数据挖掘 - python中逻辑回归中的AUC和分类报告 - 吾爱随笔录

我一直在尝试在 python 中实现逻辑回归。基本上代码可以工作，它给出了 91% 的预测模型的准确性，但由于某种原因，AUC 得分为 0.5，这基本上是最差的得分，因为这意味着模型是完全随机的。分类报告还返回错误：“UndefinedMetricWarning: Precision 和 F-score 定义不明确，在没有预测样本的标签中设置为 0.0。'precision'、'predicted'、average、warn_for)”。有谁知道我应该改变什么才能正常工作？

 import numpy as np
 import pandas as pd
 from sklearn.cross_validation import train_test_split
 from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import accuracy_score  
 from sklearn.preprocessing import StandardScaler
 from sklearn.metrics import roc_auc_score
 from sklearn.metrics import classification_report

 data_file = pd.read_csv('loan.csv', delimiter=',')

 # variable preprocessing

 data_file['loan_status'] = np.where(data_file['loan_status'].isin(['Fully 
 Paid', 'Current']), 1, 0)
 loan_stat=data_file['loan_status']
 loan_stat=loan_stat.astype(np.float64)

 m = {
    'n/a': 0,     
    '< 1 year': 0,
    '1 year': 1,
    '2 years': 2,
    '3 years': 3,
    '4 years': 4,
    '5 years': 5,
    '6 years': 6,
    '7 years': 7,
    '8 years': 8,
    '9 years': 9,
    '10+ years': 10
 }
 emp_length=data_file.emp_length.map(m)
 emp_length.astype(np.float64)

 annual_inc=data_file['annual_inc']
 delinq_2yrs=data_file['delinq_2yrs']
 dti=data_file['dti']
 loan_amnt=data_file['loan_amnt']
 installment=data_file['installment']
 int_rate=data_file['int_rate']
 total_acc=data_file['total_acc']
 open_acc=data_file['open_acc']
 pub_rec=data_file['pub_rec']
 acc_now_delinq=data_file['acc_now_delinq']

 #variables combined into one dataframe

 X=pd.DataFrame()

 X['annua_inc']=annual_inc
 X['delinq_2yrs']=delinq_2yrs
 X['dti']=dti
 X['emp_length']=emp_length
 X['loan_amnt']=loan_amnt
 X['installment']=installment
 X['int_rate']=int_rate
 X['total_acc']=total_acc
 X['open_acc']=open_acc
 X['pub_rec']=pub_rec
 X['acc_now_delinq']=acc_now_delinq
 X['loan_stat']=loan_stat

 X=X.dropna(axis=0)
 y=X['loan_stat']
 X=X.drop(['loan_stat'], axis=1)

 scaler=StandardScaler()
 X=scaler.fit_transform(X)

 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, 
 random_state=42)

 model=LogisticRegression(penalty='l2', C=1)
 model.fit(X_train, y_train)
 score=accuracy_score(y_test, model.predict(X_test))
 roc=roc_auc_score(y_test, model.predict(X_test))
 cr=classification_report(y_test, model.predict(X_test))

以下是数据链接：https ://www.kaggle.com/wendykan/lending-club-loan-data/downloads/lending-club-loan-data.zip