word_embedding_loader.saver package

loader module provides actual implementation of the file savers.

Warning

This is an internal implementation. API may change without notice in the future, so you should use word_embedding_loader.word_embedding.WordEmbedding

Submodules

word_embedding_loader.saver.glove module

Low level API for saving of word embedding file that was implemented in GloVe, Global Vectors for Word Representation, by Jeffrey Pennington, Richard Socher, Christopher D. Manning from Stanford NLP group.

word_embedding_loader.saver.glove.save(f, arr, vocab)

Save word embedding file.

Parameters:

• f (File) – File to write the vectors. File should be open for writing ascii.
• arr (numpy.array) – Numpy array with float dtype.
• vocab (iterable) – Each element is pair of a word (bytes) and arr index (int). Word should be encoded to str apriori.

word_embedding_loader.saver.word2vec_bin module

Low level API for loading of word embedding file that was implemented in word2vec, by Mikolov. This implementation is for word embedding file created with -binary 1 option.

word_embedding_loader.saver.word2vec_bin.save()

Refer to word_embedding_loader.saver.glove.save() for the API.

word_embedding_loader.saver.word2vec_text module

Low level API for saving of word embedding file that was implemented in word2vec, by Mikolov. This implementation is for word embedding file created with -binary 0 option (the default).

word_embedding_loader.saver.word2vec_text.save(f, arr, vocab)

Save word embedding file. Check word_embedding_loader.saver.glove.save() for the API.