More whitespace and line length tidying

[cipher-tools.git] / norms.py

diff --git a/norms.py b/norms.py
index 744cbe4d9d4336f574d7b0885fed973189acd7d9..f9fc1d73aebde753a52cf5038bfa6a85db2f54ed 100644 (file)
--- a/norms.py
+++ b/norms.py
@@ -13,7 +13,8 @@ def normalise(frequencies):
     [(1, 0.4082482904638631), (2, 0.8164965809277261), (3, 0.4082482904638631)]
    """
     length = sum([f ** 2 for f in frequencies.values()]) ** 0.5
-    return collections.defaultdict(int, ((k, v / length) for (k, v) in frequencies.items()))
+    return collections.defaultdict(int, ((k, v / length) 
+        for (k, v) in frequencies.items()))
 
 def scale(frequencies):
     """Scale a set of frequencies so the largest is 1
@@ -28,7 +29,8 @@ def scale(frequencies):
     [(1, 0.5), (2, 1.0), (3, 0.5)]
     """
     largest = max(frequencies.values())
-    return collections.defaultdict(int, ((k, v / largest) for (k, v) in frequencies.items()))
+    return collections.defaultdict(int, ((k, v / largest) 
+        for (k, v) in frequencies.items()))
     
 
 def l2(frequencies1, frequencies2):
@@ -96,6 +98,55 @@ def l3(frequencies1, frequencies2):
         total += abs(frequencies1[k] - frequencies2[k]) ** 3
     return total ** (1/3)
 
+def geometric_mean(frequencies1, frequencies2):
+    """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})
+    1
+    >>> geometric_mean({'a':2, 'b':2, 'c':2}, {'a':1, 'b':5, 'c':1})
+    3
+    >>> geometric_mean(normalise({'a':2, 'b':2, 'c':2}), normalise({'a':1, 'b':5, 'c':1}))
+    0.057022248808851934
+    >>> geometric_mean(normalise({'a':2, 'b':2, 'c':2}), normalise({'a':1, 'b':1, 'c':1}))
+    0.0
+    >>> geometric_mean(normalise({'a':2, 'b':2, 'c':2}), normalise({'a':1, 'b':1, 'c':0}))
+    0.009720703533656434
+    """
+    total = 1
+    for k in frequencies1.keys():
+        total *= abs(frequencies1[k] - frequencies2[k])
+    return total
+
+def harmonic_mean(frequencies1, frequencies2):
+    """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})
+    1.0
+    >>> harmonic_mean({'a':2, 'b':2, 'c':2}, {'a':1, 'b':1, 'c':1})
+    1.0
+    >>> harmonic_mean({'a':2, 'b':2, 'c':2}, {'a':1, 'b':5, 'c':1})
+    1.2857142857142858
+    >>> harmonic_mean(normalise({'a':2, 'b':2, 'c':2}), normalise({'a':1, 'b':5, 'c':1}))
+    0.3849001794597505
+    >>> harmonic_mean(normalise({'a':2, 'b':2, 'c':2}), normalise({'a':1, 'b':1, 'c':1}))
+    0
+    >>> harmonic_mean(normalise({'a':2, 'b':2, 'c':2}), normalise({'a':1, 'b':1, 'c':0}))
+    0.17497266360581604
+    """
+    total = 0
+    for k in frequencies1.keys():
+        if abs(frequencies1[k] - frequencies2[k]) == 0:
+            return 0
+        total += 1 / abs(frequencies1[k] - frequencies2[k])
+    return len(frequencies1) / total
+
+
 def cosine_distance(frequencies1, frequencies2):
     """Finds the distances between two frequency profiles, expressed as dictionaries.
     Assumes every key in frequencies1 is also in frequencies2