X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=segment.py;fp=segment.py;h=27bf103c573f0d228a03741ef34dd360138ad072;hb=6a89ca3a0906f12f0d3457642a235a4f9bc74ebf;hp=e4b019f4c8248d8647f938fea8295c132308de0b;hpb=792bef4fa890a8c834ddd83ab9a573d0e2a75dc9;p=cipher-tools.git diff --git a/segment.py b/segment.py index e4b019f..27bf103 100644 --- a/segment.py +++ b/segment.py @@ -58,7 +58,5 @@ def avoid_long_words(key, N): """ return -log10((N * 10**(len(key) - 2))) -# N = 1024908267229 ## Number of tokens - Pw = Pdist(datafile('count_1w.txt'), avoid_long_words)