金融风控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

内容介绍

• 数据预处理
  • 缺失值的填充
  • 时间格式处理
  • 对象类型特征转换到数值
• 异常值处理
  • 基于3segama原则
  • 基于箱型图
• 数据分箱
  • 固定宽度分箱
  • 分位数分箱
    • 离散数值型数据分箱
    • 连续数值型数据分箱
• 特征交互
  • 特征和特征之间组合
  • 特征和特征之间衍生
• 特征编码
  • one-hot编码
  • label-encode编码
• 特征选择
  • 1 Filter
  • 2 Wrapper （RFE）
  • 3 Embedded

代码示例

# 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')

# 特征分为数值型和类别型
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
data_train.isnull().sum()  #查看缺失值情况
data_train = data_train.fillna(0) # 所有缺失值替换为指定的值0
data_train = data_train.fillna(axis=0,method='ffill')  # 缺失值上面的值替换缺失值
data_train = data_train.fillna(axis=0,method='bfill',limit=2) # 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

#按照中位数数填充数值型特征
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()


# 时间格式处理
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


# 对象类型特征转换到数值

# 对 employmentLength 进行转换
data_train['employmentLength'].value_counts(dropna=False).sort_index()

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()

# 对earliesCreditLine进行预处理
data_train['earliesCreditLine'].sample(5)
for data in [data_train, data_test_a]:
    data['earliesCreditLine'] = data['earliesCreditLine'].apply(lambda s: int(s[-4:]))


# 部分类别特征
cate_features = ['grade', 'subGrade', 'employmentTitle', 'homeOwnership', 'verificationStatus', 'purpose', 'postCode', 'regionCode', \
                 'applicationType', 'initialListStatus', 'title', 'policyCode']
for f in cate_features:
    print(f, '类型数：', data[f].nunique())

# 像等级这种类别特征，是有优先级的可以labelencode或者自映射
for data in [data_train, data_test_a]:
    data['grade'] = data['grade'].map({'A':1,'B':2,'C':3,'D':4,'E':5,'F':6,'G':7})

# 类型数在2之上，又不是高维稀疏的,且纯分类特征
for data in [data_train, data_test_a]:
    data = pd.get_dummies(data, columns=['subGrade', 'homeOwnership', 'verificationStatus', 'purpose', 'regionCode'], drop_first=True)


# 异常值处理
# 检测异常的方法一：均方差
def find_outliers_by_3segama(data,fea):
    data_std = np.std(data[fea])
    data_mean = np.mean(data[fea])
    outliers_cut_off = data_std * 3
    lower_rule = data_mean - outliers_cut_off
    upper_rule = data_mean + outliers_cut_off
    data[fea+'_outliers'] = data[fea].apply(lambda x:str('异常值') if x > upper_rule or x < lower_rule else '正常值')
    return data

data_train = data_train.copy()
for fea in numerical_fea:
    data_train = find_outliers_by_3segama(data_train,fea)
    print(data_train[fea+'_outliers'].value_counts())
    print(data_train.groupby(fea+'_outliers')['isDefault'].sum())
    print('*'*10)

#删除异常值
for fea in numerical_fea:
    data_train = data_train[data_train[fea+'_outliers']=='正常值']
    data_train = data_train.reset_index(drop=True) 



# 数据分桶

# 固定宽度分箱
# 通过除法映射到间隔均匀的分箱中，每个分箱的取值范围都是loanAmnt/1000
data['loanAmnt_bin1'] = np.floor_divide(data['loanAmnt'], 1000)
## 通过对数函数映射到指数宽度分箱
data['loanAmnt_bin2'] = np.floor(np.log10(data['loanAmnt']))

# 分位数分箱
data['loanAmnt_bin3'] = pd.qcut(data['loanAmnt'], 10, labels=False)



# 特征交互
for col in ['grade', 'subGrade']: 
    temp_dict = data_train.groupby([col])['isDefault'].agg(['mean']).reset_index().rename(columns={'mean': col + '_target_mean'})
    temp_dict.index = temp_dict[col].values
    temp_dict = temp_dict[col + '_target_mean'].to_dict()

    data_train[col + '_target_mean'] = data_train[col].map(temp_dict)
    data_test_a[col + '_target_mean'] = data_test_a[col].map(temp_dict)

# 其他衍生变量 mean 和 std
for df in [data_train, data_test_a]:
    for item in ['n0','n1','n2','n2.1','n4','n5','n6','n7','n8','n9','n10','n11','n12','n13','n14']:
        df['grade_to_mean_' + item] = df['grade'] / df.groupby([item])['grade'].transform('mean')
        df['grade_to_std_' + item] = df['grade'] / df.groupby([item])['grade'].transform('std')


# 特征编码
#label-encode:subGrade,postCode,title
# 高维类别特征需要进行转换
for col in tqdm(['employmentTitle', 'postCode', 'title','subGrade']):
    le = LabelEncoder()
    le.fit(list(data_train[col].astype(str).values) + list(data_test_a[col].astype(str).values))
    data_train[col] = le.transform(list(data_train[col].astype(str).values))
    data_test_a[col] = le.transform(list(data_test_a[col].astype(str).values))
print('Label Encoding 完成')


# 特征选择

# Filter

# 方差选择法
from sklearn.feature_selection import VarianceThreshold
#其中参数threshold为方差的阈值
VarianceThreshold(threshold=3).fit_transform(train,target_train)

# 相关系数法
from sklearn.feature_selection import SelectKBest
from scipy.stats import pearsonr
# 选择K个最好的特征，返回选择特征后的数据
# 第一个参数为计算评估特征是否好的函数，该函数输入特征矩阵和目标向量，
# 输出二元组（评分，P值）的数组，数组第i项为第i个特征的评分和P值。在此定义为计算相关系数
# 参数k为选择的特征个数
SelectKBest(k=5).fit_transform(train,target_train)

# 卡方检验
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
#参数k为选择的特征个数
SelectKBest(chi2, k=5).fit_transform(train,target_train)

# 互信息法
from sklearn.feature_selection import SelectKBest
from minepy import MINE
#由于MINE的设计不是函数式的，定义mic方法将其为函数式的，
#返回一个二元组，二元组的第2项设置成固定的P值0.5
def mic(x, y):
    m = MINE()
    m.compute_score(x, y)
    return (m.mic(), 0.5)
#参数k为选择的特征个数
SelectKBest(lambda X, Y: array(map(lambda x:mic(x, Y), X.T)).T, k=2).fit_transform(train,target_train)


# Wrapper （Recursive feature elimination，RFE）
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
#递归特征消除法，返回特征选择后的数据
#参数estimator为基模型
#参数n_features_to_select为选择的特征个数
RFE(estimator=LogisticRegression(), n_features_to_select=2).fit_transform(train,target_train)

# Embedded
from sklearn.feature_selection import SelectFromModel
from sklearn.linear_model import LogisticRegression
#带L1惩罚项的逻辑回归作为基模型的特征选择
SelectFromModel(LogisticRegression(penalty="l1", C=0.1)).fit_transform(train,target_train)

from sklearn.feature_selection import SelectFromModel
from sklearn.ensemble import GradientBoostingClassifier
#GBDT作为基模型的特征选择
SelectFromModel(GradientBoostingClassifier()).fit_transform(train,target_train)