python机器学习sklearn挖掘乳腺癌细胞（五）

# -*- coding: utf-8 -*-
"""
Created on Thu Apr 12 22:31:31 2018&＃64;author: 231469242&＃64;qq.com
"""
import numpy as np
from sklearn import metrics
from sklearn.metrics import roc_curve, auc,roc_auc_score ###计算roc和aucimport pandas as pd
from sklearn.datasets import load_breast_cancer
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import mglearn
import matplotlib.pyplot as pltcancer&＃61;load_breast_cancer()#mglearn.plots.plot_knn_classification(n_neighbors&＃61;3)
X_train,x_test,y_train,y_test&＃61;train_test_split(cancer.data,cancer.target,stratify&＃61;cancer.target,random_state&＃61;42)knn&＃61;KNeighborsClassifier()
knn.fit(X_train,y_train)
print("accuracy on the training subset:{:.3f}".format(knn.score(X_train,y_train)))
print("accuracy on the test subset:{:.3f}".format(knn.score(x_test,y_test)))#Auc验证&＃xff0c;数据采用测试集数据
#癌症的概率
proba_cancer&＃61;knn.predict_proba(x_test)
y_scores&＃61;pd.DataFrame(proba_cancer)[1]
y_scores&＃61;np.array(y_scores)
y_true&＃61;y_test
#auc分数
#auc分数有两种计算方式&＃xff0c;第一种是根据目标变量y_true,预测分数/预测概率y_socres,通过roc_auc_score(y_true, y_scores)计算AUC
AUC&＃61;roc_auc_score(y_true, y_scores)
print("AUC:",AUC)
#auc第二种方法是通过fpr,tpr&＃xff0c;通过auc(fpr,tpr)来计算AUC
fpr, tpr, thresholds &＃61; metrics.roc_curve(y_true, y_scores, pos_label&＃61;1)
AUC1 &＃61; auc(fpr,tpr) ###计算auc的值 #print("fpr:",fpr)
#print("tpr:",tpr)
#print("thresholds:",thresholds)
print("AUC1:",AUC1)if AUC >&＃61;0.7:print("good classifier")
if 0.7>AUC>0.6:print("not very good classifier")
if 0.6>&＃61;AUC>0.5:print("useless classifier")
if 0.5>&＃61;AUC:print("bad classifier,with sorting problems")#绘制ROC曲线
#画对角线
plt.plot([0, 1], [0, 1], &＃39;--&＃39;, color&＃61;(0.6, 0.6, 0.6), label&＃61;&＃39;Diagonal line&＃39;)
plt.plot(fpr,tpr,label&＃61;&＃39;ROC curve (area &＃61; %0.2f)&＃39; % AUC)
plt.title(&＃39;ROC curve&＃39;)
plt.legend(loc&＃61;"lower right")