TypeError: ‘Word2Vec’ object is not subscriptable

Total
1
Shares

I am trying to build a Word2vec model but when I try to reshape the vector for tokens, I am getting this error. Any idea ?

wordvec_arrays = np.zeros((len(tokenized_tweet), 100)) 
for i in range(len(tokenized_tweet)):
    wordvec_arrays[i,:] = word_vector(tokenized_tweet[i], 100)
wordvec_df = pd.DataFrame(wordvec_arrays) 
wordvec_df.shape

---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-101-71156bf1c4a3> in <module>
      1 wordvec_arrays = np.zeros((len(tokenized_tweet), 100))
      2 for i in range(len(tokenized_tweet)):
----> 3     wordvec_arrays[i,:] = word_vector(tokenized_tweet[i], 100)
      4 wordvec_df = pd.DataFrame(wordvec_arrays)
      5 wordvec_df.shape

<ipython-input-100-e3a82e60af93> in word_vector(tokens, size)
      4     for word in tokens:
      5         try:
----> 6             vec += model_w2v[word].reshape((1, size))
      7             count += 1.
      8         except KeyError: # handling the case where the token is not in vocabulary

TypeError: 'Word2Vec' object is not subscriptable

Solution

As of Gensim 4.0 & higher, the Word2Vec model doesn’t support subscripted-indexed access (the ['...']') to individual words. (Previous versions would display a deprecation warning, Method will be removed in 4.0.0, use self.wv.getitem() instead, for such uses.)

So, when you want to access a specific word, do it via the Word2Vec model’s .wv property, which holds just the word-vectors, instead. So, your (unshown) word_vector() function should have its line highlighted in the error stack changed to:

vec += model_w2v.wv[word[.reshape((1, size))
Leave a Reply

Your email address will not be published. Required fields are marked *