Created
November 8, 2020 08:44
-
-
Save Shivam-316/2e4977c67982fff1dc5ec53efc618640 to your computer and use it in GitHub Desktop.
This Function will do the required processing and tokenize text into vectors.
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
def preprocess_and_tokenize(language,vocab_size,oov_size,is_input=False,is_output=False): | |
if is_output: | |
lang=[] | |
for text in language: | |
lang.append('<sos> '+ text +' <eos>') | |
lang=np.array(lang) | |
else: | |
lang=language | |
tokenizer=keras.preprocessing.text.Tokenizer(vocab_size,oov_token=oov_size) | |
tokenizer.fit_on_texts(lang) | |
tensor=tokenizer.texts_to_sequences(lang) | |
if is_output: | |
tensor = tf.keras.preprocessing.sequence.pad_sequences(tensor,padding='post',value=0) | |
if is_input: | |
tensor = tf.keras.preprocessing.sequence.pad_sequences(tensor,padding='pre',value=0) | |
tensor=tensor[:,::-1] | |
return tensor,tokenizer |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment