我想比较不同以在Python中用不同的变量构建一个字符串:
>用于连接(称为’加’)
>使用%
>使用“”.join(列表)
>使用格式化功能
>使用“{0< attribute>}”.格式(对象)
我比较了3种类型的情景
>带有2个变量的字符串
>带有4个变量的字符串
>带有4个变量的字符串,每个变量使用两次
我每次测量100万次操作并且平均执行超过6次测量.我想出了以下时间:
在每个场景中,我得出以下结论
>连接似乎是最快的方法之一
>使用%格式化比使用格式化功能格式化要快得多
我认为格式比%好很多(例如在this question),%几乎已被弃用.
因此,我有几个问题:
>%真的比格式快吗?
>如果是这样,那为什么?
>为什么“{} {}”.format(var1,var2)比“{0.attribute1} {0.attribute2}”.格式(对象)更有效?
作为参考,我使用以下代码来测量不同的时序.
import time
def timing(f, n, show, *args):
if show: print f.__name__ + ":\t",
r = range(n/10)
t1 = time.clock()
for i in r:
f(*args); f(*args); f(*args); f(*args); f(*args); f(*args); f(*args); f(*args); f(*args); f(*args)
t2 = time.clock()
timing = round(t2-t1, 3)
if show: print timing
return timing
#Class
class values(object):
def __init__(self, a, b, c="", d=""):
self.a = a
self.b = b
self.c = c
self.d = d
def test_plus(a, b):
return a + "-" + b
def test_percent(a, b):
return "%s-%s" % (a, b)
def test_join(a, b):
return ''.join([a, '-', b])
def test_format(a, b):
return "{}-{}".format(a, b)
def test_formatC(val):
return "{0.a}-{0.b}".format(val)
def test_plus_long(a, b, c, d):
return a + "-" + b + "-" + c + "-" + d
def test_percent_long(a, b, c, d):
return "%s-%s-%s-%s" % (a, b, c, d)
def test_join_long(a, b, c, d):
return ''.join([a, '-', b, '-', c, '-', d])
def test_format_long(a, b, c, d):
return "{0}-{1}-{2}-{3}".format(a, b, c, d)
def test_formatC_long(val):
return "{0.a}-{0.b}-{0.c}-{0.d}".format(val)
def test_plus_long2(a, b, c, d):
return a + "-" + b + "-" + c + "-" + d + "-" + a + "-" + b + "-" + c + "-" + d
def test_percent_long2(a, b, c, d):
return "%s-%s-%s-%s-%s-%s-%s-%s" % (a, b, c, d, a, b, c, d)
def test_join_long2(a, b, c, d):
return ''.join([a, '-', b, '-', c, '-', d, '-', a, '-', b, '-', c, '-', d])
def test_format_long2(a, b, c, d):
return "{0}-{1}-{2}-{3}-{0}-{1}-{2}-{3}".format(a, b, c, d)
def test_formatC_long2(val):
return "{0.a}-{0.b}-{0.c}-{0.d}-{0.a}-{0.b}-{0.c}-{0.d}".format(val)
def test_plus_superlong(lst):
string = ""
for i in lst:
string += str(i)
return string
def test_join_superlong(lst):
return "".join([str(i) for i in lst])
def mean(numbers):
return float(sum(numbers)) / max(len(numbers), 1)
nb_times = int(1e6)
n = xrange(5)
lst_numbers = xrange(1000)
from collections import defaultdict
metrics = defaultdict(list)
list_functions = [
test_plus, test_percent, test_join, test_format, test_formatC,
test_plus_long, test_percent_long, test_join_long, test_format_long, test_formatC_long,
test_plus_long2, test_percent_long2, test_join_long2, test_format_long2, test_formatC_long2,
# test_plus_superlong, test_join_superlong,
]
val = values("123", "456", "789", "0ab")
for i in n:
for f in list_functions:
print ".",
name = f.__name__
if "formatC" in name:
t = timing(f, nb_times, False, val)
elif '_long' in name:
t = timing(f, nb_times, False, "123", "456", "789", "0ab")
elif '_superlong' in name:
t = timing(f, nb_times, False, lst_numbers)
else:
t = timing(f, nb_times, False, "123", "456")
metrics[name].append(t)
#Get Average
print "\n===AVERAGE OF TIMINGS==="
for f in list_functions:
name = f.__name__
timings = metrics[name]
print "{:>20}:\t{:0.5f}".format(name, mean(timings))
解决方法:
>是的,%字符串格式化比.format方法快
>最有可能(这可能有更好的解释),因为%是一个语法符号(因此快速执行),而.format涉及至少一个额外的方法调用
>因为属性值访问还涉及额外的方法调用,即. __getattr__
我使用各种格式化方法的timeit进行了稍微好一点的分析(在Python 3.6.0上),其结果如下(漂亮地用BeautifulTable打印) –
+-----------------+-------+-------+-------+-------+-------+--------+
