- html - 出于某种原因,IE8 对我的 Sass 文件中继承的 html5 CSS 不友好?
- JMeter 在响应断言中使用 span 标签的问题
- html - 在 :hover and :active? 上具有不同效果的 CSS 动画
- html - 相对于居中的 html 内容固定的 CSS 重复背景?
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, y, logisticregression__sample_weight=sample_weight)`
最佳答案
我最近还意识到堆叠估算器无法处理样本加权管道。我通过子类化 scikit-learn 的 StackingRegressor
和 StackingClassifier
类并覆盖其 fit()
方法来解决这个问题,以更好地管理管道。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, y, **kwargs)
else:
estimator.fit(X, y, 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, X, y, 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), X, y, 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, est, 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), X, y, 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, y,
sample_weight=sample_weight)
return self
class FlexibleStackingRegressor(StackingRegressor):
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, X, y, 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), X, y, 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, est, 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), X, y, 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, y,
sample_weight=sample_weight)
return self
我包括了回归器和分类器版本,尽管您似乎只需要能够使用分类器子类。
但请注意:您必须在管道中为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
字段对齐。否则代码将无法运行。例如,这里将是一个适当定义的 Pipeline
实例,使用与上面显示的类定义脚本中定义的相同的名称:
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,但这是我目前拥有的,无论如何都应该可以工作。
编辑:为了清楚起见,当我覆盖 fit()
方法时,我只是从 scikit 存储库中复制并粘贴代码并进行了必要的更改,这只有几行。粘贴的代码中有很多不是我的原创作品,而是 scikit 开发人员的作品。
关于python - sklearn StackingClassifier 和样本权重,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/65850996/
我正在处理一组标记为 160 个组的 173k 点。我想通过合并最接近的(到 9 或 10 个组)来减少组/集群的数量。我搜索过 sklearn 或类似的库,但没有成功。 我猜它只是通过 knn 聚类
我有一个扁平数字列表,这些数字逻辑上以 3 为一组,其中每个三元组是 (number, __ignored, flag[0 or 1]),例如: [7,56,1, 8,0,0, 2,0,0, 6,1,
我正在使用 pipenv 来管理我的包。我想编写一个 python 脚本来调用另一个使用不同虚拟环境(VE)的 python 脚本。 如何运行使用 VE1 的 python 脚本 1 并调用另一个 p
假设我有一个文件 script.py 位于 path = "foo/bar/script.py"。我正在寻找一种在 Python 中通过函数 execute_script() 从我的主要 Python
这听起来像是谜语或笑话,但实际上我还没有找到这个问题的答案。 问题到底是什么? 我想运行 2 个脚本。在第一个脚本中,我调用另一个脚本,但我希望它们继续并行,而不是在两个单独的线程中。主要是我不希望第
我有一个带有 python 2.5.5 的软件。我想发送一个命令,该命令将在 python 2.7.5 中启动一个脚本,然后继续执行该脚本。 我试过用 #!python2.7.5 和http://re
我在 python 命令行(使用 python 2.7)中,并尝试运行 Python 脚本。我的操作系统是 Windows 7。我已将我的目录设置为包含我所有脚本的文件夹,使用: os.chdir("
剧透:部分解决(见最后)。 以下是使用 Python 嵌入的代码示例: #include int main(int argc, char** argv) { Py_SetPythonHome
假设我有以下列表,对应于及时的股票价格: prices = [1, 3, 7, 10, 9, 8, 5, 3, 6, 8, 12, 9, 6, 10, 13, 8, 4, 11] 我想确定以下总体上最
所以我试图在选择某个单选按钮时更改此框架的背景。 我的框架位于一个类中,并且单选按钮的功能位于该类之外。 (这样我就可以在所有其他框架上调用它们。) 问题是每当我选择单选按钮时都会出现以下错误: co
我正在尝试将字符串与 python 中的正则表达式进行比较,如下所示, #!/usr/bin/env python3 import re str1 = "Expecting property name
考虑以下原型(prototype) Boost.Python 模块,该模块从单独的 C++ 头文件中引入类“D”。 /* file: a/b.cpp */ BOOST_PYTHON_MODULE(c)
如何编写一个程序来“识别函数调用的行号?” python 检查模块提供了定位行号的选项,但是, def di(): return inspect.currentframe().f_back.f_l
我已经使用 macports 安装了 Python 2.7,并且由于我的 $PATH 变量,这就是我输入 $ python 时得到的变量。然而,virtualenv 默认使用 Python 2.6,除
我只想问如何加快 python 上的 re.search 速度。 我有一个很长的字符串行,长度为 176861(即带有一些符号的字母数字字符),我使用此函数测试了该行以进行研究: def getExe
list1= [u'%app%%General%%Council%', u'%people%', u'%people%%Regional%%Council%%Mandate%', u'%ppp%%Ge
这个问题在这里已经有了答案: Is it Pythonic to use list comprehensions for just side effects? (7 个答案) 关闭 4 个月前。 告
我想用 Python 将两个列表组合成一个列表,方法如下: a = [1,1,1,2,2,2,3,3,3,3] b= ["Sun", "is", "bright", "June","and" ,"Ju
我正在运行带有最新 Boost 发行版 (1.55.0) 的 Mac OS X 10.8.4 (Darwin 12.4.0)。我正在按照说明 here构建包含在我的发行版中的教程 Boost-Pyth
学习 Python,我正在尝试制作一个没有任何第 3 方库的网络抓取工具,这样过程对我来说并没有简化,而且我知道我在做什么。我浏览了一些在线资源,但所有这些都让我对某些事情感到困惑。 html 看起来
我是一名优秀的程序员,十分优秀!