def testJaro(
self): # - - - - - - - - - - - - - - - - - - - - - - - - - - -
"""Test 'Jaro' approximate string comparator"""
for pair in self.string_pairs:
approx_str_value = stringcmp.jaro(pair[0], pair[1])
assert (isinstance(approx_str_value,float)), \
'"Jaro" does not return a floating point number for: '+str(pair)
assert (approx_str_value >= 0.0), \
'"Jaro" returns a negative number for: '+str(pair)
assert (approx_str_value <= 1.0), \
'"Jaro" returns a number larger than 1.0 for: '+str(pair)
approx_str_value_1 = stringcmp.jaro(pair[0], pair[1])
approx_str_value_2 = stringcmp.jaro(pair[1], pair[0])
assert (approx_str_value_1 == approx_str_value_2), \
'"Jaro" returns different values for pair and swapped pair: '+ \
str(pair)+': '+str(approx_str_value_1)+', '+ \
str(approx_str_value_2)
# Check for value 1.0 if the strings are the same
#
if (pair[0] == pair[1]):
assert (approx_str_value == 1.0), \
'"Jaro" does not return 1.0 if strings are equal: '+str(pair)
def testJaro(self): # - - - - - - - - - - - - - - - - - - - - - - - - - - -
"""Test 'Jaro' approximate string comparator"""
for pair in self.string_pairs:
approx_str_value = stringcmp.jaro(pair[0],pair[1])
assert (isinstance(approx_str_value,float)), \
'"Jaro" does not return a floating point number for: '+str(pair)
assert (approx_str_value >= 0.0), \
'"Jaro" returns a negative number for: '+str(pair)
assert (approx_str_value <= 1.0), \
'"Jaro" returns a number larger than 1.0 for: '+str(pair)
approx_str_value_1 = stringcmp.jaro(pair[0],pair[1])
approx_str_value_2 = stringcmp.jaro(pair[1],pair[0])
assert (approx_str_value_1 == approx_str_value_2), \
'"Jaro" returns different values for pair and swapped pair: '+ \
str(pair)+': '+str(approx_str_value_1)+', '+ \
str(approx_str_value_2)
# Check for value 1.0 if the strings are the same
#
if (pair[0] == pair[1]):
assert (approx_str_value == 1.0), \
'"Jaro" does not return 1.0 if strings are equal: '+str(pair)
def testWinkler(
self): # - - - - - - - - - - - - - - - - - - - - - - - - - -
"""Test 'Winkler' approximate string comparator"""
for pair in self.string_pairs:
approx_str_value = stringcmp.winkler(pair[0], pair[1])
assert isinstance(
approx_str_value, float
), '"Winkler" does not return a floating point number for:' + str(
pair)
assert (approx_str_value >= 0.0
), '"Winkler" returns a negative number for:' + str(pair)
assert (
approx_str_value <= 1.0
), '"Winkler" returns a number larger than 1.0 for:' + str(pair)
approx_str_value_1 = stringcmp.winkler(pair[0], pair[1])
approx_str_value_2 = stringcmp.winkler(pair[1], pair[0])
assert approx_str_value_1 == approx_str_value_2, (
'"Winkler" returns different values for pair and swapped ' +
"pair: " + str(pair) + ": " + str(approx_str_value_1) + ", " +
str(approx_str_value_2))
# Check for value 1.0 if the strings are the same
#
if pair[0] == pair[1]:
assert (
approx_str_value == 1.0
), '"Winkler" does not return 1.0 if strings are equal: ' + str(
pair)
# Winkler should always return a value equal to or larger than Jaro
#
approx_str_value_winkler = stringcmp.winkler(pair[0], pair[1])
approx_str_value_jaro = stringcmp.jaro(pair[0], pair[1])
assert (
approx_str_value_winkler >= approx_str_value_jaro
), '"Winkler" value smaller than "Jaro" value for:' + str(pair)
def testWinkler(self): # - - - - - - - - - - - - - - - - - - - - - - - - - -
"""Test 'Winkler' approximate string comparator"""
for pair in self.string_pairs:
approx_str_value = stringcmp.winkler(pair[0],pair[1])
assert (isinstance(approx_str_value,float)), \
'"Winkler" does not return a floating point number for:'+ \
str(pair)
assert (approx_str_value >= 0.0), \
'"Winkler" returns a negative number for:'+str(pair)
assert (approx_str_value <= 1.0), \
'"Winkler" returns a number larger than 1.0 for:'+str(pair)
approx_str_value_1 = stringcmp.winkler(pair[0],pair[1])
approx_str_value_2 = stringcmp.winkler(pair[1],pair[0])
assert (approx_str_value_1 == approx_str_value_2), \
'"Winkler" returns different values for pair and swapped ' + \
'pair: '+str(pair)+': '+str(approx_str_value_1)+', '+ \
str(approx_str_value_2)
# Check for value 1.0 if the strings are the same
#
if (pair[0] == pair[1]):
assert (approx_str_value == 1.0), \
'"Winkler" does not return 1.0 if strings are equal: '+str(pair)
# Winkler should always return a value equal to or larger than Jaro
#
approx_str_value_winkler = stringcmp.winkler(pair[0],pair[1])
approx_str_value_jaro = stringcmp.jaro(pair[0],pair[1])
assert (approx_str_value_winkler >= approx_str_value_jaro), \
'"Winkler" value smaller than "Jaro" value for:'+str(pair)
import time
import stringcmp
with open('TEST_DATA.csv', 'rb') as f_open:
msg = []
# data = [line.rstrip('\n\r').split(',') for line in f_open]
for line in f_open:
twoNames = line.rstrip('\n\r').split(',')
#print(twoNames)
s = '%13s,%13s,' % (twoNames[0], twoNames[1])
##------Jaro------##
start_time = time.time()
s += ' %.3f' % (stringcmp.jaro(twoNames[0], twoNames[1]))
time_used = time.time() - start_time
s += ' %.10f' % (time_used)
##------winkler------##
start_time1 = time.time()
s += ' %.3f' % (stringcmp.winkler(twoNames[0], twoNames[1]))
time_used1 = time.time() - start_time1
s += ' %.10f' % (time_used1)
##------qgram 1------##
start_time2 = time.time()
s += ' %.3f' % (stringcmp.qgram(twoNames[0], twoNames[1], 1))
time_used2 = time.time() - start_time2
s += ' %.10f' % (time_used2)
