This folder contains following files:

1. Clean_corpus.txt - It has the commands to remove the english characters in the corpus and also the digits.
[Executing]: give your corpus name instead of filename in the command and run the commands sequentially.

2. Precision.py - Two files are required "undivide_output.txt" and "Hand Annotated List File", Precision, Recall and F-score are reported according to the number of hits,insertion and deletion.
[Executing]: Change the filenames in the code with the required files.
Thing to note here is that the format of the "Hand Annotated List File" should be same as that of the undivide++ output file.(i.e. there should be a colon after the word then the morphemes should be seperated by + and no extra spaces should be there.)
correct:: word:m1+m2+n3
wrong::	  word: m1 +m2 + m3

