AI训练营金融风控—06学习赛：贷款违约预测打卡

本学习笔记为阿里金融风控训练营的学习内容，学习链接为：AI训练营金融风控-阿里云天池

我的完整笔记为：AI训练营金融风控—06学习赛：贷款违约预测打卡_天池notebook-阿里云天池

  回顾：

AI训练营金融风控—01赛题理解打卡_宇宙高能量者的博客-CSDN博客

AI训练营金融风控—02EDA探索性数据分析打卡_宇宙高能量者的博客-CSDN博客

AI训练营金融风控—03特征工程打卡_宇宙高能量者的博客-CSDN博客

AI训练营金融风控—04建模与调参打卡_宇宙高能量者的博客-CSDN博客

AI训练营金融风控—05模型融合打卡_宇宙高能量者的博客-CSDN博客

一、学习知识点概要

赛题以预测用户贷款是否违约为任务，数据集报名后可见并可下载，该数据来自某信贷平台的贷款记录，总数据量超过120w，包含47列变量信息，其中15列为匿名变量。为了保证比赛的公平性，将会从中抽取80万条作为训练集，20万条作为测试集A，20万条作为测试集B，同时会对employmentTitle、purpose、postCode和title等信息进行脱敏。

评价方法为AUC评估模型效果（越大越好）。

二、学习内容

• EDA探索性数据分析
• 特征工程
• 建模与调参
• 模型融合
• 学习赛：贷款违约预测

三、学习问题与解答

1. 引入包

import pandas as pd
import numpy as np
import warnings
import os
import seaborn as sns
import matplotlib.pyplot as plt
"""
sns 相关设置
@return:
"""
# 声明使用 Seaborn 样式
sns.set()
# 有五种seaborn的绘图风格，它们分别是：darkgrid, whitegrid, dark, white, ticks。默认的主题是darkgrid。
sns.set_style("whitegrid")
# 有四个预置的环境，按大小从小到大排列分别为：paper, notebook, talk, poster。其中，notebook是默认的。
sns.set_context('talk')
# 中文字体设置-黑体
plt.rcParams['font.sans-serif'] = ['SimHei']
# 解决保存图像是负号'-'显示为方块的问题
plt.rcParams['axes.unicode_minus'] = False
# 解决Seaborn中文显示问题并调整字体大小
sns.set(font='SimHei')

import pandas as pd
import os
import gc
import lightgbm as lgb
import xgboost as xgb
from catboost import CatBoostRegressor
from sklearn.linear_model import SGDRegressor, LinearRegression, Ridge
from sklearn.preprocessing import MinMaxScaler
import math
import numpy as np
from tqdm import tqdm
from sklearn.model_selection import StratifiedKFold, KFold
from sklearn.metrics import accuracy_score, f1_score, roc_auc_score, log_loss
import matplotlib.pyplot as plt
import time
import warnings
warnings.filterwarnings('ignore')

2. 读取数据

train = pd.read_csv('http://tianchi-media.oss-cn-beijing.aliyuncs.com/dragonball/FRC/data_set/train.csv')
testA = pd.read_csv('http://tianchi-media.oss-cn-beijing.aliyuncs.com/dragonball/FRC/data_set/testA.csv')

print('Train data shape:',train.shape)
print('TestA data shape:',testA.shape)

train.head(2)

3. 数据探索

# 有缺失值的特征
print(f'There are {train.isnull().any().sum()} columns in train dataset with missing values.')

# 缺失值大于50%的特征
have_null_fea_dict = (train.isnull().sum()/len(train)).to_dict()
fea_null_moreThanHalf = {}
for key,value in have_null_fea_dict.items():
    if value > 0.5:
        fea_null_moreThanHalf[key] = value
fea_null_moreThanHalf


# nan可视化
missing = train.isnull().sum()/len(train)
missing = missing[missing > 0]
missing.sort_values(inplace=True)
missing.plot.bar()


#过滤数值型类别特征
def get_numerical_serial_fea(data,feas):
    numerical_serial_fea = []
    numerical_noserial_fea = []
    for fea in feas:
        temp = data[fea].nunique()
        if temp <= 10:
            numerical_noserial_fea.append(fea)
            continue
        numerical_serial_fea.append(fea)
    return numerical_serial_fea, numerical_noserial_fea

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)

numerical_serial_fea, numerical_noserial_fea = get_numerical_serial_fea(train,numerical_fea)

print("数值种类大于10的数值型特征", len(numerical_serial_fea), numerical_serial_fea, '\n')
print("数值种类小于等于10的数值型特征", len(numerical_noserial_fea), numerical_noserial_fea, '\n')
print("类别型特征", len(category_fea), category_fea, '\n')

4. 数据预处理

# 特征交互
for col in ['grade', 'subGrade']: 
    temp_dict = 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()

    train[col + '_target_mean'] = train[col].map(temp_dict)
    testA[col + '_target_mean'] = testA[col].map(temp_dict)
    
# 其他衍生变量 mean 和 std
for df in [train, testA]:
    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')


data = pd.concat([train, testA], axis=0, ignore_index=True)
print(data.shape)


# reduce_mem_usage 函数通过调整数据类型，帮助我们减少数据在内存中占用的空间
def reduce_mem_usage(df):
    start_mem = df.memory_usage().sum() 
    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))
    
    for col in df.columns:
        col_type = df[col].dtype
        
        if col_type != object:
            c_min = df[col].min()
            c_max = df[col].max()
            if str(col_type)[:3] == 'int':
                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:
                    df[col] = df[col].astype(np.int8)
                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:
                    df[col] = df[col].astype(np.int16)
                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:
                    df[col] = df[col].astype(np.int32)
                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:
                    df[col] = df[col].astype(np.int64)  
            else:
                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:
                    df[col] = df[col].astype(np.float16)
                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:
                    df[col] = df[col].astype(np.float32)
                else:
                    df[col] = df[col].astype(np.float64)
        else:
            df[col] = df[col].astype('category')

    end_mem = df.memory_usage().sum() 
    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))
    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))
    
    return df


# 读取数据
data = reduce_mem_usage(data)


# 首先对employmentLength进行转换到数值


data['employmentLength'].replace(to_replace='10+ years', value='10 years', inplace=True)
data['employmentLength'].replace('< 1 year', '0 years', inplace=True)

def employmentLength_to_int(s):
    if pd.isnull(s):
        return s
    else:
        return np.int8(s.split()[0])
    
data['employmentLength'] = data['employmentLength'].apply(employmentLength_to_int)
data['employmentLength'].value_counts(dropna=False).sort_index()


# 对earliesCreditLine进行预处理

print(data['earliesCreditLine'].sample(5))
data['earliesCreditLine'] = data['earliesCreditLine'].apply(lambda s: int(s[-4:]))
data['earliesCreditLine'].describe()

# 类型数在2之上，又不是高维稀疏的
data = pd.get_dummies(data, columns=['grade', 'subGrade', 'homeOwnership', 
                                     'verificationStatus', 'purpose', 'regionCode'], 
                      drop_first=True)

# 高维类别特征需要进行转换
for f in ['employmentTitle', 'postCode', 'title']:
    data[f+'_cnts'] = data.groupby([f])['id'].transform('count')
    data[f+'_rank'] = data.groupby([f])['id'].rank(ascending=False).astype(int)
    del data[f]

5. 训练数据/测试数据准备

features = [f for f in data.columns if f not in ['id','issueDate','isDefault']]

train = data[data.isDefault.notnull()].reset_index(drop=True)
test = data[data.isDefault.isnull()].reset_index(drop=True)

x_train = train[features]
x_test = test[features]

y_train = train['isDefault']

6. 模型调参

# 使用5折交叉验证进行模型性能评估

import lightgbm as lgb
"""使用lightgbm 5折交叉验证进行建模预测"""
cv_scores = []
for i, (train_index, valid_index) in enumerate(kf.split(X_train, y_train)):
    print('************************************ {} ************************************'.format(str(i+1)))
    X_train_split, y_train_split, X_val, y_val = X_train.iloc[train_index], y_train[train_index], X_train.iloc[valid_index], y_train[valid_index]
    
    train_matrix = lgb.Dataset(X_train_split, label=y_train_split)
    valid_matrix = lgb.Dataset(X_val, label=y_val)

    params = {
                'boosting_type': 'gbdt',
                'objective': 'binary',
                'learning_rate': 0.1,
                'metric': 'auc',
        
