汽车购买分类

原数据

根据 ‘buy’, ‘maintain’, ‘doors’, ‘persons’, ‘boot’, ‘safety’, ‘accept’

购买”、“维护”、“门”、“人”、“系统”、“安全” 来判断顾客是否接受买车

# -*- coding:utf-8 -*-

import pandas as pd
import numpy as np
from sklearn.linear_model import LogisticRegressionCV
from sklearn import metrics
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
import matplotlib as mpl
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier

if __name__ == '__main__': pd.set_option('display.width', 300) pd.set_option('display.max_columns', 300) data = pd.read_csv('car.data', header=None) n_columns = len(data.columns) columns = ['buy', 'maintain', 'doors', 'persons', 'boot', 'safety', 'accept'] new_columns = dict(list(zip(np.arange(n_columns), columns))) data.rename(columns=new_columns, inplace=True) print(data.head(10)) # one-hot编码 x = pd.DataFrame() for col in columns[:-1]: t = pd.get_dummies(data[col]) t = t.rename(columns=lambda x: col+'_'+str(x)) x = pd.concat((x, t), axis=1) print(x.head(10)) print(x.shape) y = np.array(pd.Categorical(data['accept']).codes) x, x_test, y, y_test = train_test_split(x, y, test_size=0.3) clf = LogisticRegressionCV(Cs=np.logspace(-3, 4, 8), cv=5) # clf = RandomForestClassifier(n_estimators=50, max_depth=7) clf.fit(x, y) y_hat = clf.predict(x) print('训练集精确度：', metrics.accuracy_score(y, y_hat)) y_test_hat = clf.predict(x_test) print('测试集精确度：', metrics.accuracy_score(y_test, y_test_hat)) n_class = len(np.unique(y)) if n_class > 2: y_test_one_hot = label_binarize(y_test, classes=np.arange(n_class)) y_test_one_hot_hat = clf.predict_proba(x_test) fpr, tpr, _ = metrics.roc_curve(y_test_one_hot.ravel(), y_test_one_hot_hat.ravel()) print('Micro AUC:\t', metrics.auc(fpr, tpr)) auc = metrics.roc_auc_score(y_test_one_hot, y_test_one_hot_hat, average='micro') print('Micro AUC(System):\t', auc) auc = metrics.roc_auc_score(y_test_one_hot, y_test_one_hot_hat, average='macro') print('Macro AUC:\t', auc) else: fpr, tpr, _ = metrics.roc_curve(y_test.ravel(), y_test_hat.ravel()) print('AUC:\t', metrics.auc(fpr, tpr)) auc = metrics.roc_auc_score(y_test, y_test_hat) print('AUC(System):\t', auc) mpl.rcParams['font.sans-serif'] = 'SimHei' mpl.rcParams['axes.unicode_minus'] = False plt.figure(figsize=(8, 7), facecolor='w') plt.plot(fpr, tpr, 'r-', lw=2, label='AUC=%.4f' % auc) plt.legend(loc='lower right', fontsize=14) plt.xlim((-0.01, 1.02)) plt.ylim((-0.01, 1.02)) plt.xticks(np.arange(0, 1.1, 0.1)) plt.yticks(np.arange(0, 1.1, 0.1)) plt.xlabel('False Positive Rate', fontsize=14) plt.ylabel('True Positive Rate', fontsize=14) plt.grid(b=True, ls=':') plt.title('ROC曲线和AUC', fontsize=16) plt.show()


  

 

  
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
 

y

独热编码：x的数据

   buy_high  buy_low  buy_med  buy_vhigh  maintain_high  maintain_low  maintain_med  maintain_vhigh  doors_2  doors_3  doors_4  doors_5more  persons_2  persons_4  persons_more  boot_big  boot_med  boot_small  safety_high  safety_low  safety_med
0 0 0 0 1 0 0 0 1 1 0 0 0 1 0 0 0 0 1 0 1 0
1 0 0 0 1 0 0 0 1 1 0 0 0 1 0 0 0 0 1 0 0 1
2 0 0 0 1 0 0 0 1 1 0 0 0 1 0 0 0 0 1 1 0 0
3 0 0 0 1 0 0 0 1 1 0 0 0 1 0 0 0 1 0 0 1 0
4 0 0 0 1 0 0 0 1 1 0 0 0 1 0 0 0 1 0 0 0 1
5 0 0 0 1 0 0 0 1 1 0 0 0 1 0 0 0 1 0 1 0 0
6 0 0 0 1 0 0 0 1 1 0 0 0 1 0 0 1 0 0 0 1 0
7 0 0 0 1 0 0 0 1 1 0 0 0 1 0 0 1 0 0 0 0 1
8 0 0 0 1 0 0 0 1 1 0 0 0 1 0 0 1 0 0 1 0 0
9 0 0 0 1 0 0 0 1 1 0 0 0 0 1 0 0 0 1 0 1 0


  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
 

LogisticRegressionCV

训练集精确度： 0.9081885856079405
测试集精确度： 0.8921001926782274
Micro AUC: 0.9834757073221438
Micro AUC(System): 0.9834757073221438
Macro AUC: 0.9668852150116471

RandomForestClassifier

训练集精确度： 0.9545078577336642
测试集精确度： 0.9075144508670521
Micro AUC: 0.9924203330598466
Micro AUC(System): 0.9924203330598466
Macro AUC: 0.988179483976249

文章来源: maoli.blog.csdn.net，作者：刘润森！，版权归原作者所有，如需转载，请联系作者。

原文链接：maoli.blog.csdn.net/article/details/89532213