drift_estimator.py 文件源码

def fit(self, df_train, df_test):

        """
        Computes the drift between the two datasets

        Parameters
        ----------
        df_train : pandas dataframe of shape = (n_train, p)
            The train set

        df_test : pandas dataframe of shape = (n_test, p)
            The test set

        Returns
        -------
        self : object
            Returns self.
        """

        df_train["target"] = 0
        df_test["target"] = 1

        self.__target = pd.concat((df_train.target, df_test.target),
                                  ignore_index=True)

        if self.stratify:
            self.__cv = StratifiedKFold(n_splits=self.n_folds,
                                        shuffle=True,
                                        random_state=self.random_state)
        else:
            self.__cv = KFold(n_splits=self.n_folds,
                              shuffle=True,
                              random_state=self.random_state)

        X_tmp = pd.concat((df_train, df_test),
                          ignore_index=True).drop(['target'], axis=1)

        self.__pred = cross_val_predict(estimator=self.estimator,
                                        X=X_tmp,
                                        y=self.__target,
                                        cv=self.__cv,
                                        method="predict_proba")[:,1]

        del df_train["target"]
        del df_test["target"]

        self.__fitOK = True

        return self