def create_keyed_vector(old_keyed_vector, new_matrix):
vector_size = new_matrix.shape[1]
keyed_vector = KeyedVectors(vector_size)
keyed_vector.vector_size = vector_size
keyed_vector.vocab = old_keyed_vector.vocab
keyed_vector.index2word = old_keyed_vector.index2word
keyed_vector.vectors = new_matrix
assert (len(old_keyed_vector.vocab),
vector_size) == keyed_vector.vectors.shape
return keyed_vector
def apply_w2v_regression(model, regression):
"""Given a word2vec model and a linear regression, apply that regression to all the vectors
in the model.
::param model:: A gensim `KeyedVectors` or `Word2Vec` instance
::param regression:: A `sklearn.linear_model.LinearRegression` instance
::returns:: A gensim `KeyedVectors` instance
"""
aligned_model = KeyedVectors() # Word2Vec()
aligned_model.vocab = model.vocab.copy()
aligned_model.vector_size = model.vector_size
aligned_model.index2word = model.index2word
# aligned_model.reset_weights()
aligned_model.syn0 = regression.predict(model.syn0).astype(np.float32)
return aligned_model
def __create_keyed_vector(matrix, orig_vocab):
vocab = dict()
index_to_word = []
for word, word_id in sorted(orig_vocab.token2id.items(),
key=itemgetter(1)):
index_to_word.append(word)
vocab[word] = Vocab(index=word_id, count=orig_vocab.word_freq[word_id])
vector_size = matrix.shape[1]
keyed_vector = KeyedVectors(vector_size)
keyed_vector.vector_size = vector_size
keyed_vector.vocab = vocab
keyed_vector.index2word = index_to_word
keyed_vector.vectors = matrix
assert (len(vocab), vector_size) == keyed_vector.vectors.shape
return keyed_vector
