process.py 文件源码

def _prepare_data(self):
        """
        Subset the dataframe to the columns needed for estimation purposes, and add a constant.
        :return: pd.DataFrame
        """
        # Subset the data to the columns used in the model
        data = self.data[self.varlist].copy()
        data = data[pd.notnull(data)].reset_index(drop=True)

        # Mapping each variable name to a unique variable code, and renaming the columns in the data.)
        data.rename(columns=self._var_to_symb, inplace=True)

        # Adding a constant to the data.
        data["Cons"] = 1

        if self.options["logit"]:
            endog = data["y"]
            uniques = np.unique(endog)
            if len(uniques) != 2:
                raise ValueError(
                    "The dependent variable does not have exactly two distinct outcomes."
                    "Please provide another dataset or change the 'logit' option to 0")
            else:
                endog_logit = [0 if i == uniques[0] else 1 for i in endog]
            data["y"] = endog_logit
        return data