Task3：特征工程

学习目标：

• 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
• 学习特征交互、、编码、选择的相应方法

# 导入包并读取数据
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('../train.csv')
data_test_a = pd.read_csv('../testA.csv')

特征预处理

#特征预处理
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)

数据缺失问题

#查看缺失值情况
data_train.isnull().sum()

#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()

#查看类别特征
category_fea

时间格式处理

#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()

对象类型特征转换到数值

def employmentLength_to_int(s):
    if pd.isnull(s):
        return s
    else:
        return np.int8(s.split()[0])
for data in [data_train, data_test_a]:
    data['employmentLength'].replace(to_replace='10+ years', value='10 years', inplace=True)
    data['employmentLength'].replace('< 1 year', '0 years', inplace=True)
    data['employmentLength'] = data['employmentLength'].apply(employmentLength_to_int)

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