Bits of tinkering

[cipher-training.git] / norms.py

diff --git a/norms.py b/norms.py
index 37fd3c93329aa018b31fdf7f9a944eb496c41d44..66452940c376658e446bb704c7198ee1ace2be22 100644 (file)
--- a/norms.py
+++ b/norms.py
@@ -13,7 +13,7 @@ def normalise(frequencies):
     >>> sorted(normalise({1: 1, 2: 2, 3: 1}).items())
     [(1, 0.25), (2, 0.5), (3, 0.25)]
     """
-    length = sum([f for f in frequencies.values()])
+    length = sum(f for f in frequencies.values())
     return collections.defaultdict(int, ((k, v / length) 
         for (k, v) in frequencies.items()))
 
@@ -163,13 +163,13 @@ def cosine_similarity(frequencies1, frequencies2):
     """Finds the distances between two frequency profiles, expressed as dictionaries.
     Assumes every key in frequencies1 is also in frequencies2
 
-    >>> cosine_distance({'a':1, 'b':1, 'c':1}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
+    >>> cosine_similarity({'a':1, 'b':1, 'c':1}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
     1.0000000000...
-    >>> cosine_distance({'a':2, 'b':2, 'c':2}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
+    >>> cosine_similarity({'a':2, 'b':2, 'c':2}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
     1.0000000000...
-    >>> cosine_distance({'a':0, 'b':2, 'c':0}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
+    >>> cosine_similarity({'a':0, 'b':2, 'c':0}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
     0.5773502691...
-    >>> cosine_distance({'a':0, 'b':1}, {'a':1, 'b':1}) # doctest: +ELLIPSIS
+    >>> cosine_similarity({'a':0, 'b':1}, {'a':1, 'b':1}) # doctest: +ELLIPSIS
     0.7071067811...
     """
     numerator = 0