recommenders/models/vae/multinomial_vae.py [468:530]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def display_metrics(self):
        """Plots:
        1) Loss per epoch both for validation and train set
        2) NDCG@k per epoch of the validation set
        """
        # Plot setup
        plt.figure(figsize=(14, 5))
        sns.set(style="whitegrid")

        # Plot loss on the left graph
        plt.subplot(1, 2, 1)
        plt.plot(self.train_loss, color="b", linestyle="-", label="Train")
        plt.plot(self.val_loss, color="r", linestyle="-", label="Val")
        plt.title("\n")
        plt.xlabel("Epochs", size=14)
        plt.ylabel("Loss", size=14)
        plt.legend(loc="upper left")

        # Plot NDCG on the right graph
        plt.subplot(1, 2, 2)
        plt.plot(self.val_ndcg, color="r", linestyle="-", label="Val")
        plt.title("\n")
        plt.xlabel("Epochs", size=14)
        plt.ylabel("NDCG@k", size=14)
        plt.legend(loc="upper left")

        # Add title
        plt.suptitle("TRAINING AND VALIDATION METRICS HISTORY", size=16)
        plt.tight_layout(pad=2)

    def recommend_k_items(self, x, k, remove_seen=True):
        """Returns the top-k items ordered by a relevancy score.
        Obtained probabilities are used as recommendation score.

        Args:
            x (numpy.ndarray, int32): input click matrix.
            k (scalar, int32): the number of items to recommend.
        Returns:
            numpy.ndarray, float: A sparse matrix containing the top_k elements ordered by their score.
        """
        # return optimal model
        self.model.load_weights(self.save_path)

        # obtain scores
        score = self.model.predict(x)

        if remove_seen:
            # if true, it removes items from the train set by setting them to zero
            seen_mask = np.not_equal(x, 0)
            score[seen_mask] = 0
        # get the top k items
        top_items = np.argpartition(-score, range(k), axis=1)[:, :k]
        # get a copy of the score matrix
        score_c = score.copy()
        # set to zero the k elements
        score_c[np.arange(score_c.shape[0])[:, None], top_items] = 0
        # set to zeros all elements other then the k
        top_scores = score - score_c
        return top_scores

    def ndcg_per_epoch(self):
        """Returns the list of NDCG@k at each epoch."""
        return self.val_ndcg
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



recommenders/models/vae/standard_vae.py [426:491]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def display_metrics(self):
        """Plots:
        1) Loss per epoch both for validation and train sets
        2) NDCG@k per epoch of the validation set
        """
        # Plot setup
        plt.figure(figsize=(14, 5))
        sns.set(style="whitegrid")

        # Plot loss on the left graph
        plt.subplot(1, 2, 1)
        plt.plot(self.train_loss, color="b", linestyle="-", label="Train")
        plt.plot(self.val_loss, color="r", linestyle="-", label="Val")
        plt.title("\n")
        plt.xlabel("Epochs", size=14)
        plt.ylabel("Loss", size=14)
        plt.legend(loc="upper left")

        # Plot NDCG on the right graph
        plt.subplot(1, 2, 2)
        plt.plot(self.val_ndcg, color="r", linestyle="-", label="Val")
        plt.title("\n")
        plt.xlabel("Epochs", size=14)
        plt.ylabel("NDCG@k", size=14)
        plt.legend(loc="upper left")

        # Add title
        plt.suptitle("TRAINING AND VALIDATION METRICS HISTORY", size=16)
        plt.tight_layout(pad=2)

    def recommend_k_items(self, x, k, remove_seen=True):
        """Returns the top-k items ordered by a relevancy score.

        Obtained probabilities are used as recommendation score.

        Args:
            x (numpy.ndarray): Input click matrix, with `int32` values.
            k (scalar): The number of items to recommend.

        Returns:
            numpy.ndarray: A sparse matrix containing the top_k elements ordered by their score.

        """
        # return optimal model
        self.model.load_weights(self.save_path)

        # obtain scores
        score = self.model.predict(x)
        if remove_seen:
            # if true, it removes items from the train set by setting them to zero
            seen_mask = np.not_equal(x, 0)
            score[seen_mask] = 0
        # get the top k items
        top_items = np.argpartition(-score, range(k), axis=1)[:, :k]
        # get a copy of the score matrix
        score_c = score.copy()
        # set to zero the k elements
        score_c[np.arange(score_c.shape[0])[:, None], top_items] = 0
        # set to zeros all elements other then the k
        top_scores = score - score_c
        return top_scores

    def ndcg_per_epoch(self):
        """Returns the list of NDCG@k at each epoch."""

        return self.val_ndcg
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -