X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=norms.py;h=66452940c376658e446bb704c7198ee1ace2be22;hb=3ba8a3b82ccec64a2939708f428354176af6746e;hp=36e7fa4440b41942386e550b4403d2bf7d59e058;hpb=74b5187560b137a68d8d4b8b7f510517dbf51d6a;p=cipher-training.git

diff --git a/norms.py b/norms.py
index 36e7fa4..6645294 100644
--- a/norms.py
+++ b/norms.py
@@ -1,10 +1,9 @@
-"""Define a variety of norms for finding distances between vectors"""
-
 import collections
+from math import log10
 
 def normalise(frequencies):
     """Scale a set of frequencies so they sum to one
-
+    
     >>> sorted(normalise({1: 1, 2: 0}).items())
     [(1, 1.0), (2, 0.0)]
     >>> sorted(normalise({1: 1, 2: 1}).items())
@@ -14,13 +13,13 @@ 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()])
-    return collections.defaultdict(int, ((k, v / length)
+    length = sum(f for f in frequencies.values())
+    return collections.defaultdict(int, ((k, v / length) 
         for (k, v) in frequencies.items()))
 
 def euclidean_scale(frequencies):
     """Scale a set of frequencies so they have a unit euclidean length
-
+    
     >>> sorted(euclidean_scale({1: 1, 2: 0}).items())
     [(1, 1.0), (2, 0.0)]
     >>> sorted(euclidean_scale({1: 1, 2: 1}).items()) # doctest: +ELLIPSIS
@@ -31,21 +30,17 @@ def euclidean_scale(frequencies):
     [(1, 0.408248...), (2, 0.81649658...), (3, 0.408248...)]
     """
     length = sum([f ** 2 for f in frequencies.values()]) ** 0.5
-    return collections.defaultdict(int, ((k, v / length)
+    return collections.defaultdict(int, ((k, v / length) 
         for (k, v) in frequencies.items()))
 
 def identity_scale(frequencies):
-    """Don't scale a set of frequencies. (For use when a function expects a
-    scaling function but you don't want to supply one.)
-    """
     return frequencies
         
 
 def l2(frequencies1, frequencies2):
-    """Finds the distances between two frequency profiles, expressed as
-    dictionaries.
+    """Finds the distances between two frequency profiles, expressed as dictionaries.
     Assumes every key in frequencies1 is also in frequencies2
-
+    
     >>> l2({'a':1, 'b':1, 'c':1}, {'a':1, 'b':1, 'c':1})
     0.0
     >>> l2({'a':2, 'b':2, 'c':2}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS
@@ -67,7 +62,7 @@ def l2(frequencies1, frequencies2):
 euclidean_distance = l2
 
 def l1(frequencies1, frequencies2):
-    """Finds the distances between two frequency profiles, expressed as
+    """Finds the distances between two frequency profiles, expressed as 
     dictionaries. Assumes every key in frequencies1 is also in frequencies2
 
     >>> l1({'a':1, 'b':1, 'c':1}, {'a':1, 'b':1, 'c':1})
@@ -87,7 +82,7 @@ def l1(frequencies1, frequencies2):
     return total
 
 def l3(frequencies1, frequencies2):
-    """Finds the distances between two frequency profiles, expressed as
+    """Finds the distances between two frequency profiles, expressed as 
     dictionaries. Assumes every key in frequencies1 is also in frequencies2
 
     >>> l3({'a':1, 'b':1, 'c':1}, {'a':1, 'b':1, 'c':1})
@@ -110,10 +105,10 @@ def l3(frequencies1, frequencies2):
     return total ** (1/3)
 
 def geometric_mean(frequencies1, frequencies2):
-    """Finds the geometric mean of the absolute differences between two
-    frequency profiles, expressed as dictionaries.
+    """Finds the geometric mean of the absolute differences between two frequency profiles, 
+    expressed as dictionaries.
     Assumes every key in frequencies1 is also in frequencies2
-
+    
     >>> geometric_mean({'a':2, 'b':2, 'c':2}, {'a':1, 'b':1, 'c':1})
     1
     >>> geometric_mean({'a':2, 'b':2, 'c':2}, {'a':1, 'b':1, 'c':1})
@@ -136,8 +131,8 @@ def geometric_mean(frequencies1, frequencies2):
     return total
 
 def harmonic_mean(frequencies1, frequencies2):
-    """Finds the harmonic mean of the absolute differences between two
-    frequency profiles, expressed as dictionaries.
+    """Finds the harmonic mean of the absolute differences between two frequency profiles, 
+    expressed as dictionaries.
     Assumes every key in frequencies1 is also in frequencies2
 
     >>> harmonic_mean({'a':2, 'b':2, 'c':2}, {'a':1, 'b':1, 'c':1})
@@ -165,8 +160,7 @@ def harmonic_mean(frequencies1, frequencies2):
 
 
 def cosine_similarity(frequencies1, frequencies2):
-    """Finds the distances between two frequency profiles, expressed as 
-    dictionaries.
+    """Finds the distances between two frequency profiles, expressed as dictionaries.
     Assumes every key in frequencies1 is also in frequencies2
 
     >>> cosine_similarity({'a':1, 'b':1, 'c':1}, {'a':1, 'b':1, 'c':1}) # doctest: +ELLIPSIS