X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=norms.py;h=eb436c3b8163141a3ada1f1f02f8be741d6f47fb;hb=85bd2222f507edc70911107af43ba1b903fdd571;hp=36af6068a93100512aac1119339b312d5ab552e5;hpb=110896f257c618d6e8361487bed50a8d07a66d2e;p=cipher-tools.git

diff --git a/norms.py b/norms.py
index 36af606..eb436c3 100644
--- 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()))
 
@@ -159,18 +159,18 @@ def harmonic_mean(frequencies1, frequencies2):
     return len(frequencies1) / total
 
 
-def cosine_distance(frequencies1, frequencies2):
+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
-    -2.22044604...e-16
-    >>> cosine_distance({'a':2, 'b':2, 'c':2}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
-    -2.22044604...e-16
-    >>> cosine_distance({'a':0, 'b':2, 'c':0}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
-    0.4226497308...
-    >>> cosine_distance({'a':0, 'b':1}, {'a':1, 'b':1}) # doctest: +ELLIPSIS
-    0.29289321881...
+    >>> cosine_similarity({'a':1, 'b':1, 'c':1}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
+    1.0000000000...
+    >>> cosine_similarity({'a':2, 'b':2, 'c':2}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
+    1.0000000000...
+    >>> cosine_similarity({'a':0, 'b':2, 'c':0}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
+    0.5773502691...
+    >>> cosine_similarity({'a':0, 'b':1}, {'a':1, 'b':1}) # doctest: +ELLIPSIS
+    0.7071067811...
     """
     numerator = 0
     length1 = 0
@@ -178,22 +178,11 @@ def cosine_distance(frequencies1, frequencies2):
     for k in frequencies1:
         numerator += frequencies1[k] * frequencies2[k]
         length1 += frequencies1[k]**2
-    for k in frequencies2.keys():
-        length2 += frequencies2[k]
-    return 1 - (numerator / (length1 ** 0.5 * length2 ** 0.5))
+    for k in frequencies2:
+        length2 += frequencies2[k]**2
+    return numerator / (length1 ** 0.5 * length2 ** 0.5)
 
 
-def log_pl(frequencies1, frequencies2):
-    return sum([frequencies2[l] * log10(frequencies1[l]) for l in frequencies1])
-
-def inverse_log_pl(frequencies1, frequencies2):
-    return -log_pl(frequencies1, frequencies2)
-
-def index_of_coincidence(frequencies):
-    """Finds the (expected) index of coincidence given a set of frequencies
-    """
-    return sum([f ** 2 for f in frequencies.values()]) * len(frequencies.keys())
-
 
 if __name__ == "__main__":
     import doctest