gistfile1.txt

In [19]: from sklearn.preprocessing import StandardScaler

In [20]: from sklearn.linear_model import LogisticRegression

In [21]: from sklearn.pipeline import Pipeline

In [22]: p = Pipeline([("scaler", StandardScaler()), ("classifier", LogisticRegression())])

In [23]: import numpy as np

In [24]: p.fit([[0., 1.], [1., 0.]], [0, 1])
Out[24]: 
Pipeline(steps=[('scaler', StandardScaler()),
                ('classifier', LogisticRegression())])

In [25]: p.fit([[0., 1.], [1., 0.]], [0, 1], sample_weight=[1., 1.])
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-25-62be8b6c7725> in <module>
----> 1 p.fit([[0., 1.], [1., 0.]], [0, 1], sample_weight=[1., 1.])

~/code/scikit-learn/sklearn/pipeline.py in fit(self, X, y, **fit_params)
    333             This estimator
    334         """
--> 335         fit_params_steps = self._check_fit_params(**fit_params)
    336         Xt = self._fit(X, y, **fit_params_steps)
    337         with _print_elapsed_time('Pipeline',

~/code/scikit-learn/sklearn/pipeline.py in _check_fit_params(self, **fit_params)
    247         for pname, pval in fit_params.items():
    248             if '__' not in pname:
--> 249                 raise ValueError(
    250                     "Pipeline.fit does not accept the {} parameter. "
    251                     "You can pass parameters to specific steps of your "

ValueError: Pipeline.fit does not accept the sample_weight 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)`.

In [26]: p.fit([[0., 1.], [1., 0.]], [0, 1], classifier__sample_weight=[1., 1.])
Out[26]: 
Pipeline(steps=[('scaler', StandardScaler()),
                ('classifier', LogisticRegression())])