This is the python implementation of our label cleanser (which we ultimately ported to ruby.) In python, we use Levenshtein, but in ruby, we just JaroWinkler. The results are slightly different, so the thresholds had to be adjusted accordingly.

label_cleanser.py

from collections import namedtuple
from Levenshtein import ratio
from Levenshtein import distance
import re, csv, os

delimiter = ','
quotechar = '|'
quoting = csv.QUOTE_MINIMAL

BrandInfo = namedtuple('BrandInfo', 'model_text utqg_correlate')
TirelineInfo = namedtuple('TirelineInfo', 'tireline_text utqg_correlate')

debug = True

def padSingleDigit(s):
	"""
		(I ENDED UP NOT USING THIS)
		
		If the DOT id is not 2 digits, pad with a zero.
		This should only apply to an entity with and ID of 1-9
	"""
	s_o = s
	is_single_digit = None
	
	if len(s) != 2:
		rx = r'^(\d{1})'
		is_single_digit = re.findall(rx, s)
		if len(is_single_digit) == 1:
			s = str("0%s" % is_single_digit[0])
	
	if debug:
		print s_o, s, is_single_digit
		
	return s

def correlateLabel(s, label_set, scrutinize_suffixes=False):
	correlated = []
	CorrelateObject = namedtuple("CorrelateObject", "label lev_ratio lev_dist")
	pre_rx = r'.*\s(.{3,4})$'
	
	for label in label_set:		
		r = ratio(s.lower(), label.lower())
		d = distance(s.lower(), label.lower())
		if r >= 0.91:
			'''
				in some cases, we have to scrutinize our data for 
				false positives.  for instance, some manufacturers
				have multiple lines of a particular product 
				(i.e. Firestone GTX and Firestone GTA) so we have to
				sniff out these suffixes and compare them.
			'''
			if scrutinize_suffixes:
				s_prefix = re.findall(pre_rx, s.lower())
				l_prefix = re.findall(pre_rx, label.lower())
				
				if len(s_prefix) == 1 and len(l_prefix) == 1:
					if debug:
						print "s_suffix: %s | l_suffix: %s (%.9f)" % (s_prefix, l_prefix, ratio(s_prefix[0], l_prefix[0]))
	
					if ratio(s_prefix[0], l_prefix[0]) < 0.8:
						continue
			
			correlated.append(CorrelateObject(label, r, d))
	
	if len(correlated) > 0:
		max_val = max(c.lev_ratio for c in correlated)
		best_matches = [c for c in correlated if c.lev_ratio == max_val]
		
		if debug:
			if max_val >= 0.91 and max_val != 1:
				print "%s | %s | %s " % (s.upper(), best_matches[0].label.lower(), best_matches)
			
	
		return best_matches[0].label
	
	return s

if __name__ == "__main__":
	this_dir = os.path.abspath(__file__)
	par_dir = os.path.abspath(os.path.join(this_dir, os.pardir))
	data_dump = os.path.join(par_dir, 'data')
	
	utqg_info = None
	utqg_brands = None
	utqg_tirelines = None
	new_brand_info = None
	new_tireline_info = None
	
	'''
		open up utqg csv.
		we want the brand column (1) and tireline column (3).
	'''
	UTQGInfo = namedtuple('UTQGInfo', 'brand tireline')
	with open(os.path.join(data_dump, "UTQG_data.csv"), 'rU') as utqg_data:
		utqg_csv = csv.reader(utqg_data, delimiter=delimiter, quotechar=quotechar)
		utqg_info = [UTQGInfo(x[0].lower(), x[2].lower()) for x in utqg_csv]
		
		'''
			create unique sets of brand and tireline observations.
		'''
		utqg_brands = list(set([x.brand for x in utqg_info]))
		utqg_tirelines = list(set([x.tireline for x in utqg_info]))
			
	with open(os.path.join(data_dump, "FLAT_CMPL_TIRE_excel.csv"), 'rU') as cmpl_data:
		cmpl_csv = csv.reader(cmpl_data, delimiter=delimiter, quotechar=quotechar)
		
		new_brand_info = [BrandInfo(x[3], correlateLabel(x[3], utqg_brands)) for x in cmpl_csv]
		new_tireline_info = [TirelineInfo(x[4], correlateLabel(x[4], utqg_tirelines, scrutinize_suffixes=True)) for x in cmpl_csv]