Shirlly / clean_text

clean_text

This code is used to clean text with special symbols, especially for tweets.

Cleaning includes:

1. Remove urls
2. Remove hashtag sign #
3. Remove account sign @
4. Remove special symbols

Input:

text files in directory

Output:

the same filenames and data format as input data in output directory

Package version:

Python 2.7

Includes a Java version text clean file