ML之分類(lèi)預(yù)測(cè)之ElasticNet：利用ElasticNet回歸對(duì)二分類(lèi)數(shù)據(jù)集構(gòu)建二分類(lèi)器(DIY交叉驗(yàn)證+分類(lèi)的兩種度量PK)

?

?

目錄

輸出結(jié)果

設(shè)計(jì)思路

核心代碼

---

?

?

輸出結(jié)果

?

設(shè)計(jì)思路

?

核心代碼

#(4)交叉驗(yàn)證 for ixval in range(nxval):idxTest = [a for a in range(nrow) if a%nxval == ixval%nxval]idxTrain = [a for a in range(nrow) if a%nxval != ixval%nxval]xTrain = numpy.array([xNormalized[r] for r in idxTrain])xTest = numpy.array([xNormalized[r] for r in idxTest])labelTrain = numpy.array([labelNormalized[r] for r in idxTrain])labelTest = numpy.array([labelNormalized[r] for r in idxTest])alphas, coefs, _ = enet_path(xTrain, labelTrain,l1_ratio=0.8, fit_intercept=False, return_models=False)if ixval == 0:pred = numpy.dot(xTest, coefs)yOut = labelTestelse:#accumulate predictions累積預(yù)測(cè)yTemp = numpy.array(yOut)yOut = numpy.concatenate((yTemp, labelTest), axis=0)#accumulate predictionspredTemp = numpy.array(pred)pred = numpy.concatenate((predTemp, numpy.dot(xTest, coefs)), axis = 0)#三處采樣P = len(idxPos) #P = Positive cases N = nrow - P #N = Negative cases#第52處采樣 TP = tpr[52] * P #TP = True positives = tpr * P FN = P - TP #FN = False negatives = P - TP FP = fpr[52] * N #FP = False positives = fpr * N TN = N - FP #TN = True negatives = N - FP print('52：Threshold Value = ', thresh[52]) print('TP = ', TP, 'FP = ', FP) print('FN = ', FN, 'TN = ', TN)#第104處采樣 TP = tpr[104] * P FN = P - TP FP = fpr[104] * N TN = N - FP print('104：Threshold Value = ', thresh[104]) print('TP = ', TP, 'FP = ', FP) print('FN = ', FN, 'TN = ', TN)#第156處采樣 TP = tpr[156] * P FN = P - TP FP = fpr[156] * N TN = N - FP print('156：Threshold Value = ', thresh[156]) print('TP = ', TP, 'FP = ', FP) print('FN = ', FN, 'TN = ', TN)

?

?

?

?

?

總結(jié)

以上是生活随笔為你收集整理的ML之分类预测之ElasticNet：利用ElasticNet回归对二分类数据集构建二分类器(DIY交叉验证+分类的两种度量PK)的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。