机器学习测试笔记（27）——模型评估和优化（下）

# coding=UTF-8
from sklearn import metrics
from sklearn.metrics import  confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.metrics import  precision_score
from sklearn.metrics import recall_score
from sklearn.metrics import f1_score
import matplotlib.pylab as plt
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
from sklearn.metrics import  precision_recall_curve
#真实值
GTlist =   [1,1,0,1,1,0,1,0,0,1]
#模型预测值
Problist = [1,0,1,1,1,1,1,1,0,1]
y_true = np.array(GTlist)
y_pred = np.array(Problist)
#混淆矩阵
confusion_matrix =  confusion_matrix(y_true, y_pred)
print("混淆矩阵:")
print(confusion_matrix)
#准确性
accuracy =  '{:.1%}'.format(accuracy_score(y_true, y_pred))
print("准确性:",end='')
print(accuracy)
#精确性
precision =  '{:.1%}'.format(precision_score(y_true, y_pred))
print("精确性:",end='')
print(precision)
#召回率
recall = '{:.1%}'.format(recall_score(y_true,  y_pred))
print("召回率:",end='')
print(recall)
#F1值
f1score = '{:.1%}'.format(f1_score(y_true,  y_pred))
print("F1值:",end='')
print(f1score)
#初始化画图数据
#真实值
GTlist = [1.0, 1.0, 0.0, 1.0, 0.0, 1.0,  0.0, 1.0, 0.0, 1.0,0.0, 1.0, 0.0, 0.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0]
#模型预测值
Problist = [0.99, 0.98, 0.97, 0.93, 0.85,  0.80, 0.79, 0.75, 0.70, 0.65,0.64, 0.63, 0.55, 0.54, 0.51, 0.49, 0.30, 0.2,  0.1, 0.09]
fpr, tpr, thresholds = metrics.roc_curve(GTlist, Problist,  pos_label=1)
roc_auc = metrics.auc(fpr, tpr)  #auc为Roc曲线下的面积
print("AUC值:",end='')
print('{:.1%}'.format(roc_auc))
#ROC曲线
plt.plot(fpr, tpr, 'b',label='AUC =  %0.2f'% roc_auc)
plt.legend(loc='lower right')
# plt.plot([0, 1], [0, 1], 'r--')
plt.xlim([-0.1, 1.1])
plt.ylim([-0.1, 1.1])
plt.xlabel('False Positive Rate') #横坐标是fpr
plt.ylabel('True Positive Rate')  #纵坐标是tpr
plt.title('Receiver operating  characteristic example')
plt.show()
#P-R曲线
plt.figure("P-R Curve")
plt.title('Precision/Recall Curve')
plt.xlabel('Recall')
plt.ylabel('Precision')
#y_true为样本实际的类别，y_scores为样本为正例的概率
y_true = np.array(GTlist)
y_scores = np.array(Problist)
precision, recall, thresholds =  precision_recall_curve(y_true, y_scores)
plt.plot(recall,precision)
plt.show()

from sklearn.neighbors import KNeighborsClassifier  
def my_score():
       X,y =datasets.load_wine().data,datasets.load_wine().target
       X_train, X_test,y_train, y_test = train_test_split(X, y, random_state=68)
       knn =KNeighborsClassifier()
       knn.fit(X_train,y_train)
       print("训练集得分:\n{:.2%}".format(knn.score(X_train,y_train)))
       print("测试集得分:\n{:.2%}".format(knn.score(X_test,y_test)))
       y_true = y_test
       y_pred =knn.predict(X_test)
#混淆矩阵
       print("混淆矩阵:\n",confusion_matrix(y_true,y_pred))
#准确性
       accuracy ='{:.1%}'.format(accuracy_score(y_true, y_pred))
       print("准确性:",accuracy)
#精确性
       precision ='{:.1%}'.format(precision_score(y_true, y_pred, average='micro'))
       print("精确性:",precision)
#召回率
       recall ='{:.1%}'.format(recall_score(y_true, y_pred, average='micro'))
       print("召回率:",recall)
#F1值
       f1score ='{:.1%}'.format(f1_score(y_true, y_pred, average='micro'))
       print("F1值:",f1score)
       X,y =make_blobs(n_samples=200,centers=2, random_state=1,cluster_std=5)
       X_train, X_test,y_train, y_test = train_test_split(X, y, random_state=68)
       gnb = GaussianNB()
       gnb.fit(X_train,y_train)
       predict_proba =gnb.predict_proba(X_test)
       mylist = [None] *int(predict_proba.shape[0])
       i = 0
for my_predict_proba inpredict_proba:
              sign = int(y[i])
              mylist[i] =my_predict_proba[sign]
        i = i+1
       GTlist = y_test
       Problist = mylist
       fpr, tpr, thresholds =roc_curve(GTlist, Problist, pos_label=1)
       roc_auc =metrics.auc(fpr, tpr)  #auc为Roc曲线下的面积
       print("AUC值:",end='')
       print('{:.1%}'.format(roc_auc))
       plt.rcParams['font.sans-serif']=['SimHei']
       plt.rcParams['axes.unicode_minus']=False
#ROC曲线
       plt.plot(fpr, tpr,'b',label='AUC = %0.2f'% roc_auc)
       plt.legend(loc='lowerright')
# plt.plot([0, 1], [0,1], 'r--')
       plt.xlim([-0.1, 1.1])
       plt.ylim([-0.1, 1.1])
       plt.xlabel(u'假阳性率') #横坐标是fpr
       plt.ylabel(u'真阳性率')  #纵坐标是tpr
plt.title(u'接收器工作特性示例')
       plt.show()
#P-R曲线 
       plt.figure(u"P-R 曲线")
       plt.title(u'精度/召回曲线')
       plt.xlabel(u'召回')
       plt.ylabel(u'精度')
#y_true为样本实际的类别，y_scores为样本为正例的概率
       y_true =np.array(GTlist)
       y_scores =np.array(Problist)
       precision, recall,thresholds = precision_recall_curve(y_true, y_scores)
       plt.plot(recall,precision)
       plt.show()

训练集得分:
76.69%
测试集得分:
80.00%
混淆矩阵:
[[17  0   0]
[ 2  12  3]
[ 3 1   7]]
准确性: 80.0%
精确性: 80.0%
召回率: 80.0%
F1值: 80.0%
AUC值:57.8%