Movie-Review-Sentiment-Analysis-LSTM-Pytorch

Movie-Review-Sentiment-Analysis-LSTM-Pytorch copied to clipboard

can't work at all

2

bugs everywhere.

libing125

Length of valid_x and length of valid_y is not same

1

https://github.com/lukysummer/Movie-Review-Sentiment-Analysis-LSTM-Pytorch/blob/587d35c6cb16b5e096014dc26766a340c3cc0ca4/sentiment_analysis_LSTM.py#L88 ``` valid_x, valid_y = padded_features[:train_cutoff : valid_cutoff], encoded_labels[train_cutoff : valid_cutoff] print(len(valid_x),len(valid_y)) ``` Output ``` (1, 5000) ``` Instead, it should be ``` valid_x, valid_y = padded_features[train_cutoff : valid_cutoff], encoded_labels[train_cutoff...

superryeti

There is a possible `keyError` while generating encoded review.

1

https://github.com/lukysummer/Movie-Review-Sentiment-Analysis-LSTM-Pytorch/blob/master/sentiment_analysis_LSTM.py#L38 ``` encoded_reviews = [[vocab_to_int[word] for word in review] for review in all_reviews] ``` here the variable `review` is a string. so `[vocab_to_int[word] for word in review] ` would generate...

superryeti

I was going through your code in detail. and trying to implement on my own sentiment analyzer. I noticed that you didn't use stemming. I was wondering why Great stuff...

superryeti

https://github.com/lukysummer/Movie-Review-Sentiment-Analysis-LSTM-Pytorch/blob/master/sentiment_analysis_LSTM.py#L35 ``` word_list = sorted(word_counts, keys = word_counts.get, reverse = True) ``` should be ``` word_list = sorted(word_counts, key = word_counts.get, reverse = True) ```

superryeti