                'min_child_weight': 1e-3,
                'num_leaves': 31,
                'max_depth': -1,
                'reg_lambda': 0,
                'reg_alpha': 0,
                'feature_fraction': 1,
                'bagging_fraction': 1,
                'bagging_freq': 0,
                'seed': 2020,
                'nthread': 8,
                'silent': True,
                'verbose': -1,
    }
    
    model = lgb.train(params, train_set=train_matrix, num_boost_round=20000, valid_sets=valid_matrix, verbose_eval=1000, early_stopping_rounds=200)
    val_pred = model.predict(X_val, num_iteration=model.best_iteration)
    
    cv_scores.append(roc_auc_score(y_val, val_pred))
    print(cv_scores)

print("lgb_scotrainre_list:{}".format(cv_scores))
print("lgb_score_mean:{}".format(np.mean(cv_scores)))
print("lgb_score_std:{}".format(np.std(cv_scores)))

from sklearn.model_selection import cross_val_score

# 调objective
best_obj = dict()
for obj in objective:
    model = LGBMRegressor(objective=obj)
    """预测并计算roc的相关指标"""
    score = cross_val_score(model, X_train, y_train, cv=5, scoring='roc_auc').mean()
    best_obj[obj] = score
    
# num_leaves
best_leaves = dict()
for leaves in num_leaves:
    model = LGBMRegressor(objective=min(best_obj.items(), key=lambda x:x[1])[0], num_leaves=leaves)
    """预测并计算roc的相关指标"""
    score = cross_val_score(model, X_train, y_train, cv=5, scoring='roc_auc').mean()
    best_leaves[leaves] = score
    
# max_depth
best_depth = dict()
for depth in max_depth:
    model = LGBMRegressor(objective=min(best_obj.items(), key=lambda x:x[1])[0],
                          num_leaves=min(best_leaves.items(), key=lambda x:x[1])[0],
                          max_depth=depth)
    """预测并计算roc的相关指标"""
    score = cross_val_score(model, X_train, y_train, cv=5, scoring='roc_auc').mean()
    best_depth[depth] = score

"""
可依次将模型的参数通过上面的方式进行调整优化，并且通过可视化观察在每一个最优参数下模型的得分情况
"""

"""通过网格搜索确定最优参数"""
from sklearn.model_selection import GridSearchCV

def get_best_cv_params(learning_rate=0.1, n_estimators=581, num_leaves=31, max_depth=-1, bagging_fraction=1.0, 
                       feature_fraction=1.0, bagging_freq=0, min_data_in_leaf=20, min_child_weight=0.001, 
                       min_split_gain=0, reg_lambda=0, reg_alpha=0, param_grid=None):
    # 设置5折交叉验证
    cv_fold = StratifiedKFold(n_splits=5, random_state=0, shuffle=True, )
    
    model_lgb = lgb.LGBMClassifier(learning_rate=learning_rate,
                                   n_estimators=n_estimators,
                                   num_leaves=num_leaves,
                                   max_depth=max_depth,
                                   bagging_fraction=bagging_fraction,
                                   feature_fraction=feature_fraction,
                                   bagging_freq=bagging_freq,
                                   min_data_in_leaf=min_data_in_leaf,
                                   min_child_weight=min_child_weight,
                                   min_split_gain=min_split_gain,
                                   reg_lambda=reg_lambda,
                                   reg_alpha=reg_alpha,
                                   n_jobs= 8
                                  )
    grid_search = GridSearchCV(estimator=model_lgb, 
                               cv=cv_fold,
                               param_grid=param_grid,
                               scoring='roc_auc'
                              )
    grid_search.fit(X_train, y_train)

    print('模型当前最优参数为:{}'.format(grid_search.best_params_))
    print('模型当前最优得分为:{}'.format(grid_search.best_score_))

