DecisionTree_HDFS.py 文件源码

def makePrediction(para,rawData,totalNumRows,labels):
    traingSetSize=int(math.floor(totalNumRows*para['trainingSetPercent']))
    print('%d instances are selected as training dataset!'%traingSetSize)
    trainX=np.array(rawData[0:traingSetSize])
    trainY=np.array(labels[0:traingSetSize])
    clf=tree.DecisionTreeClassifier()
    clf=clf.fit(trainX,trainY)

    feaNames=['event'+str(i) for i in range(1,386)]
    classNames=trainY
    # generate the decision tree figure
    # dot_data = StringIO()  #class_names=classNames,
    # tree.export_graphviz(clf, out_file=dot_data, feature_names=feaNames,
    #                      filled=True, rounded=True,
    #                      special_characters=True)
    # graph = pydot.graph_from_dot_data(dot_data.getvalue())
    # graph.write_png('sample_SOSP.png')

    testingX=rawData[traingSetSize:]
    testingY=labels[traingSetSize:]
    prediction=list(clf.predict(testingX))
    if len(prediction)!=len(testingY):
        print ('prediction and testingY have different length and SOMEWHERE WRONG!')
    sameLabelNum=0
    sameFailureNum=0
    for i in range(len(testingY)):
        if prediction[i]==testingY[i]:
            sameLabelNum+=1
            if prediction[i]==1:
                sameFailureNum+=1

    accuracy=float(sameLabelNum)/len(testingY)
    print ('accuracy is %.5f:'%accuracy)

    predictSuccess=0
    predictFailure=0
    for item in prediction:
        if item==0:
            predictSuccess+=1
        elif item==1:
            predictFailure+=1

    testSuccess=0
    testFailure=0
    for tt in testingY:
        if tt==0:
            testSuccess+=1
        elif tt==1:
            testFailure+=1

    print(predictSuccess,predictFailure,testSuccess,testFailure,sameFailureNum)
    if sameFailureNum==0:
        print ('precision is 0 and recall is 0')
    else:
        precision=float(sameFailureNum)/(predictFailure)
        print('precision is %.5f'%precision)
        recall=float(sameFailureNum)/(testFailure)
        print('recall is %.5f'%recall)
        F_measure=2*precision*recall/(precision+recall)
        print('F_measure is %.5f'%F_measure)
    return predictFailure,testFailure,sameFailureNum,precision,recall,F_measure