scikit_feature_selectors.py 文件源码

def format_selector(selector,data, target):
    x_train, x_test, y_train, y_test = data_splitting.get_train_test(data, target)

    # Fit the model
    data.drop(target, 1, inplace=True)  # Remove target feature
    selector.fit(x_train, y_train)

    # Retain the feature names
    features = selector.get_support(indices = True)  # Returns array of indexes of nonremoved features
    features = [column for column in data[features] if column != target]  # Gets feature names

    # Transform, Format, Return
    selector = pd.DataFrame(selector.transform(data))
    selector.columns = features
    return selector


# http://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.VarianceThreshold.html