This directory contains following three files:

1. corpus_to_list.py - Takes corpus of words and gives top 100,000 words in decreasing order of their frequencies

2. find_test_case.py - Takes Hand Annotated Data File and Final Segmentation file by undivide++ and outputs a file "undivide_output.txt" which contains segmentation of words(as done by individe++) in test file(or hand annotated data) 

3. compare.py - Takes "undivide_output.txt" and "Hand Annotated Data File" and outputs "True Positives, False Positives and False Negatives"


How to execute?
-----------------

All the above python files execute well with Python 3.x only
To run:

python3 <filename>
Note that input files to the above programmes may be needed to be renamed before executing.

