TextPhraseExtraction

Program to find the most used phrases in a text file

How to use

1. Place text corpus in txt file called Input.txt

2. Run phrase_extract.py

3. Enter size of the phrases(number of words per phrase.

4. Advanced options are aviliable for the following

   1. Soft delete - delete words found in the middle of phrases
   2. Hard replace - replace words.
   3. soft replace - replace the words that hard replace could not catch.
   4. Alternatively you can place words in a Delete.txt file prior to running the program

5. Outputs appear in Output.xls

Techniques Used

Regex ngrams