datawhale零基础入门金融风控-建模调参

最新推荐文章于 2022-06-24 00:06:40 发布

原创最新推荐文章于 2022-06-24 00:06:40 发布 · 置顶 · 397 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#python #机器学习

本文详细介绍了如何使用LightGBM进行建模，包括数据预处理、5折交叉验证、贪心调参、网格搜索和贝叶斯优化。通过逐步优化参数，最终确定了最佳模型配置，提升了验证集AUC分数。

建模与调参

lgb模型

建模之前的操作，划分数据集

from sklearn.model_selection import KFold
# 分离数据集，方便进行交叉验证
X_train = data.loc[data['sample']=='train', :].drop(['id','issueDate','isDefault', 'sample'], axis=1)
X_test = data.loc[data['sample']=='test', :].drop(['id','issueDate','isDefault', 'sample'], axis=1)
y_train = data.loc[data['sample']=='train', 'isDefault']

# 5折交叉验证
folds = 5
seed = 2020
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)

使用lightgbm进行建模

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)))

调参

贪心调参
lgb树模型调参的顺序
①：max_depth、num_leaves
②：min_data_in_leaf、min_child_weight
③：bagging_fraction、 feature_fraction、bagging_freq
④：reg_lambda、reg_alpha
⑤：min_split_gain

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
"""

网格搜索

"""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_))
"""以下代码未运行，耗时较长，请谨慎运行，且每一步的最优参数需要在下一步进行手动更新，请注意"""

"""
需要注意一下的是，除了获取上面的获取num_boost_round时候用的是原生的lightgbm（因为要用自带的cv）
下面配合GridSearchCV时必须使用sklearn接口的lightgbm。
"""
"""设置n_estimators 为581，调整num_leaves和max_depth，这里选择先粗调再细调"""
lgb_params = {'num_leaves': range(10, 80, 5), 'max_depth': range(3,10,2)}
get_best_cv_params(learning_rate=0.1, n_estimators=581, num_leaves=None, max_depth=None, min_data_in_leaf=20, 
                   min_child_weight=0.001,bagging_fraction=1.0, feature_fraction=1.0, bagging_freq=0, 
                   min_split_gain=0, reg_lambda=0, reg_alpha=0, param_grid=lgb_params)

"""num_leaves为30，max_depth为7，进一步细调num_leaves和max_depth"""
lgb_params = {'num_leaves': range(25, 35, 1), 'max_depth': range(5,9,1)}
get_best_cv_params(learning_rate=0.1, n_estimators=85, num_leaves=None, max_depth=None, min_data_in_leaf=20, 
                   min_child_weight=0.001,bagging_fraction=1.0, feature_fraction=1.0, bagging_freq=0, 
                   min_split_gain=0, reg_lambda=0, reg_alpha=0, param_grid=lgb_params)

"""
确定min_data_in_leaf为45，min_child_weight为0.001 ，下面进行bagging_fraction、feature_fraction和bagging_freq的调参
"""
lgb_params = {'bagging_fraction': [i/10 for i in range(5,10,1)], 
              'feature_fraction': [i/10 for i in range(5,10,1)],
              'bagging_freq': range(0,81,10)
             }
get_best_cv_params(learning_rate=0.1, n_estimators=85, num_leaves=29, max_depth=7, min_data_in_leaf=45, 
                   min_child_weight=0.001,bagging_fraction=None, feature_fraction=None, bagging_freq=None, 
                   min_split_gain=0, reg_lambda=0, reg_alpha=0, param_grid=lgb_params)

"""
确定bagging_fraction为0.4、feature_fraction为0.6、bagging_freq为 ，下面进行reg_lambda、reg_alpha的调参
"""
lgb_params = {'reg_lambda': [0,0.001,0.01,0.03,0.08,0.3,0.5], 'reg_alpha': [0,0.001,0.01,0.03,0.08,0.3,0.5]}
get_best_cv_params(learning_rate=0.1, n_estimators=85, num_leaves=29, max_depth=7, min_data_in_leaf=45, 
                   min_child_weight=0.001,bagging_fraction=0.9, feature_fraction=0.9, bagging_freq=40, 
                   min_split_gain=0, reg_lambda=None, reg_alpha=None, param_grid=lgb_params)

"""
确定reg_lambda、reg_alpha都为0，下面进行min_split_gain的调参
"""
lgb_params = {'min_split_gain': [i/10 for i in range(0,11,1)]}
get_best_cv_params(learning_rate=0.1, n_estimators=85, num_leaves=29, max_depth=7, min_data_in_leaf=45, 
                   min_child_weight=0.001,bagging_fraction=0.9, feature_fraction=0.9, bagging_freq=40, 
                   min_split_gain=None, reg_lambda=0, reg_alpha=0, param_grid=lgb_params)
"""
参数确定好了以后，我们设置一个比较小的learning_rate 0.005，来确定最终的num_boost_round
"""
# 设置5折交叉验证
# cv_fold = StratifiedKFold(n_splits=5, random_state=0, shuffle=True, )
final_params = {
                'boosting_type': 'gbdt',
                'learning_rate': 0.01,
                'num_leaves': 29,
                'max_depth': 7,
                'min_data_in_leaf':45,
                'min_child_weight':0.001,
                'bagging_fraction': 0.9,
                'feature_fraction': 0.9,
                'bagging_freq': 40,
                'min_split_gain': 0,
                'reg_lambda':0,
                'reg_alpha':0,
                'nthread': 6
               }

cv_result = lgb.cv(train_set=lgb_train,
                   early_stopping_rounds=20,
                   num_boost_round=5000,
                   nfold=5,
                   stratified=True,
                   shuffle=True,
                   params=final_params,
                   metrics='auc',
                   seed=0,
                  )

print('迭代次数{}'.format(len(cv_result['auc-mean'])))
print('交叉验证的AUC为{}'.format(max(cv_result['auc-mean'])))

