numpy_ml.preprocessing.nlp.rst

Natural language processing

BytePairEncoder

.. autoclass:: numpy_ml.preprocessing.nlp.BytePairEncoder
        :members:
        :undoc-members:
        :inherited-members:

HuffmanEncoder

.. autoclass:: numpy_ml.preprocessing.nlp.HuffmanEncoder
        :members:
        :undoc-members:
        :inherited-members:

TFIDFEncoder

.. autoclass:: numpy_ml.preprocessing.nlp.TFIDFEncoder
        :members:
        :undoc-members:
        :inherited-members:

Vocabulary

.. autoclass:: numpy_ml.preprocessing.nlp.Vocabulary
        :members:
        :undoc-members:
        :inherited-members:

Token

.. autoclass:: numpy_ml.preprocessing.nlp.Token
        :members:
        :undoc-members:
        :inherited-members:

ngrams

.. autofunction:: numpy_ml.preprocessing.nlp.ngrams

remove_stop_words

.. autofunction:: numpy_ml.preprocessing.nlp.remove_stop_words

strip_punctuation

.. autofunction:: numpy_ml.preprocessing.nlp.strip_punctuation

tokenize_words

.. autofunction:: numpy_ml.preprocessing.nlp.tokenize_words

tokenize_whitespace

.. autofunction:: numpy_ml.preprocessing.nlp.tokenize_whitespace

tokenize_chars

.. autofunction:: numpy_ml.preprocessing.nlp.tokenize_chars

tokenize_bytes_raw

.. autofunction:: numpy_ml.preprocessing.nlp.tokenize_bytes_raw

bytes_to_chars

.. autofunction:: numpy_ml.preprocessing.nlp.bytes_to_chars