阿里云天池金融风控-task4

建模调参

首先我们导入训练集和测试集

X_train = train[test.columns].drop(columns='id')
y_train = train['isDefault']
X_test = test.drop(columns='id')

fill_con = ['employmentTitle','employmentLength','postCode',
            'employmentTitle_freq_encode','title_freq_encode','title'] 
agg_train = agg_train.sort_values(by = 'id').reset_index(drop=True)
agg_test = agg_test.sort_values(by = 'id').reset_index(drop=True)
agg_train[fill_con] = agg_train[fill_con].fillna(agg_train[fill_con].mode())
agg_train = agg_train.fillna(agg_train.median())
# test1 = test
agg_test[fill_con] = agg_test[fill_con].fillna(agg_test[fill_con].mode())
agg_test = agg_test.fillna(agg_test.median())

X_train1 = agg_train[agg_test.columns].drop(columns='id')
y_train1 = agg_train['isDefault']
X_test1 = agg_test

这里我们试用一下梯度提升树进行特征选择

from sklearn.feature_selection import SelectFromModel
from sklearn.ensemble import GradientBoostingClassifier
#GBDT作为基模型的特征选择
clf = GradientBoostingClassifier().fit(X_train1,y_train1)
model_2 = SelectFromModel(clf,prefit=True)
new_feature = X_train1.columns[model_2.get_support()]

接下来定义LightGBM，XGBoost和Catboost模型

import os
import gc
import lightgbm as lgb
import xgboost as xgb
from sklearn.model_selection import KFold
# from catboost import CatBoostRegressor
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': 2021,
                      '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,model

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

利用LightGBM进行预测

lgb_train, lgb_test,model = lgb_model(X_train, y_train, X_test)

这里的话总是在跑的过程中DSW会崩溃，最好用下面的语句跑完保存一下模型。

# """保存模型到本地"""
# # 保存模型
final_model_lgb.save_model('model.txt')

还有调用保存模型的语句：

import lightgbm as lgb
gbm = lgb.Booster(model_file='model.txt')

接下来是调参工作-贝叶斯调参

#贝叶斯调参-----------------
from sklearn.model_selection import cross_val_score

"""定义优化函数"""
def rf_cv_lgb(num_leaves, max_depth, bagging_fraction, feature_fraction, bagging_freq, min_data_in_leaf, 
              min_child_weight, min_split_gain, reg_lambda, reg_alpha):
    # 建立模型
    model_lgb = lgb.LGBMClassifier(boosting_type='gbdt', bjective='binary', metric='auc',
                                   learning_rate=0.1, n_estimators=5000,
                                   num_leaves=int(num_leaves), max_depth=int(max_depth), 
                                   bagging_fraction=round(bagging_fraction, 2), feature_fraction=round(feature_fraction, 2),
                                   bagging_freq=int(bagging_freq), min_data_in_leaf=int(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
                                  )
    
    val = cross_val_score(model_lgb, X_train_split, y_train_split, cv=5, scoring='roc_auc').mean()
    
    return val
from bayes_opt import BayesianOptimization
from sklearn.model_selection import cross_val_score
"""定义优化参数"""
X_train_split, X_val, y_train_split, y_val = train_test_split(x_train, y_train, test_size=0.2)
bayes_lgb = BayesianOptimization(
    rf_cv_lgb, 
    {
        'num_leaves':(10, 200),
        'max_depth':(3, 20),
        'bagging_fraction':(0.5, 1.0),
        'feature_fraction':(0.5, 1.0),
        'bagging_freq':(0, 100),
        'min_data_in_leaf':(10,100),
        'min_child_weight':(0, 10),
        'min_split_gain':(0.0, 1.0),
        'reg_alpha':(0.0, 10),
        'reg_lambda':(0.0, 10),
    }
)

"""开始优化"""
bayes_lgb.maximize(n_iter=10)

最后的AUC为0.74提升了一点