>>> 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()])
+ length = sum(f for f in frequencies.values())
return collections.defaultdict(int, ((k, v / length)
for (k, v) in frequencies.items()))
for k in frequencies1:
numerator += frequencies1[k] * frequencies2[k]
length1 += frequencies1[k]**2
- for k in frequencies2.keys():
+ for k in frequencies2:
length2 += frequencies2[k]**2
return numerator / (length1 ** 0.5 * length2 ** 0.5)