#! /usr/bin/python import sys import csv from fuzzywuzzy import fuzz LIMIT=70 streetfilename = sys.argv[1] obsfilename = sys.argv[2] finalscore=dict() with open( obsfilename ) as f: csvreader=csv.reader( f, delimiter=";", quotechar='"' ) for obs in csvreader: with open( streetfilename ) as s: for street in s: score = fuzz.partial_ratio(street, obs[1] ) if ( score > LIMIT ): #print "<<"+street.strip('\n')+">>", obs[0], obs[1], score keyname = street.strip('\n').replace( ' ', '_' ) if( finalscore.has_key( keyname ) ): finalscore[keyname]+=1 else: finalscore[keyname]=1 for street, count in finalscore.items(): print street, count