示例#1
0
    def __getitem__(self, index):
        """
        Returns the _transformed_ item from the dataset

        Args:
            index (int):

        Returns:
            (tuple):
                * example (ndarray): vector representation of a training sample
                * label (string): the class label
                * length (int): the length (tokens) of the sentence
                * index (int): the index of the dataitem in the dataset.
                  It is useful for getting the raw input for visualizations.
        """
        sample, label = self.data[index], self.labels[index]

        # transform the sample and the label,
        # in order to feed them to the model
        sample = vectorize(sample, self.char2idx, self.max_length)

        if self.label_transformer is not None:
            label = self.label_transformer.transform(label)

        if isinstance(label, (list, tuple)):
            label = numpy.array(label)

        return sample, label, len(self.data[index]), index
示例#2
0
    def __getitem__(self, index):
        """
        Returns the _transformed_ item from the dataset

        Args:
            index (int):

        Returns:
            (tuple):
                * example (ndarray): vector representation of a training example
                * label (int): the class label
                * length (int): the length (tokens) of the sentence

        Examples:
            For an `index` where:
            ::
                self.data[index] = ['this', 'is', 'really', 'simple']
                self.target[index] = "neutral"

            the function will have to return return:
            ::
                example = [  533  3908  1387   649   0     0     0     0
                             0     0     0     0     0     0     0     0
                             0     0     0     0     0     0     0     0]
                label = 1
        """
        sample, label = self.data[index], self.labels[index]
        length = min(self.max_length, len(sample))
        sample = vectorize(sample, self.word2idx, self.max_length)
        return sample, label, length
示例#3
0
    def __getitem__(self, index):
        """
        Returns the _transformed_ item from the dataset

        Args:
            index (int):

        Returns:
            (tuple):
                * example (ndarray): vector representation of a training sample
                * label (string): the class label
                * length (int): the length (tokens) of the sentence
                * index (int): the index of the dataitem in the dataset.
                  It is useful for getting the raw input for visualizations.
        """
        sample, label = self.data[index], self.labels[index]

        # transform the sample and the label,
        # in order to feed them to the model
        sample = vectorize(sample, self.char2idx, self.max_length)

        if self.label_transformer is not None:
            label = self.label_transformer.transform(label)

        if isinstance(label, (list, tuple)):
            label = numpy.array(label)

        return sample, label, len(self.data[index]), index