数据挖掘-金融风控-建模调参

数据挖掘-金融风控-建模调参

在模型预测中一般用的预测模型是逻辑回归模型、树模型、集成模型；调参的方法一般有贪心调参方法、网格调参方法、贝叶斯调参方法。

1、导入数据

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')

2、读入数据

data_train=pd.read_csv('数据挖掘-金融风控/train.csv')
data_test=pd.read_csv('数据挖掘-金融风控/testA.csv')

data_train['sample']='train'
data_test['sample']='test'
data_base=pd.concat([data_train,data_test],axis=0)

将train数据集和test数据集合并

3、特征工程

特征工程参照task3来，将特征工程做好。

4、建模

建模前的预操作

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

"""对训练集数据进行划分，分成训练集和验证集，并进行相应的操作"""
from sklearn.model_selection import train_test_split
import lightgbm as lgb
# 数据集划分
X_train_split, X_val, y_train_split, y_val = train_test_split(X_train, y_train, test_size=0.2)
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,
}

"""使用训练集数据进行模型训练"""
model = lgb.train(params, train_set=train_matrix, valid_sets=valid_matrix, num_boost_round=20000, verbose_eval=1000, early_stopping_rounds=200)

对验证集进行预测

from sklearn import metrics
from sklearn.metrics import roc_auc_score

"""预测并计算roc的相关指标"""
val_pre_lgb = model.predict(X_val, num_iteration=model.best_iteration)
fpr, tpr, threshold = metrics.roc_curve(y_val, val_pre_lgb)
roc_auc = metrics.auc(fpr, tpr)
print('未调参前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()

采用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)))

5、模型调参

1、贪心调参

先使用当前对模型影响最大的参数进行调优，达到当前参数下的模型最优化，再使用对模型影响次之的参数进行调优，如此下去，直到所有的参数调整完毕。

这个方法的缺点就是可能会调到局部最优而不是全局最优，但是只需要一步一步的进行参数最优化调试即可，容易理解。

需要注意的是在树模型中参数调整的顺序，也就是各个参数对模型的影响程度，这里列举一下日常调参过程中常用的参数和调参顺序：

• 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
"""

2、网格搜索

sklearn 提供GridSearchCV用于进行网格搜索，只需要把模型的参数输进去，就能给出最优化的结果和参数。相比起贪心调参，网格搜索的结果会更优，但是网格搜索只适合于小数据集，一旦数据的量级上去了，很难得出结果。

同样以Lightgbm算法为例，进行网格搜索调参：

"""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'])))

在实际调整过程中，可先设置一个较大的学习率（上面的例子中0.1），通过Lgb原生的cv函数进行树个数的确定，之后再通过上面的实例代码进行参数的调整优化。
最后针对最优的参数设置一个较小的学习率（例如0.05），同样通过cv函数确定树的个数，确定最终的参数
需要注意的是，针对大数据集，上面每一层参数的调整都需要耗费较长时间．

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)