1.把列表转化为series,并且命名,和其他列进行拼接:
new_concat=pd.concat([id,Series(train_predict,name='pre')],axis=1)
2 .把已经打乱顺序的id重新进行排序
id = id.reset_index(drop=True)
3,删除重复的行,其他行保留下来
new_concat=new_concat.drop_duplicates(subset='SUBSCR_ID', keep='first', inplace=False)
4.结果评估,输出混淆矩阵,输出准确率,查全率,精确率,f1值
a = metrics.confusion_matrix(test_predict, y_test)
test_f1 = metrics.f1_score(test_predict, y_test)
test_acc = metrics.accuracy_score(test_predict, y_test)
test_rec = metrics.recall_score(test_predict, y_test)
c=metrics.precision_score(test_predict, y_test)
整体结果:
b=metrics.classification_report(test_predict, y_test)