| Type \ num_vars | 1 | 2 | 5 | 10 | 50 | 250 |
+-----------------+-------+-------+-------+-------+-------+--------+
| f_str_str | 0.306 | 0.064 | 0.106 | 0.183 | 0.737 | 3.422 |
+-----------------+-------+-------+-------+-------+-------+--------+
| f_str_int | 0.295 | 0.174 | 0.385 | 0.686 | 3.378 | 16.399 |
+-----------------+-------+-------+-------+-------+-------+--------+
| concat_str | 0.012 | 0.053 | 0.156 | 0.31 | 1.707 | 16.762 |
+-----------------+-------+-------+-------+-------+-------+--------+
| pct_s_str | 0.056 | 0.178 | 0.275 | 0.469 | 1.872 | 9.191 |
+-----------------+-------+-------+-------+-------+-------+--------+
| pct_s_int | 0.128 | 0.208 | 0.343 | 0.605 | 2.483 | 13.24 |
+-----------------+-------+-------+-------+-------+-------+--------+
| dot_format_str | 0.418 | 0.217 | 0.343 | 0.58 | 2.241 | 11.163 |
+-----------------+-------+-------+-------+-------+-------+--------+
| dot_format_int | 0.416 | 0.277 | 0.476 | 0.811 | 3.378 | 17.829 |
+-----------------+-------+-------+-------+-------+-------+--------+
| dot_format2_str | 0.433 | 0.242 | 0.416 | 0.675 | 3.152 | 16.783 |
+-----------------+-------+-------+-------+-------+-------+--------+
| dot_format2_int | 0.428 | 0.298 | 0.541 | 0.933 | 4.444 | 24.767 |
+-----------------+-------+-------+-------+-------+-------+--------+
尾随_str& _int表示对各个值类型执行的操作.
请注意,单个变量的concat_str结果基本上只是字符串本身,所以不应该考虑它.
我得到的结果 –
from timeit import timeit
from beautifultable import BeautifulTable # pip install beautifultable
times = {}
for num_vars in (1, 2, 5, 10, 50, 250):
f_str = "f'{" + '}{'.join([f'x{i}' for i in range(num_vars)]) + "}'"
# "f'{x0}{x1}"
concat = '+'.join([f'x{i}' for i in range(num_vars)])
# 'x0+x1'
pct_s = '"' + '%s'*num_vars + '" % (' + ','.join([f'x{i}' for i in range(num_vars)]) + ')'
# '"%s%s" % (x0,x1)'
dot_format = '"' + '{}'*num_vars + '".format(' + ','.join([f'x{i}' for i in range(num_vars)]) + ')'
# '"{}{}".format(x0,x1)'
dot_format2 = '"{' + '}{'.join([f'{i}' for i in range(num_vars)]) + '}".format(' + ','.join([f'x{i}' for i in range(num_vars)]) + ')'
# '"{0}{1}".format(x0,x1)'
vars = ','.join([f'x{i}' for i in range(num_vars)])
vals_str = tuple(map(str, range(num_vars)))
setup_str = f'{vars} = {vals_str}'
# "x0,x1 = ('0', '1')"
vals_int = tuple(range(num_vars))
setup_int = f'{vars} = {vals_int}'
# 'x0,x1 = (0, 1)'
times[num_vars] = {
'f_str_str': timeit(f_str, setup_str),
'f_str_int': timeit(f_str, setup_int),
'concat_str': timeit(concat, setup_str),
# 'concat_int': timeit(concat, setup_int), # this will be summation, not concat
'pct_s_str': timeit(pct_s, setup_str),
'pct_s_int': timeit(pct_s, setup_int),
'dot_format_str': timeit(dot_format, setup_str),
'dot_format_int': timeit(dot_format, setup_int),
'dot_format2_str': timeit(dot_format2, setup_str),
'dot_format2_int': timeit(dot_format2, setup_int),
}
table = BeautifulTable()
table.column_headers = ['Type \ num_vars'] + list(map(str, times.keys()))
# Order is preserved, so I didn't worry much
for key in ('f_str_str', 'f_str_int', 'concat_str', 'pct_s_str', 'pct_s_int', 'dot_format_str', 'dot_format_int', 'dot_format2_str', 'dot_format2_int'):
table.append_row([key] + [times[num_vars][key] for num_vars in (1, 2, 5, 10, 50, 250)])
print(table)
因为timeit的一些最大参数(255)限制,我无法超越num_vars = 250.
tl; dr – Python字符串格式化性能:f-strings最快,更优雅,但有时(由于某些implementation restrictions和仅为Py3.6),您可能必须使用其他格式化选项.
标签:python,performance
来源: https://codeday.me/bug/20191004/1854154.html