task3-特征工程

导入需要用的函数库

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import datetime
from tqdm import tqdm
from sklearn.preprocessing import LabelEncoder
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
from sklearn.preprocessing import MinMaxScaler
import xgboost as xgb
import lightgbm as lgb
from catboost import CatBoostRegressor
import warnings
from sklearn.model_selection import StratifiedKFold, KFold
from sklearn.metrics import accuracy_score, f1_score, roc_auc_score, log_loss
warnings.filterwarnings('ignore')

导入数据

data_train =pd.read_csv('train.csv')
data_test_a = pd.read_csv('testA.csv')

#查找出数据中的对象特征和数值特征
numerical_fea = list(data_train.select_dtypes(exclude=['object']).columns)
category_fea = list(filter(lambda x: x not in numerical_fea,list(data_train.columns)))
label = 'isDefault'
numerical_fea.remove(label)

#查看缺失值情况
data_train.isnull().sum()

id                        0
loanAmnt                  0
term                      0
interestRate              0
installment               0
grade                     0
subGrade                  0
employmentTitle           1
employmentLength      46799
homeOwnership             0
annualIncome              0
verificationStatus        0
issueDate                 0
isDefault                 0
purpose                   0
postCode                  1
regionCode                0
dti                     239
delinquency_2years        0
ficoRangeLow              0
ficoRangeHigh             0
openAcc                   0
pubRec                    0
pubRecBankruptcies      405
revolBal                  0
revolUtil               531
totalAcc                  0
initialListStatus         0
applicationType           0
earliesCreditLine         0
title                     1
policyCode                0
n0                    40270
n1                    40270
n2                    40270
n3                    40270
n4                    33239
n5                    40270
n6                    40270
n7                    40270
n8                    40271
n9                    40270
n10                   33239
n11                   69752
n12                   40270
n13                   40270
n14                   40270
dtype: int64

#按照平均数填充数值型特征
data_train[numerical_fea] = data_train[numerical_fea].fillna(data_train[numerical_fea].median())
data_test_a[numerical_fea] = data_test_a[numerical_fea].fillna(data_train[numerical_fea].median())
#按照众数填充类别型特征
data_train[category_fea] = data_train[category_fea].fillna(data_train[category_fea].mode())
data_test_a[category_fea] = data_test_a[category_fea].fillna(data_train[category_fea].mode())

data_train.isnull().sum()

id                        0
loanAmnt                  0
term                      0
interestRate              0
installment               0
grade                     0
subGrade                  0
employmentTitle           0
employmentLength      46799
homeOwnership             0
annualIncome              0
verificationStatus        0
issueDate                 0
isDefault                 0
purpose                   0
postCode                  0
regionCode                0
dti                       0
delinquency_2years        0
ficoRangeLow              0
ficoRangeHigh             0
openAcc                   0
pubRec                    0
pubRecBankruptcies        0
revolBal                  0
revolUtil                 0
totalAcc                  0
initialListStatus         0
applicationType           0
earliesCreditLine         0
title                     0
policyCode                0
n0                        0
n1                        0
n2                        0
n3                        0
n4                        0
n5                        0
n6                        0
n7                        0
n8                        0
n9                        0
n10                       0
n11                       0
n12                       0
n13                       0
n14                       0
dtype: int64

category_fea

['grade', 'subGrade', 'employmentLength', 'issueDate', 'earliesCreditLine']

#转化成时间格式
for data in [data_train, data_test_a]:
    data['issueDate'] = pd.to_datetime(data['issueDate'],format='%Y-%m-%d')
    startdate = datetime.datetime.strptime('2007-06-01', '%Y-%m-%d')
    #构造时间特征
    data['issueDateDT'] = data['issueDate'].apply(lambda x: x-startdate).dt.days

data_train['employmentLength'].value_counts(dropna=False).sort_index()

1 year        52489
10+ years    262753
2 years       72358
3 years       64152
4 years       47985
5 years       50102
6 years       37254
7 years       35407
8 years       36192
9 years       30272
< 1 year      64237
NaN           46799
Name: employmentLength, dtype: int64

其他分类特征同理