二分类模型评估指标

Posted 2020-11-12 yspxizhen

分类结果混淆矩阵（confusion matrix）：

真实\\预测	正例	反例
正例	TP	FN
反例	FP	TN

1.准确率--accuracy

定义：对于给定的测试数据集，分类器正确分类的样本数与总样本数之比。
计算方法：

2.精确率--precision（P）
定义：被判定为正例（反例）的样本中，真正的正例样本（反例样本）的比例。
计算方法：

3.召回率--recall（R）
定义：被正确分类的正例（反例）样本，占所有正例（反例）样本的比例。
计算方法：

4.F1_score
定义：基于精确率和召回率的调和平均。
计算方法：

5.macro 度量
定义：对于n个二分类混淆矩阵，在各混淆矩阵上分别计算精确率和召回率，记（P1,R1），（P2,R2）...（Pn，Rn），再计算平均值，得到宏精确率（macro-P）、宏召回率（macro-R），继而得到宏F1（macro-F1）。

6.micro度量
定义：对于n个二分类混淆矩阵，先对TP、FN、FP、TN求平均值，再用均值计算得到微精确率（micro-P）、微召回率（micro-P），继而得到微F1（micro-F1）。

# -*-coding: utf-8 -*-
import numpy
 
#true = [真实组1，真实组2...真实组N]，predict = [预测组1，预测组2...预测组N]
def evaluation(true,predict):
 
    num = len(true)#确定有几组
    (TP, FP, FN, TN) = ([0] * num for i in range(4))#赋初值
 
    for m in range(0,len(true)):
        if(len(true[m]) != len(predict[m])):#样本数都不等，显然是有错误的
            print "真实结果与预测结果样本数不一致。"
        else:
            for i in range(0,len(true[m])):#对每一组数据分别计数
                if   (predict[m][i] == 1) and ((true[m][i] == 1)):    TP[m] += 1.0
                elif (predict[m][i] == 1) and ((true[m][i] == 0)):    FP[m] += 1.0
                elif (predict[m][i] == 0) and ((true[m][i] == 1)):    FN[m] += 1.0
                elif (predict[m][i] == 0) and ((true[m][i] == 0)):    TN[m] += 1.0
 
 
    # macro度量，先求每一组的评价指标，再求均值
    (accuracy_macro,      precision1_macro, precision0_macro,      recall1_macro, recall0_macro,      F1_score1_macro,F1_score0_macro) =      ([0] * num for i in range(7))
 
    for m in range(0,num):
 
        accuracy_macro[m]    = (TP[m] + TN[m]) / (TP[m] + FP[m] + FN[m] +TN[m])
 
        if (TP[m] + FP[m] == 0) : precision1_macro[m] = 0#预防一些分母为0的情况
        else :precision1_macro[m] = TP[m] / (TP[m] + FP[m])
 
        if (TN[m] + FN[m] == 0) : precision0_macro[m] = 0
        else :precision0_macro[m] = TN[m] / (TN[m] + FN[m])
 
        if (TP[m] + FN[m] == 0) : recall1_macro[m] = 0
        else :recall1_macro[m]    = TP[m] / (TP[m] + FN[m])
 
        if (TN[m] + FP[m] == 0) : recall0_macro[m] = 0
        recall0_macro[m]    = TN[m] / (TN[m] + FP[m])
 
    macro_accuracy    = numpy.mean(accuracy_macro)
    macro_precision1  = numpy.mean(precision1_macro)
    macro_precision0  = numpy.mean(precision0_macro)
    macro_recall1     = numpy.mean(recall1_macro)
    macro_recall0     = numpy.mean(recall0_macro)
 
    #F1_score还是按这个公式来算，用macro-P和macro-R
    if (macro_precision1 + macro_recall1 == 0): macro_F1_score1 = 0
    else: macro_F1_score1   = 2 * macro_precision1 * macro_recall1 / (macro_precision1 + macro_recall1)
 
    if (macro_precision0 + macro_recall0 == 0): macro_F1_score0 = 0
    else: macro_F1_score0   = 2 * macro_precision0 * macro_recall0 / (macro_precision0 + macro_recall0)
 
