The main file is 

> unigram_code.py

It take hi_wordseg.txt as input, and when executed, gives the segmented result in "unigram.txt". The comparison code is in "comparison.py". It compares it with "hi-wseg-gt.txt".

The precison and recall are given in
"final".

They are

hits=1088
miss=62
precision=0.946086956522
recall=0.0539130434783
