glm.py 文件源码

def _create_main_design(self, **kwargs):
        r"""
        Create design matrix for main effects
        Keyword Args:
            * *df* (``DataFrame``). specify a new dataframe to create
                design matrix from
        Returns:
            array_like: design matrix in sparse CSR format

        """
        df = kwargs.get('df', self.train_df)
        df.reset_index(drop=True, inplace=True)
        df['row_index'] = df.index
        df['intercept'] = 1.0  # assume intercept is always included

        id_cols = ['row_index']

        melted_df = pd.melt(df[id_cols + self.main_effects], id_cols)
        melted_df = melted_df.merge(self.main_map, on='variable')
        melted_df['col_index'] = melted_df['main_idx']
        row = melted_df.row_index
        col = melted_df.col_index
        data = melted_df.value
        return sparse.coo_matrix((data, (row, col)),
                                 shape=(max(row) + 1, max(col) + 1)).tocsr()