- >>> sorted(letter_frequencies('abcdefabc').items())
- [('a', 2), ('b', 2), ('c', 2), ('d', 1), ('e', 1), ('f', 1)]
- >>> sorted(letter_frequencies('the quick brown fox jumped over the lazy dog').items())
- [(' ', 8), ('a', 1), ('b', 1), ('c', 1), ('d', 2), ('e', 4), ('f', 1), ('g', 1), ('h', 2), ('i', 1), ('j', 1), ('k', 1), ('l', 1), ('m', 1), ('n', 1), ('o', 4), ('p', 1), ('q', 1), ('r', 2), ('t', 2), ('u', 2), ('v', 1), ('w', 1), ('x', 1), ('y', 1), ('z', 1)]
- >>> sorted(letter_frequencies('The Quick BROWN fox jumped! over... the (9lazy) DOG').items())
- [(' ', 8), ('!', 1), ('(', 1), (')', 1), ('.', 3), ('9', 1), ('B', 1), ('D', 1), ('G', 1), ('N', 1), ('O', 2), ('Q', 1), ('R', 1), ('T', 1), ('W', 1), ('a', 1), ('c', 1), ('d', 1), ('e', 4), ('f', 1), ('h', 2), ('i', 1), ('j', 1), ('k', 1), ('l', 1), ('m', 1), ('o', 2), ('p', 1), ('r', 1), ('t', 1), ('u', 2), ('v', 1), ('x', 1), ('y', 1), ('z', 1)]
- >>> sorted(letter_frequencies(sanitise('The Quick BROWN fox jumped! over... the (9lazy) DOG')).items())
- [('a', 1), ('b', 1), ('c', 1), ('d', 2), ('e', 4), ('f', 1), ('g', 1), ('h', 2), ('i', 1), ('j', 1), ('k', 1), ('l', 1), ('m', 1), ('n', 1), ('o', 4), ('p', 1), ('q', 1), ('r', 2), ('t', 2), ('u', 2), ('v', 1), ('w', 1), ('x', 1), ('y', 1), ('z', 1)]
- """
- counts = collections.defaultdict(int)
- for c in text:
- counts[c] += 1
- return counts
-
-
-def normalise_frequencies(frequencies):
- """Scale a set of letter frequenies so they add to 1
-
- >>> sorted(normalise_frequencies(letter_frequencies('abcdefabc')).items())
- [('a', 0.2222222222222222), ('b', 0.2222222222222222), ('c', 0.2222222222222222), ('d', 0.1111111111111111), ('e', 0.1111111111111111), ('f', 0.1111111111111111)]
- >>> sorted(normalise_frequencies(letter_frequencies('the quick brown fox jumped over the lazy dog')).items())
- [(' ', 0.18181818181818182), ('a', 0.022727272727272728), ('b', 0.022727272727272728), ('c', 0.022727272727272728), ('d', 0.045454545454545456), ('e', 0.09090909090909091), ('f', 0.022727272727272728), ('g', 0.022727272727272728), ('h', 0.045454545454545456), ('i', 0.022727272727272728), ('j', 0.022727272727272728), ('k', 0.022727272727272728), ('l', 0.022727272727272728), ('m', 0.022727272727272728), ('n', 0.022727272727272728), ('o', 0.09090909090909091), ('p', 0.022727272727272728), ('q', 0.022727272727272728), ('r', 0.045454545454545456), ('t', 0.045454545454545456), ('u', 0.045454545454545456), ('v', 0.022727272727272728), ('w', 0.022727272727272728), ('x', 0.022727272727272728), ('y', 0.022727272727272728), ('z', 0.022727272727272728)]
- >>> sorted(normalise_frequencies(letter_frequencies('The Quick BROWN fox jumped! over... the (9lazy) DOG')).items())
- [(' ', 0.1568627450980392), ('!', 0.0196078431372549), ('(', 0.0196078431372549), (')', 0.0196078431372549), ('.', 0.058823529411764705), ('9', 0.0196078431372549), ('B', 0.0196078431372549), ('D', 0.0196078431372549), ('G', 0.0196078431372549), ('N', 0.0196078431372549), ('O', 0.0392156862745098), ('Q', 0.0196078431372549), ('R', 0.0196078431372549), ('T', 0.0196078431372549), ('W', 0.0196078431372549), ('a', 0.0196078431372549), ('c', 0.0196078431372549), ('d', 0.0196078431372549), ('e', 0.0784313725490196), ('f', 0.0196078431372549), ('h', 0.0392156862745098), ('i', 0.0196078431372549), ('j', 0.0196078431372549), ('k', 0.0196078431372549), ('l', 0.0196078431372549), ('m', 0.0196078431372549), ('o', 0.0392156862745098), ('p', 0.0196078431372549), ('r', 0.0196078431372549), ('t', 0.0196078431372549), ('u', 0.0392156862745098), ('v', 0.0196078431372549), ('x', 0.0196078431372549), ('y', 0.0196078431372549), ('z', 0.0196078431372549)]
- >>> sorted(normalise_frequencies(letter_frequencies(sanitise('The Quick BROWN fox jumped! over... the (9lazy) DOG'))).items())
- [('a', 0.027777777777777776), ('b', 0.027777777777777776), ('c', 0.027777777777777776), ('d', 0.05555555555555555), ('e', 0.1111111111111111), ('f', 0.027777777777777776), ('g', 0.027777777777777776), ('h', 0.05555555555555555), ('i', 0.027777777777777776), ('j', 0.027777777777777776), ('k', 0.027777777777777776), ('l', 0.027777777777777776), ('m', 0.027777777777777776), ('n', 0.027777777777777776), ('o', 0.1111111111111111), ('p', 0.027777777777777776), ('q', 0.027777777777777776), ('r', 0.05555555555555555), ('t', 0.05555555555555555), ('u', 0.05555555555555555), ('v', 0.027777777777777776), ('w', 0.027777777777777776), ('x', 0.027777777777777776), ('y', 0.027777777777777776), ('z', 0.027777777777777776)]
- """
- total = sum(frequencies.values())
- return dict((k, v / total) for (k, v) in frequencies.items())
-
-def l2_norm(frequencies1, frequencies2):
- """Finds the distances between two frequency profiles, expressed as dictionaries.
- Assumes every key in frequencies1 is also in frequencies2