tanimoto.py

# not my code but very similar to what i'm trying to accomplish
"""
Formula:
  Na = number of set A elements
  Nb = number of set B elements
  Nc = number of common items

  T = Nc / (Na + Nb - Nc)
"""
def tanimoto(a, b):
    c = [v for v in a if v in b]
    return float(len(c)) / (len(a)+len(b)-len(c))

def name_compare(name1, name2):
    return tanimoto(name1, name2)


>>> name_compare("James Brown", "Brown, James")
0.91666666666666663
>>> name_compare("Berry Tsakala", "Bernard Tsakala")
0.75
>>>