1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
|
from timeit import timeit
import math
import csv
iterations = 100000
reader = csv.DictReader(open('data/titledata.csv'), delimiter='|')
titles = [i['custom_title'] for i in reader]
title_blob = '\n'.join(titles)
cirque_strings = [
"cirque du soleil - zarkana - las vegas",
"cirque du soleil ",
"cirque du soleil las vegas",
"zarkana las vegas",
"las vegas cirque du soleil at the bellagio",
"zarakana - cirque du soleil - bellagio"
]
choices = [
"",
"new york yankees vs boston red sox",
"",
"zarakana - cirque du soleil - bellagio",
None,
"cirque du soleil las vegas",
None
]
mixed_strings = [
"Lorem Ipsum is simply dummy text of the printing and typesetting industry.",
"C\\'est la vie",
"Ça va?",
"Cães danados",
"\xacCamarões assados",
"a\xac\u1234\u20ac\U00008000"
]
common_setup = "from thefuzz import fuzz, utils; "
def print_result_from_timeit(stmt='pass', setup='pass', number=1000000):
"""
Clean function to know how much time took the execution of one statement
"""
units = ["s", "ms", "us", "ns"]
duration = timeit(stmt, setup, number=int(number))
avg_duration = duration / float(number)
thousands = int(math.floor(math.log(avg_duration, 1000)))
print("Total time: {:f}s. Average run: {:.3f}{}.".format(
duration, avg_duration * (1000 ** -thousands), units[-thousands]))
for s in mixed_strings + cirque_strings + choices:
print('Test full_process for: "%s"' % s)
print_result_from_timeit('utils.full_process(u\'%s\')' % s,
common_setup, number=iterations)
# benchmarking the core matching methods...
for s in cirque_strings:
print('Test fuzz.ratio for string: "%s"' % s)
print('-------------------------------')
print_result_from_timeit('fuzz.ratio(u\'cirque du soleil\', u\'%s\')' % s,
common_setup, number=iterations / 100)
for s in cirque_strings:
print('Test fuzz.partial_ratio for string: "%s"' % s)
print('-------------------------------')
print_result_from_timeit('fuzz.partial_ratio(u\'cirque du soleil\', u\'%s\')'
% s, common_setup, number=iterations / 100)
for s in cirque_strings:
print('Test fuzz.WRatio for string: "%s"' % s)
print('-------------------------------')
print_result_from_timeit('fuzz.WRatio(u\'cirque du soleil\', u\'%s\')' % s,
common_setup, number=iterations / 100)
print('Test process.extract(scorer = fuzz.QRatio) for string: "%s"' % s)
print('-------------------------------')
print_result_from_timeit('process.extract(u\'cirque du soleil\', choices, scorer = fuzz.QRatio)',
common_setup + " from thefuzz import process; import string,random; random.seed(18);"
" choices = [\'\'.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(30)) for s in range(5000)]",
number=10)
print('Test process.extract(scorer = fuzz.WRatio) for string: "%s"' % s)
print('-------------------------------')
print_result_from_timeit('process.extract(u\'cirque du soleil\', choices, scorer = fuzz.WRatio)',
common_setup + " from thefuzz import process; import string,random; random.seed(18);"
" choices = [\'\'.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(30)) for s in range(5000)]",
number=10)
# let me show you something
s = 'New York Yankees'
test = 'import functools\n'
test += 'title_blob = """%s"""\n' % title_blob
test += 'title_blob = title_blob.strip()\n'
test += 'titles = title_blob.split("\\n")\n'
print('Real world ratio(): "%s"' % s)
print('-------------------------------')
test += 'prepared_ratio = functools.partial(fuzz.ratio, "%s")\n' % s
test += 'titles.sort(key=prepared_ratio)\n'
print_result_from_timeit(test, common_setup, number=100)
|
