《Python数据分析与应用》 第六章 构建并评价分类模型(中)

1.加载所需的函数、数据

import numpy as np
from sklearn.datasets import load_breast_cancer
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
cancer = load_breast_cancer()
cancer_data = cancer['data']
cancer_target = cancer['target']
cancer_names = cancer['feature_names']

2.将数据划分为训练集测试集

cancer_data_train,cancer_data_test, \
cancer_target_train,cancer_target_test = \
train_test_split(cancer_data,cancer_target,test_size = 0.2,random_state = 22)

3.数据标准化

stdScaler = StandardScaler().fit(cancer_data_train)
cancer_trainStd = stdScaler.transform(cancer_data_train)
cancer_testStd = stdScaler.transform(cancer_data_test)

4.建立SVM模型

svm = SVC().fit(cancer_trainStd,cancer_target_train)## train  target
print('建立的SVM模型为：\n',svm)

5.预测训练集结果

cancer_target_pred = svm.predict(cancer_testStd)
print('预测前20个结果为：\n',cancer_target_pred[:20])

6.求出预测和真实一样的数目

true = np.sum(cancer_target_pred == cancer_target_test )
print('预测对的结果数目为：', true)
print('预测错的的结果数目为：', cancer_target_test.shape[0]-true)
print('预测结果准确率为：', true/cancer_target_test.shape[0])

7.分类模型评价方法

7.1建立的支持向量机模型的Precision、Recall、F1、Cohen’s Kappa系数的评价指数如下代码所示：

# 代码 6-19
from sklearn.metrics import accuracy_score,precision_score, \
recall_score,f1_score,cohen_kappa_score
print('使用SVM预测breast_cancer数据的准确率为：',
      accuracy_score(cancer_target_test,cancer_target_pred))
print('使用SVM预测breast_cancer数据的精确率为：',
      precision_score(cancer_target_test,cancer_target_pred))
print('使用SVM预测breast_cancer数据的召回率为：',
      recall_score(cancer_target_test,cancer_target_pred))
print('使用SVM预测breast_cancer数据的F1值为：',
      f1_score(cancer_target_test,cancer_target_pred))
print('使用SVM预测breast_cancer数据的Cohen’s Kappa系数为：',
      cohen_kappa_score(cancer_target_test,cancer_target_pred))

7.2 sklearn的metrics模块除了提供Precision等单一评价指标的函数外，还能够输出分类模型评价报告的classification_report函数

from sklearn.metrics import classification_report
print('使用SVM预测iris数据的分类报告为：','\n',
      classification_report(cancer_target_test,
            cancer_target_pred))

7.3绘制ROC曲线

from sklearn.metrics import roc_curve
import matplotlib.pyplot as plt
## 求出ROC曲线的x轴和y轴
fpr, tpr, thresholds = roc_curve(cancer_target_test,cancer_target_pred)
#fps和tps就是混淆矩阵中的FP和TP的值；thresholds就是 cancer_target_pred 逆序排列后的结果
# （由于保留的小数位数不同，所以表面上看上去不一样，其实是一样的）
print(fpr,'\n',tpr,'\n',thresholds)
plt.figure(figsize=(10,6))
plt.xlim(0,1) ##设定x轴的范围
plt.ylim(0.0,1.1) ## 设定y轴的范围
plt.xlabel('False Postive Rate')
plt.ylabel('True Postive Rate')
plt.plot(fpr,tpr,linewidth=2, linestyle="-",color='red')
plt.show()