make_synvec_feats_cv.py 文件源码

def fit_classifier(feat_dicts=None, y_true=None, weights=None):
    # clf = MultinomialNB()
    clf = LogisticRegression(class_weight='balanced')

    pipeline = Pipeline([
        ('vectorizer', DictVectorizer()),
        ('selection', VarianceThreshold()),
        ('classifier', clf)
    ])

    # cf. http://stackoverflow.com/questions/36205850/sklearn-pipeline-applying-sample-weights-after-applying-a-polynomial-feature-t
    pipeline.fit(feat_dicts, y_true, **{'classifier__sample_weight': weights})

    return pipeline