“““Build?an?np.array?from?some?glove?file?and?some?vocab?file

You?need?to?download?‘glove.840B.300d.txt‘?from
https://nlp.stanford.edu/projects/glove/?and?you?need?to?have?built
your?vocabulary?first?（Maybe?using?‘build_vocab.py‘）
“““

__author__?=?“Guillaume?Genthial“

from?pathlib?import?Path

import?numpy?as?np


if?__name__?==?‘__main__‘:
????#?Load?vocab
????with?Path（‘vocab.words.txt‘）.open（）?as?f:
????????word_to_idx?=?{line.strip（）:?idx?for?idx?line?in?enumerate（f）}
????size_vocab?=?len（word_to_idx）

????#?Array?of?zeros
????embeddings?=?np.zeros（（size_vocab?300））

????#?Get?relevant?glove?vectors
????found?=?0
????print（‘Reading?GloVe?file?（may?take?a?while）‘）
????with?Path（‘glove.840B.300d.txt‘）.open（）?as?f:
????????for?line_idx?line?in?enumerate（f）:
????????????if?line_idx?%?100000?==?0:
????????????????print（‘-?At?line?{}‘.format（line_idx））
????????????line?=?line.strip（）.split（）
????????????if?len（line）?!=?300?+?1:
????????????????continue
????????????word?=?line[0]
????????????embedding?=?line[1:]
????????????if?word?in?word_to_idx:
????????????????found?+=?1
????????????????word_idx?=?word_to_idx[word]
????????????????embeddings[word_idx]?=?embedding
????print（‘-?done.?Found?{}?vectors?for?{}?words‘.format（found?size_vocab））

????#?Save?np.array?to?file
????np.savez_compressed（‘glove.npz‘?embeddings=embeddings）

?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2018-10-10?03:03??tf_ner-master\
?????文件???????10763??2018-10-10?03:03??tf_ner-master\LICENSE
?????文件????????7383??2018-10-10?03:03??tf_ner-master\README.md
?????目錄???????????0??2018-10-10?03:03??tf_ner-master\data\
?????目錄???????????0??2018-10-10?03:03??tf_ner-master\data\example\
?????文件?????????206??2018-10-10?03:03??tf_ner-master\data\example\Makefile
?????文件????????1354??2018-10-10?03:03??tf_ner-master\data\example\build_glove.py
?????文件????????1960??2018-10-10?03:03??tf_ner-master\data\example\build_vocab.py
?????文件???????35951??2018-10-10?03:03??tf_ner-master\data\example\glove.npz
?????文件?????????156??2018-10-10?03:03??tf_ner-master\data\example\testa.tags.txt
?????文件?????????212??2018-10-10?03:03??tf_ner-master\data\example\testa.words.txt
?????文件?????????156??2018-10-10?03:03??tf_ner-master\data\example\testb.tags.txt
?????文件?????????212??2018-10-10?03:03??tf_ner-master\data\example\testb.words.txt
?????文件?????????156??2018-10-10?03:03??tf_ner-master\data\example\train.tags.txt
?????文件?????????212??2018-10-10?03:03??tf_ner-master\data\example\train.words.txt
?????文件??????????64??2018-10-10?03:03??tf_ner-master\data\example\vocab.chars.txt
?????文件??????????20??2018-10-10?03:03??tf_ner-master\data\example\vocab.tags.txt
?????文件?????????140??2018-10-10?03:03??tf_ner-master\data\example\vocab.words.txt
?????目錄???????????0??2018-10-10?03:03??tf_ner-master\images\
?????文件???????39578??2018-10-10?03:03??tf_ner-master\images\data.png
?????文件???????19599??2018-10-10?03:03??tf_ner-master\images\ner.png
?????目錄???????????0??2018-10-10?03:03??tf_ner-master\models\
?????目錄???????????0??2018-10-10?03:03??tf_ner-master\models\chars_conv_lstm_crf\
?????文件????????8866??2018-10-10?03:03??tf_ner-master\models\chars_conv_lstm_crf\main.py
?????文件????????1557??2018-10-10?03:03??tf_ner-master\models\chars_conv_lstm_crf\masked_conv.py
?????文件?????????315??2018-10-10?03:03??tf_ner-master\models\chars_conv_lstm_crf\metrics.py
?????目錄???????????0??2018-10-10?03:03??tf_ner-master\models\chars_conv_lstm_crf_ema\
?????文件???????10997??2018-10-10?03:03??tf_ner-master\models\chars_conv_lstm_crf_ema\main.py
?????文件????????1557??2018-10-10?03:03??tf_ner-master\models\chars_conv_lstm_crf_ema\masked_conv.py
?????文件?????????577??2018-10-10?03:03??tf_ner-master\models\chars_conv_lstm_crf_ema\metrics.py
?????目錄???????????0??2018-10-10?03:03??tf_ner-master\models\chars_lstm_lstm_crf\
............此處省略13個(gè)文件信息