贝叶斯调参

pip install bayesian-optimization
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
"""定义优化参数"""
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)
"""显示优化结果"""
bayes_lgb.max
{'target': 0.7282530196283977,
 'params': {'bagging_fraction': 0.9815471914843896,
  'bagging_freq': 96.14757648686668,
  'feature_fraction': 0.6961281791730929,
  'max_depth': 19.45450235568963,
  'min_child_weight': 1.6266132496156782,
  'min_data_in_leaf': 37.697878831472295,
  'min_split_gain': 0.4184947943942168,
  'num_leaves': 14.221122487200399,
  'reg_alpha': 7.056502173310882,
  'reg_lambda': 9.924023764203156}}
参数优化完成后，我们可以根据优化后的参数建立新的模型，降低学习率并寻找最优模型迭代次数

"""调整一个较小的学习率，并通过cv函数确定当前最优的迭代次数"""
base_params_lgb = {
                    'boosting_type': 'gbdt',
                    'objective': 'binary',
                    'metric': 'auc',
                    'learning_rate': 0.01,
                    'num_leaves': 14,
                    'max_depth': 19,
                    'min_data_in_leaf': 37,
                    'min_child_weight':1.6,
                    'bagging_fraction': 0.98,
                    'feature_fraction': 0.69,
                    'bagging_freq': 96,
                    'reg_lambda': 9,
                    'reg_alpha': 7,
                    'min_split_gain': 0.4,
                    'nthread': 8,
                    'seed': 2020,
                    'silent': True,
                    'verbose': -1,
}

cv_result_lgb = lgb.cv(
    train_set=train_matrix,
    early_stopping_rounds=1000, 
    num_boost_round=20000,
    nfold=5,
    stratified=True,
    shuffle=True,
    params=base_params_lgb,
    metrics='auc',
    seed=0
)

print('迭代次数{}'.format(len(cv_result_lgb['auc-mean'])))
print('最终模型的AUC为{}'.format(max(cv_result_lgb['auc-mean'])))
迭代次数14269
最终模型的AUC为0.7315032037635779

模型参数已经确定，建立最终模型并对验证集进行验证

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',
                'metric': 'auc',
                'learning_rate': 0.01,
                'num_leaves': 14,
                'max_depth': 19,
                'min_data_in_leaf': 37,
                'min_child_weight':1.6,
                'bagging_fraction': 0.98,
                'feature_fraction': 0.69,
                'bagging_freq': 96,
                'reg_lambda': 9,
                'reg_alpha': 7,
                'min_split_gain': 0.4,
                'nthread': 8,
                'seed': 2020,
                'silent': True,
    }
    
    model = lgb.train(params, train_set=train_matrix, num_boost_round=14269, 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)))

通过5折交叉验证可以发现，模型迭代次数在13000次的时候会停之，那么我们在建立新模型时直接设置最大迭代次数，并使用验证集进行模型预测。

""""""
base_params_lgb = {
                    'boosting_type': 'gbdt',
                    'objective': 'binary',
                    'metric': 'auc',
                    'learning_rate': 0.01,
                    'num_leaves': 14,
                    'max_depth': 19,
                    'min_data_in_leaf': 37,
                    'min_child_weight':1.6,
                    'bagging_fraction': 0.98,
                    'feature_fraction': 0.69,
                    'bagging_freq': 96,
                    'reg_lambda': 9,
                    'reg_alpha': 7,
                    'min_split_gain': 0.4,
                    'nthread': 8,
                    'seed': 2020,
                    'silent': True,
}

"""使用训练集数据进行模型训练"""
final_model_lgb = lgb.train(base_params_lgb, train_set=train_matrix, valid_sets=valid_matrix, num_boost_round=13000, verbose_eval=1000, early_stopping_rounds=200)

"""预测并计算roc的相关指标"""
val_pre_lgb = final_model_lgb.predict(X_val)
fpr, tpr, threshold = metrics.roc_curve(y_val, val_pre_lgb)
roc_auc = metrics.auc(fpr, tpr)
print('调参后lightgbm单模型在验证集上的AUC：{}'.format(roc_auc))
"""画出roc曲线图"""
plt.figure(figsize=(8, 8))
plt.title('Validation ROC')
plt.plot(fpr, tpr, 'b', label = 'Val AUC = %0.4f' % roc_auc)
plt.ylim(0,1)
plt.xlim(0,1)
plt.legend(loc='best')
plt.title('ROC')
plt.ylabel('True Positive Rate')
plt.xlabel('False Positive Rate')
# 画出对角线
plt.plot([0,1],[0,1],'r--')
plt.show()