X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=norms.py;h=2c8eb70e0401b163ba1ecce6858aec82820b9d53;hb=36820d02361529d5327ad040432d0198b72baed2;hp=c9cafc4f718b05b697a20e4f8b5f55085336bc88;hpb=d86a492d92a9dfa8f27db824ac67acd641b24714;p=cipher-tools.git

diff --git a/norms.py b/norms.py
index c9cafc4..2c8eb70 100644
--- a/norms.py
+++ b/norms.py
@@ -1,4 +1,5 @@
 import collections
+from math import log10
 
 def normalise(frequencies):
     """Scale a set of frequencies so they sum to one
@@ -32,23 +33,9 @@ def euclidean_scale(frequencies):
     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
-    
-    >>> sorted(scale({1: 1, 2: 0}).items())
-    [(1, 1.0), (2, 0.0)]
-    >>> sorted(scale({1: 1, 2: 1}).items())
-    [(1, 1.0), (2, 1.0)]
-    >>> sorted(scale({1: 1, 2: 1, 3: 1}).items())
-    [(1, 1.0), (2, 1.0), (3, 1.0)]
-    >>> sorted(scale({1: 1, 2: 2, 3: 1}).items())
-    [(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()))
-    
+def identity_scale(frequencies):
+    return frequencies
+        
 
 def l2(frequencies1, frequencies2):
     """Finds the distances between two frequency profiles, expressed as dictionaries.
@@ -196,6 +183,14 @@ def cosine_distance(frequencies1, frequencies2):
     return 1 - (numerator / (length1 ** 0.5 * length2 ** 0.5))
 
 
+def log_pl(frequencies1, frequencies2):
+    return sum([frequencies2[l] * log10(frequencies1[l])  for l in frequencies1.keys()])
+
+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
     """