如何解决sklearn StackingClassifier 和样本权重
我有一个类似于
的堆叠工作流程import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import StackingClassifier
from sklearn.pipeline import make_pipeline
import xgboost as xgb
X = np.random.random(size=(1000,5))
y = np.random.choice([0,1],1000)
w = np.random.random(size=(1000,))
scaler = StandardScaler()
log_reg = LogisticRegression()
params = {
'n_estimators': 10,'max_depth': 3,'learning_rate': 0.1
}
log_reg_pipe = make_pipeline(
scaler,log_reg
)
stack_pipe = make_pipeline(
StackingClassifier(
estimators=[('lr',lr_stack_pipe)],final_estimator=xgb.XGBClassifier(**params),passthrough=True,cv=2
)
)
我希望能够将样本权重传递到 xgboost。我的问题是如何在最终估算器中设置样本权重?
我试过了
stack_pipe.fit(X,y,sample_weights=w)
抛出
ValueError: Pipeline.fit does not accept the sample_weights parameter. You can pass parameters to specific steps of your pipeline using the stepname__parameter format,e.g. `Pipeline.fit(X,logisticregression__sample_weight=sample_weight)`
解决方法
我最近也意识到堆叠估计器无法处理样本加权管道。我通过从 scikit-learn 继承 StackingRegressor
和 StackingClassifier
类并覆盖其 fit()
方法以更好地管理流水线来解决这个问题。请看以下内容:
"""Implement StackingClassifier that can handle sample-weighted Pipelines."""
from sklearn.ensemble import StackingRegressor,StackingClassifier
from copy import deepcopy
import numpy as np
from joblib import Parallel
from sklearn.base import clone
from sklearn.base import is_classifier,is_regressor
from sklearn.model_selection import cross_val_predict
from sklearn.model_selection import check_cv
from sklearn.utils import Bunch
from sklearn.utils.fixes import delayed
from sklearn.pipeline import Pipeline
ESTIMATOR_NAME_IN_PIPELINE = 'estimator'
def new_fit_single_estimator(estimator,X,y,sample_weight=None,message_clsname=None,message=None):
"""Private function used to fit an estimator within a job."""
if sample_weight is not None:
try:
if isinstance(estimator,Pipeline):
# determine name of final estimator
estimator_name = estimator.steps[-1][0]
kwargs = {estimator_name + '__sample_weight': sample_weight}
estimator.fit(X,**kwargs)
else:
estimator.fit(X,sample_weight=sample_weight)
except TypeError as exc:
if "unexpected keyword argument 'sample_weight'" in str(exc):
raise TypeError(
"Underlying estimator {} does not support sample weights."
.format(estimator.__class__.__name__)
) from exc
raise
else:
estimator.fit(X,y)
return estimator
class FlexibleStackingClassifier(StackingClassifier):
def __init__(self,estimators,final_estimator=None,*,cv=None,n_jobs=None,passthrough=False,verbose=0):
super().__init__(
estimators=estimators,final_estimator=final_estimator,cv=cv,n_jobs=n_jobs,passthrough=passthrough,verbose=verbose
)
def fit(self,sample_weight=None):
"""Fit the estimators.
Parameters
----------
X : {array-like,sparse matrix} of shape (n_samples,n_features)
Training vectors,where `n_samples` is the number of samples and
`n_features` is the number of features.
y : array-like of shape (n_samples,)
Target values.
sample_weight : array-like of shape (n_samples,) or default=None
Sample weights. If None,then samples are equally weighted.
Note that this is supported only if all underlying estimators
support sample weights.
.. versionchanged:: 0.23
when not None,`sample_weight` is passed to all underlying
estimators
Returns
-------
self : object
"""
# all_estimators contains all estimators,the one to be fitted and the
# 'drop' string.
names,all_estimators = self._validate_estimators()
self._validate_final_estimator()
stack_method = [self.stack_method] * len(all_estimators)
# Fit the base estimators on the whole training data. Those
# base estimators will be used in transform,predict,and
# predict_proba. They are exposed publicly.
self.estimators_ = Parallel(n_jobs=self.n_jobs)(
delayed(new_fit_single_estimator)(clone(est),sample_weight)
for est in all_estimators if est != 'drop'
)
self.named_estimators_ = Bunch()
est_fitted_idx = 0
for name_est,org_est in zip(names,all_estimators):
if org_est != 'drop':
self.named_estimators_[name_est] = self.estimators_[
est_fitted_idx]
est_fitted_idx += 1
else:
self.named_estimators_[name_est] = 'drop'
