feat_regress.py 文件源码

def select_kbest_reg(data_frame, target, k=5):
    """
    Selecting K-Best features regression
    :param data_frame: A pandas dataFrame with the training data
    :param target: target variable name in DataFrame
    :param k: desired number of features from the data
    :returns feature_scores: scores for each feature in the data as 
    pandas DataFrame
    """
    feat_selector = SelectKBest(f_regression, k=k)
    _ = feat_selector.fit(data_frame.drop(target, axis=1), data_frame[target])

    feat_scores = pd.DataFrame()
    feat_scores["F Score"] = feat_selector.scores_
    feat_scores["P Value"] = feat_selector.pvalues_
    feat_scores["Support"] = feat_selector.get_support()
    feat_scores["Attribute"] = data_frame.drop(target, axis=1).columns

    return feat_scores