53个技巧！老司机熬夜总结Python 实用和高性能技巧大集合！

import random
random.choices(seq, k=1)  # 长度为k的list，有放回采样
random.sample(seq, k)     # 长度为k的list，无放回采样

func = lambda y: x + y          # x的值在函数运行时被绑定
func = lambda y, x=x: x + y     # x的值在函数定义时被绑定

import copy
y = copy.copy(x)      # 只复制最顶层
y = copy.deepcopy(x)  # 复制所有嵌套部分

a = [1, 2, [3, 4]]

# Alias.
b_alias = a  
assert b_alias == a and b_alias is a

# Shallow copy.
b_shallow_copy = a[:]  
assert b_shallow_copy == a and b_shallow_copy is not a and b_shallow_copy[2] is a[2]

# Deep copy.
import copy
b_deep_copy = copy.deepcopy(a)  
assert b_deep_copy == a and b_deep_copy is not a and b_deep_copy[2] is not a[2]

x == y  # 两引用对象是否有相同值
x is y  # 两引用是否指向同一对象

type(a) == int      # 忽略面向对象设计中的多态特征
isinstance(a, int)  # 考虑了面向对象设计中的多态特征

str.find(sub, start=None, end=None); str.rfind(...)     # 如果找不到返回-1
str.index(sub, start=None, end=None); str.rindex(...)   # 如果找不到抛出ValueError异常

print(a[-1], a[-2], a[-3])
print(a[~0], a[~1], a[~2])

a = float('inf')
b = float('-inf')

a = True
b = False

if x is None:
    pass

a, b = b, a

if 0 < a < 5:
    pass

with open(file_path, 'rt', encoding='utf-8') as f:
   for line in f:
       print(line)       # 末尾的\n会保留

import os
os.path.join('usr', 'lib', 'local')

import subprocess
# 如果外部命令返回值非0，则抛出subprocess.CalledProcessError异常
result = subprocess.check_output(['cmd', 'arg1', 'arg2']).decode('utf-8')  
# 同时收集标准输出和标准错误
result = subprocess.check_output(['cmd', 'arg1', 'arg2'], stderr=subprocess.STDOUT).decode('utf-8')  
# 执行shell命令（管道、重定向等），可以使用shlex.quote()将参数双引号引起来
result = subprocess.check_output('grep python | wc > out', shell=True).decode('utf-8')

import csv
# 无header的读写
with open(name, 'rt', encoding='utf-8', newline='') as f:  # newline=''让Python不将换行统一处理
    for row in csv.reader(f):
        print(row[0], row[1])  # CSV读到的数据都是str类型
with open(name, mode='wt') as f:
    f_csv = csv.writer(f)
    f_csv.writerow(['symbol', 'change'])

# 有header的读写
with open(name, mode='rt', newline='') as f:
    for row in csv.DictReader(f):
        print(row['symbol'], row['change'])
with open(name, mode='wt') as f:
    header = ['symbol', 'change']
    f_csv = csv.DictWriter(f, header)
    f_csv.writeheader()
    f_csv.writerow({'symbol': xx, 'change': xx})

import sys
csv.field_size_limit(sys.maxsize)

f = csv.reader(f, delimiter='\t')

import itertools
itertools.islice(iterable, start=None, stop, step=None)
# islice('ABCDEF', 2, None) -> C, D, E, F

itertools.filterfalse(predicate, iterable)         # 过滤掉predicate为False的元素
# filterfalse(lambda x: x < 5, [1, 4, 6, 4, 1]) -> 6

itertools.takewhile(predicate, iterable)           # 当predicate为False时停止迭代
# takewhile(lambda x: x < 5, [1, 4, 6, 4, 1]) -> 1, 4

itertools.dropwhile(predicate, iterable)           # 当predicate为False时开始迭代
# dropwhile(lambda x: x < 5, [1, 4, 6, 4, 1]) -> 6, 4, 1

itertools.compress(iterable, selectors)            # 根据selectors每个元素是True或False进行选择
# compress('ABCDEF', [1, 0, 1, 0, 1, 1]) -> A, C, E, F

sorted(iterable, key=None, reverse=False)

itertools.groupby(iterable, key=None)              # 按值分组，iterable需要先被排序
# groupby(sorted([1, 4, 6, 4, 1])) -> (1, iter1), (4, iter4), (6, iter6)

itertools.permutations(iterable, r=None)           # 排列，返回值是Tuple
# permutations('ABCD', 2) -> AB, AC, AD, BA, BC, BD, CA, CB, CD, DA, DB, DC

itertools.combinations(iterable, r=None)           # 组合，返回值是Tuple
itertools.combinations_with_replacement(...)
# combinations('ABCD', 2) -> AB, AC, AD, BC, BD, CD

itertools.chain(*iterables)                        # 多个序列直接拼接
# chain('ABC', 'DEF') -> A, B, C, D, E, F

import heapq
heapq.merge(*iterables, key=None, reverse=False)   # 多个序列按顺序拼接
# merge('ABF', 'CDE') -> A, B, C, D, E, F

zip(*iterables)                                    # 当最短的序列耗尽时停止，结果只能被消耗一次
itertools.zip_longest(*iterables, fillvalue=None)  # 当最长的序列耗尽时停止，结果只能被消耗一次

import collections
# 创建
collections.Counter(iterable)

# 频次
collections.Counter[key]                 # key出现频次
# 返回n个出现频次最高的元素和其对应出现频次，如果n为None，返回所有元素
collections.Counter.most_common(n=None)

# 插入/更新
collections.Counter.update(iterable)
counter1 + counter2; counter1 - counter2  # counter加减

# 检查两个字符串的组成元素是否相同
collections.Counter(list1) == collections.Counter(list2)

import collections
collections.defaultdict(type)  # 当第一次访问dict[key]时，会无参数调用type，给dict[key]提供一个初始值

import collections
collections.OrderedDict(items=None)  # 迭代时保留原始插入顺序

import sys
sys.stderr.write('')

import warnings
warnings.warn(message, category=UserWarning)  
# category的取值有DeprecationWarning, SyntaxWarning, RuntimeWarning, ResourceWarning, FutureWarning

$ python -W all     # 输出所有警告，等同于设置warnings.simplefilter('always')
$ python -W ignore  # 忽略所有警告，等同于设置warnings.simplefilter('ignore')
$ python -W error   # 将所有警告转换为异常，等同于设置warnings.simplefilter('error')

# 在代码中的debug部分
if __debug__:
    pass

$ python -0 main.py

pylint main.py

$ python -m cProfile main.py

# 代码块耗时定义
from contextlib import contextmanager
from time import perf_counter

@contextmanager
def timeblock(label):
    tic = perf_counter()
    try:
        yield
    finally:
        toc = perf_counter()
        print('%s : %s' % (label, toc - tic))

# 代码块耗时测试
with timeblock('counting'):
    pass

items = [2, 1, 3, 4]
argmin = min(range(len(items)), key=items.__getitem__)

A = [['a11', 'a12'], ['a21', 'a22'], ['a31', 'a32']]
A_transpose = list(zip(*A))  # list of tuple
A_transpose = list(list(col) for col in zip(*A))  # list of list

A = [1, 2, 3, 4, 5, 6]

# Preferred.
list(zip(*[iter(A)] * 2))