# To train the meta-classifier using the most data as possible,we use
# a cross-validation to obtain the output of the stacked estimators.
# To ensure that the data provided to each estimator are the same,we
# need to set the random state of the cv if there is one and we need to
# take a copy.
cv = check_cv(self.cv,y=y,classifier=is_classifier(self))
if hasattr(cv,'random_state') and cv.random_state is None:
cv.random_state = np.random.RandomState()
self.stack_method_ = [
self._method_name(name,est,meth)
for name,meth in zip(names,all_estimators,stack_method)
]
fit_params = ({f"{ESTIMATOR_NAME_IN_PIPELINE}__sample_weight": sample_weight}
if sample_weight is not None
else None)
predictions = Parallel(n_jobs=self.n_jobs)(
delayed(cross_val_predict)(clone(est),cv=deepcopy(cv),method=meth,n_jobs=self.n_jobs,fit_params=fit_params,verbose=self.verbose)
for est,meth in zip(all_estimators,self.stack_method_)
if est != 'drop'
)
# Only not None or not 'drop' estimators will be used in transform.
# Remove the None from the method as well.
self.stack_method_ = [
meth for (meth,est) in zip(self.stack_method_,all_estimators)
if est != 'drop'
]
X_meta = self._concatenate_predictions(X,predictions)
new_fit_single_estimator(self.final_estimator_,X_meta,sample_weight=sample_weight)
return self
class FlexibleStackingRegressor(StackingRegressor):
def __init__(self,sample_weight=sample_weight)
return self
我包含了 Regressor 和 Classifier 版本,尽管您似乎只需要能够使用 Classifier 子类。
但有一点警告:您必须在管道中为您的估算器指定相同的名称,并且该名称必须与下面定义的 ESTIMATOR_NAME_IN_PIPELINE
字段保持一致。否则代码将无法工作。例如,这里将是一个适当定义的 Pipeline
实例,其名称与上面显示的类定义脚本中定义的名称相同:
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import TweedieRegressor
from sklearn.feature_selection import VarianceThreshold
validly_named_pipeline = Pipeline([
('variance_threshold',VarianceThreshold()),('scaler',StandardScaler()),('estimator',TweedieRegressor())
])
这并不理想,但这是我现在所拥有的,无论如何都应该工作。
编辑: 明确地说,当我覆盖 fit()
方法时,我只是从 scikit 存储库中复制并粘贴了代码并进行了必要的更改,其中仅包含几个线。粘贴的代码很多都不是我的原创,而是scikit开发者的。
对于您的情况,由于您有一个嵌套的管道,以下是您在传递参数时必须使用的键。
list(stack_pipe.get_params().keys())
['memory','steps','verbose','stackingclassifier','stackingclassifier__cv','stackingclassifier__estimators','stackingclassifier__final_estimator__objective','stackingclassifier__final_estimator__use_label_encoder','stackingclassifier__final_estimator__base_score','stackingclassifier__final_estimator__booster','stackingclassifier__final_estimator__colsample_bylevel','stackingclassifier__final_estimator__colsample_bynode','stackingclassifier__final_estimator__colsample_bytree','stackingclassifier__final_estimator__gamma','stackingclassifier__final_estimator__gpu_id','stackingclassifier__final_estimator__importance_type','stackingclassifier__final_estimator__interaction_constraints','stackingclassifier__final_estimator__learning_rate','stackingclassifier__final_estimator__max_delta_step','stackingclassifier__final_estimator__max_depth','stackingclassifier__final_estimator__min_child_weight','stackingclassifier__final_estimator__missing','stackingclassifier__final_estimator__monotone_constraints','stackingclassifier__final_estimator__n_estimators','stackingclassifier__final_estimator__n_jobs','stackingclassifier__final_estimator__num_parallel_tree','stackingclassifier__final_estimator__random_state','stackingclassifier__final_estimator__reg_alpha','stackingclassifier__final_estimator__reg_lambda','stackingclassifier__final_estimator__scale_pos_weight','stackingclassifier__final_estimator__subsample','stackingclassifier__final_estimator__tree_method','stackingclassifier__final_estimator__validate_parameters','stackingclassifier__final_estimator__verbosity','stackingclassifier__final_estimator','stackingclassifier__n_jobs','stackingclassifier__passthrough','stackingclassifier__stack_method','stackingclassifier__verbose','stackingclassifier__lr','stackingclassifier__lr__memory','stackingclassifier__lr__steps','stackingclassifier__lr__verbose','stackingclassifier__lr__standardscaler','stackingclassifier__lr__logisticregression','stackingclassifier__lr__standardscaler__copy','stackingclassifier__lr__standardscaler__with_mean','stackingclassifier__lr__standardscaler__with_std','stackingclassifier__lr__logisticregression__C','stackingclassifier__lr__logisticregression__class_weight','stackingclassifier__lr__logisticregression__dual','stackingclassifier__lr__logisticregression__fit_intercept','stackingclassifier__lr__logisticregression__intercept_scaling','stackingclassifier__lr__logisticregression__l1_ratio','stackingclassifier__lr__logisticregression__max_iter','stackingclassifier__lr__logisticregression__multi_class','stackingclassifier__lr__logisticregression__n_jobs','stackingclassifier__lr__logisticregression__penalty','stackingclassifier__lr__logisticregression__random_state','stackingclassifier__lr__logisticregression__solver','stackingclassifier__lr__logisticregression__tol','stackingclassifier__lr__logisticregression__verbose','stackingclassifier__lr__logisticregression__warm_start']
如果仔细观察,sample_weight
中没有 final_estimator
键。您可能需要检查原始 API,看看它是否已折旧或重命名。
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。