X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=lettercount.py;fp=lettercount.py;h=0000000000000000000000000000000000000000;hb=92ae3192f1ac20bfefacbefa7c2d68f843553e80;hp=956eca1a5b2ba469d66c80612446726cdf8307d4;hpb=20aff345391c6ae2d00a55c586fda31f6f4315d5;p=cipher-training.git

diff --git a/lettercount.py b/lettercount.py
deleted file mode 100644
index 956eca1..0000000
--- a/lettercount.py
+++ /dev/null
@@ -1,13 +0,0 @@
-from language_models import sanitise
-import collections
-
-corpora = ['shakespeare.txt', 'sherlock-holmes.txt', 'war-and-peace.txt']
-counts = collections.Counter()
-
-for corpus in corpora:
-    text = sanitise(open(corpus).read())
-    counts.update(text)
-
-with open('count_1l.txt', 'w') as f:
-    for l, c in counts.most_common():
-        f.write("{}\t{}\n".format(l, c))