The folder should contain: 
filwords.txt (our word-freq list)
disjoin.txt (our invalid characters list)
matra.txt (list of matras)
hindi-seg.txt (the segmented test corpus)
hindi-glued.txt (the agglutinated corpus)

1)Run agglutinate.py: creates a file hindi-glued.txt agglutinating the data in hindi-seg.txt
2)Run seg.py: returns the segmented and the actual sentences, along with the precision, recall and f-score

3)Run fil1.py: returns statistics of number of characters in a word
3)Run fil2.py: returns statistics of number of hindi-characters in a word

