enron_poi_ml_ci.py 文件源码

def transform_pca(clf_list):
    '''
    From classifier list to pipeline list of the same classifiers and PCA.
    '''

    pca = PCA()
    params_pca = {"pca__n_components":[2, 3, 4, 5, 10, 15, 20], "pca__whiten": [False]}

    for j in range(len(clf_list)):

        name = "clf_" + str(j)
        clf, params = clf_list[j]

        # Parameters in GridSearchCV need to have double underscores
        # between specific classifiers.
        new_params = {}
        for key, value in params.iteritems():
            new_params[name + "__" + key] = value

        new_params.update(params_pca)
        clf_list[j] = (Pipeline([("pca", pca), (name, clf)]), new_params)

    return clf_list