Datawhale17期-task3

原始链接

数据特征工程

1. 学习特征预处理、缺失值、异常值处理、数据分桶等特征处理方法
2. 学习特征交互、编码、选择的相应方法

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')

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

确实值、异常值、对象类型值处理

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)

缺失值填充

1. 把所有缺失值替换为指定的值0

   data_train = data_train.fillna(0)

2. 向用缺失值上面的值替换缺失值

   data_train = data_train.fillna(axis=0,method=‘ffill’)

3. 纵向用缺失值下面的值替换缺失值,且设置最多只填充两个连续的缺失值

   data_train = data_train.fillna(axis=0,method=‘bfill’,limit=2)

#缺失值查看
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
n2.1                  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

#用平均值填充数值型
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_test_a[numerical_fea].median())

#用众数填充类别型数据
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_test_a[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
initialListStat