Created
September 1, 2020 03:44
-
-
Save rishisidhu/90fee8e695c6131402f5f7f5d6e4c69a to your computer and use it in GitHub Desktop.
Adding Padding to the tokenization process
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
from tensorflow.keras.preprocessing.text import Tokenizer | |
from tensorflow.keras.preprocessing.sequence import pad_sequences | |
#Let's add custom sentences | |
sentences = [ | |
"Apples are red", | |
"Apples are round", | |
"Oranges are round", | |
'Grapes are sour, oranges are sweet' | |
] | |
#Tokenize the sentences | |
myTokenizer = Tokenizer(num_words=100) | |
myTokenizer.fit_on_texts(sentences) | |
sequences = myTokenizer.texts_to_sequences(sentences) | |
#Padding | |
padded = pad_sequences(sequences, maxlen=len(sentences[3].split(" "))) | |
#Display the output | |
print("\nWord Index = " , myTokenizer.word_index) | |
print("\nSequences = " , sequences) | |
print("\nPadded Sequences:") | |
print(padded) | |
print("\nOriginal Sentences: \n",[x for x in myTokenizer.sequences_to_texts_generator(padded)]) | |
#Pre and Post Padding | |
padded = pad_sequences(sequences) | |
print("\nPre Padded Sequences:") | |
print(padded) | |
padded = pad_sequences(sequences, padding="post") | |
print("\nPost Padded Sequences:") | |
print(padded) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment