【金融风控系列】_[1]_贷款违约预测

#!pip install pandas --user#!pip install lightgbm --user#!pip install xgboost --user!pip install catboost --user
!pip install joblib --user
!pip install scikit-learn --user
!pip install imblearn --user
!pip install imbalanced-ensemble --user
!pip self-paced-ensemble --user

import pandas as pdimport datetimeimport warnings
warnings.filterwarnings('ignore')from sklearn.model_selection import StratifiedKFold#warnings.filterwarnings('ignore')#%matplotlib inlinefrom sklearn.metrics import roc_auc_score## 数据降维处理的from sklearn.model_selection import train_test_split  
from catboost import CatBoostClassifierimport imbalanced_ensemble as imbensfrom collections import Counterfrom imbalanced_ensemble.sampler.over_sampling import     SMOTE 
import numpy as np
train=pd.read_csv("./data/data53042/train.csv")
testA=pd.read_csv("./data/data53042/testA.csv")

numerical_fea = list(train.select_dtypes(exclude=['object']).columns)
category_fea = list(filter(lambda x: x not in numerical_fea,list(train.columns)))
label = 'isDefault'numerical_fea.remove(label)#按照中位数填充数值型特征train[numerical_fea] = train[numerical_fea].fillna(train[numerical_fea].median())
testA[numerical_fea] = testA[numerical_fea].fillna(testA[numerical_fea].median())#按照众数填充类别型特征train[category_fea] = train[category_fea].fillna(train[category_fea].mode())
testA[category_fea] = testA[category_fea].fillna(testA[category_fea].mode())def make_fea(data):
    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['grade'] = data['grade'].map({'A':1,'B':2,'C':3,'D':4,'E':5,'F':6,'G':7})
    data['subGrade'] = data['subGrade'].map({'E2':1,'D2':2,'D3':3,'A4':4,'C2':5,'A5':6,'C3':7,'B4':8,'B5':9,'E5':10,        'D4':11,'B3':12,'B2':13,'D1':14,'E1':15,'C5':16,'C1':17,'A2':18,'A3':19,'B1':20,        'E3':21,'F1':22,'C4':23,'A1':24,'D5':25,'F2':26,'E4':27,'F3':28,'G2':29,'F5':30,        'G3':31,'G1':32,'F4':33,'G4':34,'G5':35})

    data = pd.get_dummies(data, columns=['subGrade', 'homeOwnership', 'verificationStatus', 'purpose', 'regionCode'], drop_first=True)
    data['employmentLength'] = data['employmentLength'].map({'NaN':-1,'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,'< 1 year':0})
    data['earliesCreditLine'] = data['earliesCreditLine'].apply(lambda s: int(s[-4:]))    for item in ['n0','n1','n2','n2.1','n4','n5','n6','n7','n8','n9','n10','n11','n12','n13','n14']:
        data['grade_to_mean_' + item] = data['grade'] / data.groupby([item])['grade'].transform('mean')
        data['grade_to_std_' + item] = data['grade'] / data.groupby([item])['grade'].transform('std')
    data['n15']=data['n8']*data['n10']    return data# 特征工程 简单处理train = make_fea(train)
testA = make_fea(testA)print(train.shape)print(testA.shape)print("数据预处理完成!")  
sub=testA[['id']].copy()
sub['isDefault']=0testA=testA.drop(['id','issueDate'],axis=1)
data_x=train.drop(['isDefault','id','issueDate'],axis=1)

data_y=train[['isDefault']].copy()

col=['grade','subGrade','employmentTitle','homeOwnership','verificationStatus','purpose','postCode','regionCode',     'initialListStatus','applicationType','policyCode']for i in data_x.columns:    if i in col:
        data_x[i] = data_x[i].astype('str')for i in testA.columns:    if i in col:
        testA[i] = testA[i].astype('str')

answers = []
mean_score = 0n_folds = 5sk = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=2019)print(data_x.shape)print(testA.shape)# 在测试集中有部分特征训练集中没有，进行处理COLNAME = data_x.columns
testA = testA[COLNAME]# 处理INF NAN ，替换成 -1 注意：np.inf和-np.inf是不同的两个值，这里经常遇到忘记处理后者引发错误data_x.replace([np.inf, -np.inf, np.nan], -1, inplace=True)
testA.replace([np.inf, -np.inf, np.nan], -1, inplace=True)#  -----重复正样本，因为原始数据比例约为3：1 因此对正样本重复三次拼接到原始数据中-----a = [i for i, x in enumerate(data_y.values) if x[0]==1]
all_1 = data_x.iloc[a]
all_y = pd.DataFrame(np.ones(all_1.shape[0],dtype=int),columns=['isDefault'])print(all_y.shape)print(data_x.shape,data_y.shape)for i in range(3):
    data_y= pd.concat([data_y,all_y],axis=0)
    data_x = pd.concat([data_x,all_1],axis=0)    print(data_x.shape,data_y.shape)
data_x.reset_index(drop=True,inplace =True)
data_y.reset_index(drop=True,inplace =True)'''
# -----使用SMOTE算法对负样本进行扩充-----
sm = SMOTE(random_state=42)
data_x, data_y = sm.fit_resample(data_x, data_y)
print('Resampled dataset' , data_y.value_counts())
'''

