shaswat-dharaiya / TUTC

The Ultimate Text Cleaner

TUTC (TOOTSY) - The Ultimate Text Cleaner

Features

1. Text Cleaning
2. Stop Word Removal

Text Cleaning

1. Round 0

• Upper case to lower case
• Remove contractions (Eg: I've -> I have)

2. Round 1

• Convert numerical numbers to textual numbers (Eg: 20 -> twenty)

3. Round 2

• Remove any kind of special characters
• Remove punctuations
• Remove all kinds of extra spaces
• Remove links

Stop Words

Stop words are words in a sentence that contribute very less to the meaning of the sentence. Eg: I am a boy gets converted to I boy where [am, a] are stop words and as we can see after removing it the meaning of the sentence doesn't detoriate.

Libraries used:

• num2words
• nltk