Created
September 4, 2020 14:33
-
-
Save pranjalAI/0c343e49b0fdfc3cf953d49a4ce446c3 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
| def tokenized_data(questions,answers,VOCAB_SIZE,tokenizer): | |
| # encoder_input_data | |
| import numpy as np | |
| tokenized_questions = tokenizer.texts_to_sequences( questions ) | |
| maxlen_questions = max( [ len(x) for x in tokenized_questions ] ) | |
| padded_questions = preprocessing.sequence.pad_sequences( tokenized_questions , maxlen=maxlen , padding='post' ) | |
| encoder_input_data = np.array( padded_questions ) | |
| #print( encoder_input_data.shape , maxlen_questions ) | |
| # decoder_input_data | |
| tokenized_answers = tokenizer.texts_to_sequences( answers ) | |
| maxlen_answers = max( [ len(x) for x in tokenized_answers ] ) | |
| padded_answers = preprocessing.sequence.pad_sequences( tokenized_answers , maxlen=maxlen , padding='post' ) | |
| decoder_input_data = np.array( padded_answers ) | |
| #print( decoder_input_data.shape , maxlen_answers ) | |
| # decoder_output_data | |
| tokenized_answers = tokenizer.texts_to_sequences( answers ) | |
| for i in range(len(tokenized_answers)) : | |
| tokenized_answers[i] = tokenized_answers[i][1:] # remove <start> take rest | |
| padded_answers = preprocessing.sequence.pad_sequences( tokenized_answers , maxlen=maxlen , padding='post' ) | |
| onehot_answers = utils.to_categorical( padded_answers , VOCAB_SIZE) | |
| decoder_output_data = np.array( onehot_answers ) | |
| #print( decoder_output_data.shape ) | |
| return [encoder_input_data,decoder_input_data,decoder_output_data,maxlen_answers] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment