python 回归问题特征筛选

import statsmodels.formula.api as smf
import pandas as pd
 
def forward_selected(data, response):
    """前向逐步回归算法，源代码来自https://planspace.org/20150423-forward_selection_with_statsmodels/
    使用Adjusted R-squared来评判新加的参数是否提高回归中的统计显著性
    Linear model designed by forward selection.
    Parameters:
    -----------
    data : pandas DataFrame with all possible predictors and response
    response: string, name of response column in data
    Returns:
    --------
    model: an "optimal" fitted statsmodels linear model
           with an intercept
           selected by forward selection
           evaluated by adjusted R-squared
    """
    remaining = set(data.columns)
    remaining.remove(response)
    selected = []
    current_score, best_new_score = 0.0, 0.0
    while remaining and current_score == best_new_score:
        scores_with_candidates = []
        for candidate in remaining:
            formul