Created
March 29, 2020 05:47
-
-
Save groverpr/9d6013f05ae0dca59cc86b8dc869cfcc to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
few_words = ['great', 'excellent', 'best', 'perfect', 'wonderful', 'well', | |
'fun', 'love', 'amazing', 'also', 'enjoyed', 'favorite', 'it', | |
'and', 'loved', 'highly', 'bit', 'job', 'today', 'beautiful', | |
'you', 'definitely', 'superb', 'brilliant', 'world', 'liked', | |
'still', 'enjoy', 'life', 'very', 'especially', 'see', 'fantastic', | |
'both', 'shows', 'good', 'may', 'terrific', 'heart', 'classic', | |
'will', 'enjoyable', 'beautifully', 'always', 'true', 'perfectly', | |
'surprised', 'think', 'outstanding', 'most', | |
'bad', 'worst', 'awful', 'waste', 'boring', 'poor', 'terrible', | |
'no', 'nothing', 'poorly', 'dull', 'horrible', 'script', 'stupid', | |
'worse', 'even', 'minutes', 'instead', 'fails', 'unfortunately', | |
'just', 'annoying', 'ridiculous', 'plot', 'money', 'supposed', | |
'avoid', 'mess', 'disappointing', 'disappointment', 'lame', 'crap', | |
'predictable', 'any', 'pointless', 'weak', 'badly', 'not', 'only', | |
'unless', 'looks', 'why', 'wasted', 'save', 'oh', 'attempt', | |
'problem', 'acting', 'lacks', 'seems'] | |
tok_embed = net1.embed.weight.list_data()[0].asnumpy() # extract weights of embedding matrix from network | |
# use token to index map from transformer to get token for each index in embedding matrix | |
tok_trans = transformer.named_steps['token2index'] | |
tok_embed_sub = tok_embed[[tok_trans.tok2idx[i] for i in few_words]] | |
# t-SNE (tune perplexity and n_iter for your purpose) | |
tsne = TSNE(perplexity=40, n_iter=1000,) | |
Y_char = tsne.fit_transform(tok_embed_sub) | |
# Matplotlib plot of 2D embeddings | |
fig, ax = plt.subplots(figsize=(10,10)) | |
ax.scatter(x=Y_char[:,0], y=Y_char[:,1], s=4) | |
ax.grid() | |
for i in range(Y_char.shape[0]): | |
txt = few_words[i] | |
ax.annotate(txt, (Y_char[i,0], Y_char[i,1]), fontsize=10) | |
_ = ax.set_title('t-SNE of Word Tokens') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment