Basic Usage


>>> from wikipedia2vec import Wikipedia2Vec

>>> wiki2vec = Wikipedia2Vec.load(MODEL_FILE)

>>> wiki2vec.get_word_vector('the')
memmap([ 0.01617998, -0.03325786, -0.01397999, -0.00150471,  0.03237337,
...
       -0.04226106, -0.19677088, -0.31087297,  0.1071524 , -0.09824426], dtype=float32)

>>> wiki2vec.get_entity_vector('Scarlett Johansson')
memmap([-0.19793572,  0.30861306,  0.29620451, -0.01193621,  0.18228433,
...
        0.04986198,  0.24383858, -0.01466644,  0.10835337, -0.0697331 ], dtype=float32)

>>> wiki2vec.most_similar(wiki2vec.get_word('yoda'), 5)
[(<Word yoda>, 1.0),
 (<Entity Yoda>, 0.84333622),
 (<Word darth>, 0.73328167),
 (<Word kenobi>, 0.7328127),
 (<Word jedi>, 0.7223742)]

>>> wiki2vec.most_similar(wiki2vec.get_entity('Scarlett Johansson'), 5)
[(<Entity Scarlett Johansson>, 1.0),
 (<Entity Natalie Portman>, 0.75090045),
 (<Entity Eva Mendes>, 0.73651594),
 (<Entity Emma Stone>, 0.72868186),
 (<Entity Cameron Diaz>, 0.72390842)]