python 随机分类

#encoding:utf-8import pandas as pdimport numpy as npfrom sklearn import datasets,linear_modelfrom sklearn.metrics import roc_curve,aucimport pylab as plfrom matplotlib.pyplot import plot

def confusionMatrix(predicted,actual,threshold):    if len(predicted)!=len(actual):return -1    tp = 0.0    fp = 0.0    tn = 0.0    fn = 0.0    for i in range(len(actual)):        if actual[i]>0.5:            if predicted[i]>threshold:                tp += 1.0            else:                fn += 1.0        else:            if predicted[i]<threshold:                tn += 1.0            else:                fp += 1.0    rtn = [fp,fn,fp,tn]    return rtn#获取数据rockdata = open(‘sonar.all-data‘)xList = []labels = []#将标签转换成数值,M转换成1.0,R转换为0.0for line in rockdata:    row = line.strip().split(",")    if(row[-1] ==‘M‘):        labels.append(1.0)    else:        labels.append(0.0)    row.pop()    floatRow = [float(num) for num in row]    xList.append(floatRow)print labels#获取数据的行数,通过对3的求余,将数据划分为2个子集,1/3的测试集,2/3的训练集indices = range(len(xList))xListTest = [xList[i] for i in indices if i%3==0]xListTrain = [xList[i] for i in indices if i%3!=0]labelsTest = [labels[i] for i in indices if i%3==0]labelsTrain = [labels[i] for i in indices if i%3!=0]#将列表转换成数组xTrain = np.array(xListTrain)yTrain = np.array(labelsTrain)xTest = np.array(xListTest)yTest = np.array(labelsTest)#预测模型rocksVMinesModel = linear_model.LinearRegression()#训练数据rocksVMinesModel.fit(xTrain,yTrain)# 预测训练数据trainingPredictions = rocksVMinesModel.predict(xTrain)print ("---------",trainingPredictions[0:5],trainingPredictions[-6:-1])#生成训练数据的混淆矩阵confusionMatTrain = confusionMatrix(trainingPredictions,yTrain,0.5)print confusionMatTrain#预测测试数据testPredictions = rocksVMinesModel.predict(xTest)#生成测试数据的混淆矩阵confusionTest = confusionMatrix(testPredictions,yTest,0.5)print confusionTest#通过roc_curve函数计算fpt,tpr,并计算roc_auc,AUC越高代表越好fpr,tpr,thresholds = roc_curve(yTrain,trainingPredictions)roc_auc = auc(fpr,tpr)print roc_auc#生成训练集上的ROC曲线#plot roc curvepl.clf()#清楚图形,初始化图形的时候需要pl.plot(fpr,tpr,label=‘ROC curve (area=%0.2f)‘ %roc_auc)#画ROC曲线pl.plot([0,1],[0,1],‘k-‘)#生成对角线pl.xlim([0.0,1.0])#X轴范围pl.ylim([0.0,1.0])#Y轴范围pl.xlabel(‘False Positive Rate‘)#X轴标签显示pl.ylabel(‘True Positive Rate‘)#Y轴标签显示pl.title(‘In sample ROC rocks versus mines‘)#标题pl.legend(loc="lower left")#图例位置pl.show()

#生成测试集上的ROC曲线fpr,tpr,thresholds = roc_curve(yTest,testPredictions)roc_auc = auc(fpr,tpr)print roc_auc#plot roc curvepl.clf()pl.plot(fpr,tpr,label=‘ROC curve (area=%0.2f)‘ %roc_auc)pl.plot([0,1],[0,1],‘k-‘)pl.xlim([0.0,1.0])pl.ylim([0.0,1.0])pl.xlabel(‘False Positive Rate‘)pl.ylabel(‘True Positive Rate‘)pl.title(‘In sample ROC rocks versus mines‘)pl.legend(loc="lower right")pl.show()

训练集上的ROC曲线

测试集上的ROC曲线