google-research
49 строк · 1.4 Кб
1# coding=utf-8
2# Copyright 2024 The Google Research Authors.
3#
4# Licensed under the Apache License, Version 2.0 (the "License");
5# you may not use this file except in compliance with the License.
6# You may obtain a copy of the License at
7#
8# http://www.apache.org/licenses/LICENSE-2.0
9#
10# Unless required by applicable law or agreed to in writing, software
11# distributed under the License is distributed on an "AS IS" BASIS,
12# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13# See the License for the specific language governing permissions and
14# limitations under the License.
15
16"""Client for looking up word2vec Embeddings."""
17
18from typing import List
19
20from gensim.models import KeyedVectors
21import numpy as np
22
23
24class Word2VecClient(object):
25"""API for looking up word2vec vectors for words."""
26
27def __init__(self, path):
28self.path = path
29
30self.keyed_vectors = KeyedVectors.load_word2vec_format(path, binary=True)
31
32test_vec = self.keyed_vectors['test']
33assert test_vec is not None
34
35self.vec_len = len(test_vec)
36self.empty_vec = np.array([0.0] * self.vec_len)
37
38def lookup(self, words):
39"""Look up a list of words and return list of wordvecs."""
40res = []
41
42for word in words:
43try:
44vec = self.keyed_vectors[word]
45except KeyError:
46vec = self.empty_vec
47res.append(vec)
48
49return res
50