rnum = 0 for row in cur.execute('select * from assign'): (assignee, assignor) = (row[5], row[6]) assignor_toks = name_standardize_strong(assignor) assignee_toks = name_standardize_strong(assignee) word_match = 0 for tok in assignor_toks: if tok in assignee_toks: word_match += 1 word_match /= max(1.0, 0.5 * (len(assignor_toks) + len(assignee_toks))) match = word_match > 0.5 chunker.insert(*row) match_num += match rnum += 1 if rnum % 50000 == 0: print(rnum) # commit changes con.commit() con.close() # display summary print(match_num) print(rnum) print(rnum - match_num)