kats/models/metalearner/get_metadata.py [333:373]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def _calc_mape(
        self,
        training_inputs: np.ndarray,
        predictions: np.ndarray,
        truth: np.ndarray,
        diffs: np.ndarray,
    ) -> float:
        logging.info("Calculating MAPE")
        return np.mean(np.abs((truth - predictions) / truth))

    def _calc_smape(
        self,
        training_inputs: np.ndarray,
        predictions: np.ndarray,
        truth: np.ndarray,
        diffs: np.ndarray,
    ) -> float:
        logging.info("Calculating SMAPE")
        return ((abs(truth - predictions) / (truth + predictions)).sum()) * (
            2.0 / truth.size
        )

    def _calc_mae(
        self,
        training_inputs: np.ndarray,
        predictions: np.ndarray,
        truth: np.ndarray,
        diffs: np.ndarray,
    ) -> float:
        logging.info("Calculating MAE")
        return diffs.mean()

    def _calc_mase(
        self,
        training_inputs: np.ndarray,
        predictions: np.ndarray,
        truth: np.ndarray,
        diffs: np.ndarray,
    ) -> float:
        # MASE = mean(|actual - forecast| / naiveError), where naiveError = 1/ (n-1) sigma^n_[i=2](|actual_[i] - actual_[i-1]|).
        logging.info("Calculating MASE")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



kats/utils/backtesters.py [183:234]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def _calc_mape(
        self,
        training_inputs: np.ndarray,
        predictions: np.ndarray,
        truth: np.ndarray,
        diffs: np.ndarray,
    ) -> float:
        """Calculates MAPE error."""

        logging.info("Calculating MAPE")
        return np.mean(np.abs((truth - predictions) / truth))

    def _calc_smape(
        self,
        training_inputs: np.ndarray,
        predictions: np.ndarray,
        truth: np.ndarray,
        diffs: np.ndarray,
    ) -> float:
        """Calculates SMAPE error."""

        logging.info("Calculating SMAPE")
        return ((abs(truth - predictions) / (truth + predictions)).sum()) * (
            2.0 / truth.size
        )

    def _calc_mae(
        self,
        training_inputs: np.ndarray,
        predictions: np.ndarray,
        truth: np.ndarray,
        diffs: np.ndarray,
    ) -> float:
        """Calculates MAE error."""

        logging.info("Calculating MAE")
        return diffs.mean()

    def _calc_mase(
        self,
        training_inputs: np.ndarray,
        predictions: np.ndarray,
        truth: np.ndarray,
        diffs: np.ndarray,
    ) -> float:
        """Calculates non-seasonal MASE error.

        mean(|actual - forecast| / naiveError), where
        naiveError = mean(|actual_[i] - actual_[i-1]|)
        """

        logging.info("Calculating MASE")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -