Method evaluate

matchzoo/engine/base_model.py:279–338

Evaluate the model. :param x: Input data. :param y: Labels. :param batch_size: Number of samples when `predict` for evaluation. (default: 128) Examples:: >>> import matchzoo as mz >>> data_pack = mz.datasets.toy.load_data

(
        self,
        x: typing.Dict[str, np.ndarray],
        y: np.ndarray,
        batch_size: int = 128
    )

        )

    def evaluate(
        self,
        x: typing.Dict[str, np.ndarray],
        y: np.ndarray,
        batch_size: int = 128
    ) -> typing.Dict[BaseMetric, float]:
        """
        Evaluate the model.

        :param x: Input data.
        :param y: Labels.
        :param batch_size: Number of samples when `predict` for evaluation.
            (default: 128)

        Examples::
            >>> import matchzoo as mz
            >>> data_pack = mz.datasets.toy.load_data()
            >>> preprocessor = mz.preprocessors.NaivePreprocessor()
            >>> data_pack = preprocessor.fit_transform(data_pack, verbose=0)
            >>> m = mz.models.DenseBaseline()
            >>> m.params['task'] = mz.tasks.Ranking()
            >>> m.params['task'].metrics = [
            ...     'acc', 'mse', 'mae', 'ce',
            ...     'average_precision', 'precision', 'dcg', 'ndcg',
            ...     'mean_reciprocal_rank', 'mean_average_precision', 'mrr',
            ...     'map', 'MAP',
            ...     mz.metrics.AveragePrecision(threshold=1),
            ...     mz.metrics.Precision(k=2, threshold=2),
            ...     mz.metrics.DiscountedCumulativeGain(k=2),
            ...     mz.metrics.NormalizedDiscountedCumulativeGain(
            ...         k=3, threshold=-1),
            ...     mz.metrics.MeanReciprocalRank(threshold=2),
            ...     mz.metrics.MeanAveragePrecision(threshold=3)
            ... ]
            >>> m.guess_and_fill_missing_params(verbose=0)
            >>> m.build()
            >>> m.compile()
            >>> x, y = data_pack.unpack()
            >>> evals = m.evaluate(x, y)
            >>> type(evals)
            <class 'dict'>

        """
        result = dict()
        matchzoo_metrics, keras_metrics = self._separate_metrics()
        y_pred = self.predict(x, batch_size)

        for metric in keras_metrics:
            metric_func = keras.metrics.get(metric)
            result[metric] = K.eval(K.mean(
                metric_func(K.variable(y), K.variable(y_pred))))

        if matchzoo_metrics:
            if not isinstance(self.params['task'], tasks.Ranking):
                raise ValueError("Matchzoo metrics only works on ranking.")
            for metric in matchzoo_metrics:
                result[metric] = self._eval_metric_on_data_frame(
                    metric, x['id_left'], y, y_pred)