Upload New File

letters.py

+#!/usr/bin/env python
+
+letters = 'abcdefghijklmnopqrstuvwxyz '
+
+def file2prob(filename):
+    """
+    Read a file and return a dictionary of letters and
+    their probabilities
+    """
+    letter_dict  = { c: 0 for c in letters }
+    letter_total = 0
+
+    with open(filename, encoding="utf-8") as fp:
+        for c in fp.read():
+            if c.lower() not in letter_dict:
+                continue
+            letter_dict[c.lower()] += 1
+            letter_total += 1
+
+    probs = { c: letter_dict[c]/letter_total for c in letter_dict }
+    return probs
+
+def file2pairs(filename):
+    """
+    Read a file and return a dictionary of letters and
+    the probabilities of following letters. That is, the
+    conditional probability of a letter given its
+    predecessor.
+    """
+    letter_dict  = { c: { a: 0 for a in letters }
+                     for c in letters }
+    previous = None
+    with open(filename, encoding="utf-8") as fp:
+        for c in fp.read():
+            if c not in letter_dict:
+                continue
+            c = c.lower()
+            if previous is None:
+                previous = c
+                continue
+            letter_dict[previous][c] += 1
+            previous = c
+
+    probs = { c: { d: letter_dict[c][d]/sum(letter_dict[c].values())
+                   for d in letters } for c in letters }
+    return probs
+
+if __name__ == '__main__':
+    import sys
+    
+    if len(sys.argv) != 3:
+        print("Usage: %s filename letter" % sys.argv[0])
+        sys.exit(-1)
+        
+    filename = sys.argv[1]
+    letter = sys.argv[2]
+    
+    probs = file2prob(filename)
+    print(probs[letter])