如何在XGBRressor的MultiOutputRegressor上使用验证集

Question

我正在使用以下MultiOutputRegressor：

from xgboost import XGBRegressor
from sklearn.multioutput import MultiOutputRegressor
#Define the estimator
estimator = XGBRegressor(
objective = 'reg:squarederror'
)
# Define the model
my_model = MultiOutputRegressor(estimator = estimator, n_jobs = -1).fit(X_train, y_train)

我想使用验证集来评估XGBRgressor的性能，但我认为MultiOutputRegressor不支持将eval_set传递给拟合函数。

在这种情况下，如何使用验证集？是否有任何变通方法可以调整XGBRgressor以具有多个输出？

Answer 1

您可以尝试编辑MultiOutputRegressor对象的fit方法，如下所示：

from sklearn.utils.validation import _check_fit_params
from sklearn.base import is_classifier
from sklearn.utils.fixes import delayed
from joblib import Parallel
from sklearn.multioutput import _fit_estimator
class MyMultiOutputRegressor(MultiOutputRegressor):

def fit(self, X, y, sample_weight=None, **fit_params):
""" Fit the model to data.
Fit a separate model for each output variable.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
Data.
y : {array-like, sparse matrix} of shape (n_samples, n_outputs)
Multi-output targets. An indicator matrix turns on multilabel
estimation.
sample_weight : array-like of shape (n_samples,), default=None
Sample weights. If None, then samples are equally weighted.
Only supported if the underlying regressor supports sample
weights.
**fit_params : dict of string -> object
Parameters passed to the ``estimator.fit`` method of each step.
.. versionadded:: 0.23
Returns
-------
self : object
"""
if not hasattr(self.estimator, "fit"):
raise ValueError("The base estimator should implement"
" a fit method")
X, y = self._validate_data(X, y,
force_all_finite=False,
multi_output=True, accept_sparse=True)
if is_classifier(self):
check_classification_targets(y)
if y.ndim == 1:
raise ValueError("y must have at least two dimensions for "
"multi-output regression but has only one.")
if (sample_weight is not None and
not has_fit_parameter(self.estimator, 'sample_weight')):
raise ValueError("Underlying estimator does not support"
" sample weights.")
fit_params_validated = _check_fit_params(X, fit_params)
[(X_test, Y_test)] = fit_params_validated.pop('eval_set')
self.estimators_ = Parallel(n_jobs=self.n_jobs)(
delayed(_fit_estimator)(
self.estimator, X, y[:, i], sample_weight,
**fit_params_validated, eval_set=[(X_test, Y_test[:, i])])
for i in range(y.shape[1]))
return self

并将CCD_ 5传递给CCD_

fit_params = dict(
eval_set=[(X_test, Y_test)], 
early_stopping_rounds=10
)
model.fit(X_train, Y_train, **fit_params)