basic_dataset
=============

.. py:module:: topmost.data.basic_dataset



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



.. autoapisummary::


   topmost.data.basic_dataset.DocEmbedModel


   topmost.data.basic_dataset.RawDataset


   topmost.data.basic_dataset.BasicDataset





.. py:class:: DocEmbedModel(model: Union[str, callable] = 'all-MiniLM-L6-v2', device: str = 'cpu', verbose: bool = False)

   .. py:attribute:: verbose
      :value: False



   .. py:method:: encode(docs: List[str], convert_to_tensor: bool = False)


.. py:class:: RawDataset(docs, preprocess=None, batch_size=200, device='cpu', as_tensor=True, contextual_embed=False, pretrained_WE=False, doc_embed_model='all-MiniLM-L6-v2', embed_model_device=None, verbose=False)

   .. py:attribute:: train_data


   .. py:attribute:: train_texts


   .. py:attribute:: vocab


   .. py:attribute:: vocab_size


.. py:class:: BasicDataset(dataset_dir, batch_size=200, read_labels=False, as_tensor=True, contextual_embed=False, doc_embed_model='all-MiniLM-L6-v2', device='cpu')

   .. py:attribute:: vocab_size
      :value: 0



   .. py:method:: load_data(path, read_labels)