    #micro度量，是用TP、TN、FP、FN的均值来计算评价指标
    TPM = numpy.mean(TP)
    TNM = numpy.mean(TN)
    FPM = numpy.mean(FP)
    FNM = numpy.mean(FN)
 
    micro_accuracy    = (TPM + TNM) / (TPM + FPM + FNM + TNM)
 
    if(TPM + FPM ==0): micro_precision1  = 0#预防一些分母为0的情况
    else: micro_precision1  = TPM / (TPM + FPM)
 
    if(TNM + FNM ==0): micro_precision0  = 0
    else: micro_precision0  = TNM / (TNM + FNM)
 
    if (TPM + FNM == 0):micro_recall1 = 0
    else: micro_recall1     = TPM / (TPM + FNM)
 
    if (TNM + FPM == 0):micro_recall0 = 0
    else: micro_recall0     = TNM / (TNM + FPM)
 
    # F1_score仍然按这个公式来算，用micro-P和micro-R
    if (micro_precision1 + micro_recall1 == 0): micro_F1_score1 = 0
    else :micro_F1_score1   = 2 * micro_precision1 * micro_recall1 / (micro_precision1 + micro_recall1)
 
    if (micro_precision0 + micro_recall0 == 0): micro_F1_score0 = 0
    else :micro_F1_score0   = 2 * micro_precision0 * micro_recall0 / (micro_precision0 + micro_recall0)
 
    print "*****************************macro*****************************"
    print "accuracy",":%.3f" % macro_accuracy
    print "%20s"%‘precision‘,"%12s"%‘recall‘,"%12s"%‘F1_score‘
    print "%5s" % "0", "%14.3f" % macro_precision0, "%12.3f" % macro_recall0, "%12.3f" %macro_F1_score0
    print "%5s" % "1", "%14.3f" % macro_precision1, "%12.3f" % macro_recall1, "%12.3f" %macro_F1_score1
    print "%5s" % "avg","%14.3f" % ((macro_precision0+macro_precision1)/2),           "%12.3f" % ((macro_recall0+macro_recall1)/2), "%12.3f" %((macro_F1_score1+macro_F1_score0)/2)
    print "*****************************micro*****************************"
    print "accuracy",":%.3f" % micro_accuracy
    print "%20s"%‘precision‘,"%12s"%‘recall‘,"%12s"%‘F1_score‘
    print "%5s" % "0", "%14.3f" % micro_precision0, "%12.3f" % micro_recall0, "%12.3f" %micro_F1_score0
    print "%5s" % "1", "%14.3f" % micro_precision1, "%12.3f" % micro_recall1, "%12.3f" %micro_F1_score1
    print "%5s" % "avg", "%14.3f" % ((micro_precision0 + micro_precision1) / 2),         "%12.3f" % ((micro_recall0 + micro_recall1) / 2), "%12.3f" % ((micro_F1_score0 + micro_F1_score1) / 2)
 
if __name__ == "__main__":
    #简单举例 - 当未采用交叉验证方法时，显然True和Predict都只有一组，Macro和Micro会输出一样的值
    true = [[0, 1, 0, 1, 0], [0, 1, 1, 0]]
    predict = [[0, 1, 1, 1, 0], [0, 1, 0, 1]]
    evaluation(true,predict)

*****************************macro*****************************
accuracy :0.650
           precision       recall     F1_score
    0          0.750        0.583        0.656
    1          0.583        0.750        0.656
  avg        0.667        0.667        0.656
*****************************micro*****************************
accuracy :0.667
           precision       recall     F1_score
    0          0.750        0.600        0.667
    1          0.600        0.750        0.667
  avg        0.675        0.675        0.667