model=CatBoostClassifier(
            loss_function="Logloss",
            eval_metric="AUC",
            task_type="CPU",
            learning_rate=0.1,
            iterations=500,
            random_seed=2020,
            verbose=500,
            depth=7)for train, test in sk.split(data_x, data_y):
    x_train = data_x.iloc[train]
    y_train = data_y.iloc[train]
    x_test = data_x.iloc[test]
    y_test = data_y.iloc[test]    '''
    # -----使用SPE 算法对不平衡数据进行处理-----
    clf = imbens.ensemble.SelfPacedEnsembleClassifier(
        base_estimator = model,#基准分类模型 可以自定义，需要模型包含fit等方法，具体信息请查看参考文献3
        n_estimators = 5,
        random_state=49
    ).fit(x_train, y_train)
    '''
    # -----使用BalanceCascade 算法对不平衡数据进行处理-----
    '''
    clf = imbens.ensemble.BalanceCascadeClassifier(        
        base_estimator = model,#基准分类模型 可以自定义，需要模型包含fit等方法，具体信息请查看参考文献3
        n_estimators = 5,
        random_state=49
    ).fit(x_train, y_train)
    '''

    # 基准分类模型
    clf = model.fit(x_train,y_train)#, eval_set=(x_test,y_test),cat_features=col)

    yy_pred_valid=clf.predict_proba(x_test)[:,-1]    print('cat验证的auc:{}'.format(roc_auc_score(y_test, yy_pred_valid)))
    mean_score += roc_auc_score(y_test, yy_pred_valid) / n_folds
    y_pred_valid = clf.predict_proba(testA)[:,-1]
    answers.append(y_pred_valid)print('mean valAuc:{}'.format(mean_score))
cat_pre=sum(answers)/n_folds
sub['isDefault']=cat_pre
sub.to_csv('金融预测.csv',index=False)

model=CatBoostClassifier(
            loss_function="Logloss",
            eval_metric="AUC",
            task_type="CPU",
            learning_rate=0.1,
            iterations=500,
            random_seed=2020,
            verbose=500,
            depth=7)#----- 欠采样模型 -----a = [i for i, x in enumerate(data_y.values) if x[0]==1]
all_1 = data_x.iloc[a]
all_y1 = pd.DataFrame(np.ones(all_1.shape[0]),columns=['isDefault'])
all_y0 = pd.DataFrame(np.ones(all_y.shape[0]),columns=['isDefault'])print(all_y1.shape)#for i in range(4): # 数据比1：4+i= 0all_0 = data_x.iloc[i*all_y1.shape[0]:(i+1)*all_y1.shape[0],:]
data_y_= pd.concat([all_y1,all_y0],axis=0)
data_x_ = pd.concat([all_1,all_0],axis=0)print(data_x_.shape,data_y_.shape,all_0.shape)for train, test in sk.split(data_x, data_y):
    x_train = data_x.iloc[train]
    y_train = data_y.iloc[train]
    x_test = data_x.iloc[test]
    y_test = data_y.iloc[test]    # 基准分类模型
    #clf = model.fit(x_train,y_train)#, eval_set=(x_test,y_test),cat_features=col)

    clf = imbens.ensemble.SelfPacedEnsembleClassifier(
        base_estimator = model,#基准分类模型 可以自定义，需要模型包含fit等方法，具体信息请查看参考文献3
        n_estimators = 5,
        random_state=49
    ).fit(x_train, y_train)
    yy_pred_valid=clf.predict_proba(x_test)[:,-1]    print('cat验证的auc:{}'.format(roc_auc_score(y_test, yy_pred_valid)))
    mean_score += roc_auc_score(y_test, yy_pred_valid) / n_folds
    y_pred_valid = clf.predict_proba(testA)[:,-1]
    answers.append(y_pred_valid)print('mean valAuc:{}'.format(mean_score))
cat_pre=sum(answers)/(n_folds) # 数据比1：4sub['isDefault']=cat_pre
sub.to_csv('金融预测.csv',index=False)