X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=counts.py;fp=counts.py;h=2714db294760ebd524bebad4614813fef8e8e4a3;hb=19a359ab34be225b4ab7df3974368a2833d45648;hp=0000000000000000000000000000000000000000;hpb=382cdeb6aee9e799db696d84455b447e3cad778b;p=cipher-tools.git

diff --git a/counts.py b/counts.py
new file mode 100644
index 0000000..2714db2
--- /dev/null
+++ b/counts.py
@@ -0,0 +1,32 @@
+import norms
+import itertools
+import random
+import bisect
+import collections
+
+english_counts = collections.defaultdict(int)
+with open('count_1l.txt', 'r') as f:
+    for line in f:
+        (letter, count) = line.split("\t")
+        english_counts[letter] = int(count)
+normalised_english_counts = norms.normalise(english_counts)
+
+english_bigram_counts = collections.defaultdict(int)
+with open('count_2l.txt', 'r') as f:
+    for line in f:
+        (bigram, count) = line.split("\t")
+        english_bigram_counts[bigram] = int(count)
+normalised_english_bigram_counts = norms.normalise(english_bigram_counts)
+
+english_trigram_counts = collections.defaultdict(int)
+with open('count_3l.txt', 'r') as f:
+    for line in f:
+        (trigram, count) = line.split("\t")
+        english_trigram_counts[trigram] = int(count)
+normalised_english_trigram_counts = norms.normalise(english_trigram_counts)
+
+
+# choices, weights = zip(*weighted_choices)
+# cumdist = list(itertools.accumulate(weights))
+# x = random.random() * cumdist[-1]
+# choices[bisect.bisect(cumdist, x)]