否", "否", "好"],
        ["中年", "是", "是", "好"],
        ["中年", "否", "是", "非常好"],
        ["中年", "否", "是", "非常好"],
        ["老年", "否", "是", "非常好"],
        ["老年", "否", "是", "好"],
        ["老年", "是", "否", "好"],
        ["老年", "是", "否", "非常好"],
        ["老年", "否", "否", "一般"]
    ])
    y_train = pd.DataFrame(["否", "否", "是", "是", "否", "否", "否", "是", "是", "是", "是", "是", "是", "是", "否"])
    y_type = [str(k) for k in np.unique(y_train)]
    # one-hot编码
    le_x = LabelEncoder()
    le_x.fit(np.unique(x_train))
    x_train = x_train.apply(le_x.transform)

    le_y = LabelEncoder()
    le_y.fit(y_train)
    y_train = le_y.transform(y_train)
    return x_train, y_train,features,le_x,le_y


# 决策树可视化
def show(clf,feature,y_type):
    dot_data = tree.export_graphviz(clf,out_file=None,
                                    feature_names=feature,
                                    class_names=y_type,filled=True,
                                    rounded=True,special_characters=True)
    # 生成图片
    graph = pydotplus.graph_from_dot_data(dot_data)
    graph.write_png('DT_show.png')






if __name__ == '__main__':
    mpl.rcParams["font.sans-serif"] = [u'simHei']
    mpl.rcParams['axes.unicode_minus'] = False
    # 加载数据
    x_train, y_train,features,le_x,le_y = loaddata()
    # 分类
    clf = DecisionTreeClassifier()
    clf.fit(x_train, y_train)
    y_type = [str(k) for k in np.unique(y_train)]
    # 可视化
    show(clf, features,y_type)

    # 预测
    X_show = pd.DataFrame([["青年", "否", "否", "一般"]])
    X_test = X_show.apply(le_x.transform)
    y_predict = clf.predict(X_test)
    # 结果输出
    X_show = [{features[i] :X_show.values[0][i]} for i in range(len(features))]
    print("{0}被分类为{1}".format(X_show,le_y.inverse_transform(y_predict)))


[{'age': '青年'}, {'work': '否'}, {'house': '否'}, {'credit': '一般'}]被分类为['否']
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

在这里插入图片描述

2.生成pdf

import pydotplus
import graphviz
import numpy as np
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn import tree
import matplotlib as mpl

# 加载数据
def loaddata():
    features = ["age", "work", "house", "credit"]
    x_train = pd.DataFrame([
        ["青年", "否", "否", "一般"],
        ["青年", "否", "否", "好"],
        ["青年", "是", "否", "好"],
        ["青年", "是", "是", "一般"],
        ["青年", "否", "否", "一般"],
        ["中年", "否", "否", "一般"],
        ["中年", "否", "否", "好"],
        ["中年", "是", "是", "好"],
        ["中年", "否", "是", "非常好"],
        ["中年", "否", "是", "非常好"],
        ["老年", "否", "是", "非常好"],
        ["老年", "否", "是", "好"],
        ["老年", "是", "否", "好"],
        ["老年", "是", "否", "非常好"],
        ["老年", "否", "否", "一般"]
    ])
    y_train = pd.DataFrame(["否", "否", "是", "是", "否", "否", "否", "是", "是", "是", "是", "是", "是", "是", "否"])
    y_type = [str(k) for k in np.unique(y_train)]
    # one-hot编码
    le_x = LabelEncoder()
    le_x.fit(np.unique(x_train))
    x_train = x_train.apply(le_x.transform)

    le_y = LabelEncoder()
    le_y.fit(y_train)
    y_train = le_y.transform(y_train)
    return x_train, y_train,features,le_x,le_y


# 决策树可视化
def show(clf,feature,y_type):
    dot_data = tree.export_graphviz(clf,out_file=None,
                                    feature_names=feature,
                                    class_names=y_type,filled=True,
                                    rounded=True,special_characters=True)
    # 生成pdf
    graph = pydotplus.graph_from_dot_data(dot_data)
    # 写入pdf
    graph.write_pdf('iris.pdf')


if __name__ == '__main__':
    mpl.rcParams["font.sans-serif"] = [u'simHei']
    mpl.rcParams['axes.unicode_minus'] = False
    # 加载数据
    x_train, y_train,features,le_x,le_y = loaddata()
    # 分类
    clf = DecisionTreeClassifier()
    clf.fit(x_train, y_train)
    y_type = [str(k) for k in np.unique(y_train)]
    # 可视化
    show(clf, features,y_type)

    # 预测
    X_show = pd.DataFrame([["青年", "否", "否", "一般"]])
    X_test = X_show.apply(le_x.transform)
    y_predict = clf.predict(X_test)
    # 结果输出
    X_show = [{features[i] :X_show.values[0][i]} for i in range(len(features))]
    print("{0}被分类为{1}".format(X_show,le_y.inverse_transform(y_predict)))
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

import pydotplus
import graphviz
import numpy as np
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn import tree
import matplotlib as mpl

# 加载数据
def loaddata():
    features = ["age", "work", "house", "credit"]
    x_train = pd.DataFrame([
        ["青年", "否", "否", "一般"],
        ["青年", "否", "否", "好"],
        ["青年", "是", "否", "好"],
        ["青年", "是", "是", "一般"],
        ["青年", "否", "否", "一般"],
        ["中年", "否", "否", "一般"],
        ["中年", "否", "否", "好"],
        ["中年", "是", "是", "好"],
        ["中年", "否", "是", "非常好"],
        ["中年", "否", "是", "非常好"],
        ["老年", "否", "是", "非常好"],
        ["老年", "否", "是", "好"],
        ["老年", "是", "否", "好"],
        ["老年", "是", "否", "非常好"],
        ["老年", "否", "否", "一般"]
    ])
    y_train = pd.DataFrame(["否", "否", "是", "是", "否", "否", "否", "是", "是", "是", "是", "是", "是", "是", "否"])
    y_type = [str(k) for k in np.unique(y_train)]
    # one-hot编码
    le_x = LabelEncoder()
    le_x.fit(np.unique(x_train))
    x_train = x_train.apply(le_x.transform)

    le_y = LabelEncoder()
    le_y.fit(y_train)
    y_train = le_y.transform(y_train)
    return x_train, y_train,features,le_x,le_y


# 决策树可视化
def show(clf,feature,y_type):
    dot_data = tree.export_graphviz(clf,out_file='tree.dot',
                                    feature_names=feature,
                                    class_names=y_type,filled=True,
                                    rounded=True,special_characters=True)

    # 生成pdf
    with open('tree.dot') as f:
        dot_grapth = f.read()
    dot = graphviz.Source(dot_grapth)
    dot.view()






if __name__ == '__main__':
    mpl.rcParams["font.sans-serif"] = [u'simHei']
    mpl.rcParams['axes.unicode_minus'] = False
    # 加载数据
    x_train, y_train,features,le_x,le_y = loaddata()
    # 分类
    clf = DecisionTreeClassifier()
    clf.fit(x_train, y_train)
    y_type = [str(k) for k in np.unique(y_train)]
    # 可视化
    show(clf, features,y_type)

    # 预测
    X_show = pd.DataFrame([["青年", "否", "否", "一般"]])
    X_test = X_show.apply(le_x.transform)
    y_predict = clf.predict(X_test)
    # 结果输出
    X_show = [{features[i] :X_show.values[0][i]} for i in range(len(features))]
    print("{0}被分类为{1}".format(X_show,le_y.inverse_transform(y_predict)))
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

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/一键难忘520/article/detail/750390