小编ina*_*tos的帖子

我正在使用scikit，正在尝试调整XGBoost。我尝试使用嵌套的交叉验证，通过管道对训练折叠进行重新缩放（以避免数据泄漏和过度拟合），并与GridSearchCV并行进行参数调整，并与cross_val_score并行获得roc_auc得分。

from imblearn.pipeline import Pipeline 
from sklearn.model_selection import RepeatedKFold 
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import cross_val_score
from xgboost import XGBClassifier


std_scaling = StandardScaler() 
algo = XGBClassifier()

steps = [('std_scaling', StandardScaler()), ('algo', XGBClassifier())]

pipeline = Pipeline(steps)

parameters = {'algo__min_child_weight': [1, 2],
              'algo__subsample': [0.6, 0.9],
              'algo__max_depth': [4, 6],
              'algo__gamma': [0.1, 0.2],
              'algo__learning_rate': [0.05, 0.5, 0.3]}

cv1 = RepeatedKFold(n_splits=2, n_repeats = 5, random_state = 15)

clf_auc = GridSearchCV(pipeline, cv = cv1, param_grid = parameters, scoring = 'roc_auc', n_jobs=-1, return_train_score=False)

cv1 = RepeatedKFold(n_splits=2, …