7. 模型训练

def cv_model(clf, train_x, train_y, test_x, clf_name):
    folds = 5
    seed = 2020
    kf = KFold(n_splits=folds, shuffle=True, random_state=seed)

    train = np.zeros(train_x.shape[0])
    test = np.zeros(test_x.shape[0])

    cv_scores = []

    for i, (train_index, valid_index) in enumerate(kf.split(train_x, train_y)):
        print('************************************ {} ************************************'.format(str(i+1)))
        trn_x, trn_y, val_x, val_y = train_x.iloc[train_index], train_y[train_index], train_x.iloc[valid_index], train_y[valid_index]

        if clf_name == "lgb":
            train_matrix = clf.Dataset(trn_x, label=trn_y)
            valid_matrix = clf.Dataset(val_x, label=val_y)

            params = {
                'boosting_type': 'gbdt',
                'objective': 'binary',
                'metric': 'auc',
                'min_child_weight': 5,
                'num_leaves': 2 ** 5,
                'lambda_l2': 10,
                'feature_fraction': 0.8,
                'bagging_fraction': 0.8,
                'bagging_freq': 4,
                'learning_rate': 0.1,
                'seed': 2020,
                'nthread': 28,
                'n_jobs':24,
                'silent': True,
                'verbose': -1,
            }

            model = clf.train(params, train_matrix, 50000, valid_sets=[train_matrix, valid_matrix], verbose_eval=200,early_stopping_rounds=200)
            val_pred = model.predict(val_x, num_iteration=model.best_iteration)
            test_pred = model.predict(test_x, num_iteration=model.best_iteration)
            
            # print(list(sorted(zip(features, model.feature_importance("gain")), key=lambda x: x[1], reverse=True))[:20])
                
        if clf_name == "xgb":
            train_matrix = clf.DMatrix(trn_x , label=trn_y)
            valid_matrix = clf.DMatrix(val_x , label=val_y)
            test_matrix = clf.DMatrix(test_x)
            
            params = {'booster': 'gbtree',
                      'objective': 'binary:logistic',
                      'eval_metric': 'auc',
                      'gamma': 1,
                      'min_child_weight': 1.5,
                      'max_depth': 5,
                      'lambda': 10,
                      'subsample': 0.7,
                      'colsample_bytree': 0.7,
                      'colsample_bylevel': 0.7,
                      'eta': 0.04,
                      'tree_method': 'exact',
                      'seed': 2020,
                      'nthread': 36,
                      "silent": True,
                      }
            
            watchlist = [(train_matrix, 'train'),(valid_matrix, 'eval')]
            
            model = clf.train(params, train_matrix, num_boost_round=50000, evals=watchlist, verbose_eval=200, early_stopping_rounds=200)
            val_pred  = model.predict(valid_matrix, ntree_limit=model.best_ntree_limit)
            test_pred = model.predict(test_matrix , ntree_limit=model.best_ntree_limit)
                 
        if clf_name == "cat":
            params = {'learning_rate': 0.05, 'depth': 5, 'l2_leaf_reg': 10, 'bootstrap_type': 'Bernoulli',
                      'od_type': 'Iter', 'od_wait': 50, 'random_seed': 11, 'allow_writing_files': False}
            
            model = clf(iterations=20000, **params)
            model.fit(trn_x, trn_y, eval_set=(val_x, val_y),
                      cat_features=[], use_best_model=True, verbose=500)
            
            val_pred  = model.predict(val_x)
            test_pred = model.predict(test_x)
            
        train[valid_index] = val_pred
        test = test_pred / kf.n_splits
        cv_scores.append(roc_auc_score(val_y, val_pred))
        
        print(cv_scores)
       
    print("%s_scotrainre_list:" % clf_name, cv_scores)
    print("%s_score_mean:" % clf_name, np.mean(cv_scores))
    print("%s_score_std:" % clf_name, np.std(cv_scores))
    return train, test


def lgb_model(x_train, y_train, x_test):
    lgb_train, lgb_test = cv_model(lgb, x_train, y_train, x_test, "lgb")
    return lgb_train, lgb_test

def xgb_model(x_train, y_train, x_test):
    xgb_train, xgb_test = cv_model(xgb, x_train, y_train, x_test, "xgb")
    return xgb_train, xgb_test

def cat_model(x_train, y_train, x_test):
    cat_train, cat_test = cv_model(CatBoostRegressor, x_train, y_train, x_test, "cat") 
    return cat_train, cat_test

lgb_train, lgb_test = lgb_model(x_train, y_train, x_test)
xgb_train, xgb_test = xgb_model(x_train, y_train, x_test)
cat_train, cat_test = cat_model(x_train, y_train, x_test)

rh_test = lgb_test*0.5 + xgb_test*0.5
testA['isDefault'] = rh_test
testA[['id','isDefault']].to_csv('test_sub.csv', index=False)

四、学习思考与总结

 

得分要点：特征构造