bdc3fe70d33b85cfdaa5ed02ccfd60807ae4f1da,category_encoders/helmert.py,HelmertEncoder,fit_helmert_coding,#,213

Before Change

        if len(values) == 0:
            return pd.DataFrame()

        helmert_contrast_matrix = Helmert().code_without_intercept(values.get_values())
        df = pd.DataFrame(data=helmert_contrast_matrix.matrix,
                          columns=helmert_contrast_matrix.column_suffixes,
                          index=values.get_values())

        if handle_unknown == "return_nan":
            df.loc[-1] = np.nan
        elif handle_unknown == "value":
            df.loc[-1] = np.zeros(len(values) - 1)

        if handle_missing == "return_nan":
            df.loc[values.loc[np.nan]] = np.nan
        elif handle_missing == "value":
            df.loc[-2] = np.zeros(len(values) - 1)

        return df

    @staticmethod

After Change

        if handle_missing == "value":
            values = values[values > 0]

        values_to_encode = values.get_values()

        if len(values) < 2:
            return pd.DataFrame(index=values_to_encode)

        if handle_unknown == "indicator":
            values_to_encode = np.append(values_to_encode, -1)

        helmert_contrast_matrix = Helmert().code_without_intercept(values_to_encode)
        df = pd.DataFrame(data=helmert_contrast_matrix.matrix, index=values_to_encode,
                          columns=[str(col) + "_%d" % (i,) for i in
                                   range(len(helmert_contrast_matrix.column_suffixes))])

        if handle_unknown == "return_nan":
            df.loc[-1] = np.nan
        elif handle_unknown == "value":
            df.loc[-1] = np.zeros(len(values_to_encode) - 1)

        if handle_missing == "return_nan":
            df.loc[values.loc[np.nan]] = np.nan
        elif handle_missing == "value":
            df.loc[-2] = np.zeros(len(values_to_encode) - 1)

        return df

    @staticmethod

Instances