mexca.text.sentiment
====================

.. py:module:: mexca.text.sentiment

.. autoapi-nested-parse::

   Extract sentiment from text.



Classes
-------

.. autoapisummary::

   mexca.text.sentiment.SentimentExtractor


Functions
---------

.. autoapisummary::

   mexca.text.sentiment.cli


Module Contents
---------------

.. py:class:: SentimentExtractor(model_name: Optional[str] = None, device: Optional[torch.device] = None)

   Extract sentiment from text.

   :param model_name: The name of the text sequence classification model on Hugging Face hub used for
                      sentiment prediction. By default `'cardiffnlp/twitter-xlm-roberta-base-sentiment'`.
   :type model_name: str, optional
   :param device: The device on which sentiment extraction is performed. If `None`, defaults to `'cpu'`.
   :type device: torch.device, optional, default=None

   .. attribute:: tokenizer

      The pretrained tokenizer for sequence classification.
      Loaded automatically from `model_name`.

      :type: transformers.PreTrainedTokenizer


   .. py:property:: classifier
      :type: transformers.XLMRobertaForSequenceClassification


      The pretrained sequence classification model for sentiment prediction.
      Loaded automatically from `model_name`.


   .. py:method:: apply(transcription: mexca.data.AudioTranscription, show_progress: bool = True) -> mexca.data.SentimentAnnotation

      Extract the sentiment from text.

      Iterates over the sentences in the audio transcription and predicts the sentiment
      (negative, neutral, positive).

      :param transcription: The transcription of the speech segments in the audio fie split into sentences.
                            Returned by `AudioTranscriber`.
      :type transcription: AudioTranscription
      :param show_progress: Whether a progress bar is displayed or not.
      :type show_progress: bool, optional, default=True

      :returns: An data class object with the positive, negative, and neutral sentiment scores
                for each sentence.
      :rtype: SentimentAnnotation



.. py:function:: cli()

   Command line interface for sentiment extraction.
   See `extract-sentiment -h` for details.