Source code for transformers.pipelines.text_classification

import numpy as np

from ..file_utils import add_end_docstrings, is_tf_available, is_torch_available
from .base import PIPELINE_INIT_ARGS, Pipeline


if is_tf_available():
    from ..models.auto.modeling_tf_auto import TF_MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING

if is_torch_available():
    from ..models.auto.modeling_auto import MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING


@add_end_docstrings(
    PIPELINE_INIT_ARGS,
    r"""
        return_all_scores (:obj:`bool`, `optional`, defaults to :obj:`False`):
            Whether to return all prediction scores or just the one of the predicted class.
    """,
)
class TextClassificationPipeline(Pipeline):
    """
    Text classification pipeline using any :obj:`ModelForSequenceClassification`. See the `sequence classification
    examples <../task_summary.html#sequence-classification>`__ for more information.

    This text classification pipeline can currently be loaded from :func:`~transformers.pipeline` using the following
    task identifier: :obj:`"sentiment-analysis"` (for classifying sequences according to positive or negative
    sentiments).

    If multiple classification labels are available (:obj:`model.config.num_labels >= 2`), the pipeline will run a
    softmax over the results. If there is a single label, the pipeline will run a sigmoid over the result.

    The models that this pipeline can use are models that have been fine-tuned on a sequence classification task. See
    the up-to-date list of available models on `huggingface.co/models
    <https://huggingface.co/models?filter=text-classification>`__.
    """

    def __init__(self, return_all_scores: bool = False, **kwargs):
        super().__init__(**kwargs)

        self.check_model_type(
            TF_MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING
            if self.framework == "tf"
            else MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING
        )

        self.return_all_scores = return_all_scores

    def __call__(self, *args, **kwargs):
        """
        Classify the text(s) given as inputs.

        Args:
            args (:obj:`str` or :obj:`List[str]`):
                One or several texts (or one list of prompts) to classify.

        Return:
            A list or a list of list of :obj:`dict`: Each result comes as list of dictionaries with the following keys:

            - **label** (:obj:`str`) -- The label predicted.
            - **score** (:obj:`float`) -- The corresponding probability.

            If ``self.return_all_scores=True``, one such dictionary is returned per label.
        """
        outputs = super().__call__(*args, **kwargs)

        if self.model.config.num_labels == 1:
            scores = 1.0 / (1.0 + np.exp(-outputs))
        else:
            scores = np.exp(outputs) / np.exp(outputs).sum(-1, keepdims=True)
        if self.return_all_scores:
            return [
                [{"label": self.model.config.id2label[i], "score": score.item()} for i, score in enumerate(item)]
                for item in scores
            ]
        else:
            return [
                {"label": self.model.config.id2label[item.argmax()], "score": item.max().item()} for item in scores
            ]