3
from spacy.en import English
from numpy import dot
from numpy.linalg import norm
parser = English()
# you can access known words from the parser's vocabulary
nasa = parser.vocab['NASA']
# cosine similarity
cosine = lambda v1, v2: dot(v1, v2)/(norm(v1) * norm(v2))
# gather all known words, take only the lowercased versions
allWords = list({w for w in parser.vocab if w.has_repvec and w.orth_.islower() and w.lower_ != "nasa"})
# sort by similarity to NASA
allWords.sort(key=lambda w: cosine(w.repvec, nasa.repvec))
allWords.reverse()
print("Top 10 most similar words to NASA:")
for word in allWords[:10]:
print(word.orth_)
例子問題我試圖運行上面的例子,但我得到以下錯誤:詞矢量在spacy
Traceback (most recent call last):
File "C:\Users\bulusu.kiran\Documents\WORK\nlp\wordVectors1.py", line 8, in <module>
nasa = parser.vocab['NASA']
File "spacy/vocab.pyx", line 330, in spacy.vocab.Vocab.__getitem__ (spacy/vocab.cpp:7708)
orth = id_or_string TypeError: an integer is required
是什麼原因造成這個錯誤?
你發佈的很好的例子,如果他們只有他們在他們的文檔中有這樣的事情.. – cardamom