C3W3 Assignment - seq_and_pad - error in dependency

Course Q&A TensorFlow Developer Professional Natural Language Processing in TensorFlow
1

I am working on the final assignment for C3W3 and all of my functions work as expected and return the correct test values except when running the seq_pad_and_truncate function I get an TypeError deep in one of the Keras dependency functions for pad_sequences

TypeError                                 Traceback (most recent call last)
<ipython-input-13-31226c891137> in <module>
      2 
      3 # Test your function
----> 4 train_pad_trunc_seq = seq_pad_and_trunc(train_sentences, tokenizer, PADDING, TRUNCATING, MAXLEN)
      5 val_pad_trunc_seq = seq_pad_and_trunc(val_sentences, tokenizer, PADDING, TRUNCATING, MAXLEN)
      6 

<ipython-input-12-523a330bbbe3> in seq_pad_and_trunc(sentences, tokenizer, padding, truncating, maxlen)
     19 
     20     # Convert sentences to sequences
---> 21     sequences = tokenizer.texts_to_sequences(sentences)
     22     # Pad the sequences using the correct padding, truncating and maxlen
     23     pad_trunc_sequences = pad_sequences(sequences, padding=padding, maxlen=maxlen, truncating=truncating)

/opt/conda/lib/python3.8/site-packages/keras_preprocessing/text.py in texts_to_sequences(self, texts)
    279             A list of sequences.
    280         """
--> 281         return list(self.texts_to_sequences_generator(texts))
    282 
    283     def texts_to_sequences_generator(self, texts):

/opt/conda/lib/python3.8/site-packages/keras_preprocessing/text.py in texts_to_sequences_generator(self, texts)
    315                 i = self.word_index.get(w)
    316                 if i is not None:
--> 317                     if num_words and i >= num_words:
    318                         if oov_token_index is not None:
    319                             vect.append(oov_token_index)

TypeError: '>=' not supported between instances of 'int' and 'tuple'
2

Please click my name and message your notebook as an attachment.

3

The way you’ve created the Tokenizer inside fit_tokenizer is incorrect. The 1st positional argument is num_words.