select_percentile_classification.py 文件源码

def fit(self, X, y):
        import scipy.sparse
        import sklearn.feature_selection

        self.preprocessor = sklearn.feature_selection.SelectPercentile(
            score_func=self.score_func,
                percentile=self.percentile)

        # Because the pipeline guarantees that each feature is positive,
        # clip all values below zero to zero
        if self.score_func == sklearn.feature_selection.chi2:
            if scipy.sparse.issparse(X):
                X.data[X.data<0] = 0.0
            else:
                X[X<0] = 0.0

        self.preprocessor.fit(X, y)
        return self