Python：itertools模块

https://docs.python.org/zh-cn/3.7/library/itertools.html

>>> import itertools
>>> for i in itertools.product('ABCD', repeat = 2):
...     print i,
... 
('A', 'A') ('A', 'B') ('A', 'C') ('A', 'D') ('B', 'A') ('B', 'B') ('B', 'C') ('B', 'D') ('C', 'A') ('C', 'B') ('C', 'C') ('C', 'D') ('D', 'A') ('D', 'B') ('D', 'C') ('D', 'D')
>>> for i in itertools.permutations('ABCD', 2):
...     print i,
... 
('A', 'B') ('A', 'C') ('A', 'D') ('B', 'A') ('B', 'C') ('B', 'D') ('C', 'A') ('C', 'B') ('C', 'D') ('D', 'A') ('D', 'B') ('D', 'C')
>>> for i in itertools.combinations('ABCD', 2):
...     print i,
... 
('A', 'B') ('A', 'C') ('A', 'D') ('B', 'C') ('B', 'D') ('C', 'D')
>>> for i in itertools.combinations_with_replacement('ABCD', 2):
...     print i,
... 
('A', 'A') ('A', 'B') ('A', 'C') ('A', 'D') ('B', 'B') ('B', 'C') ('B', 'D') ('C', 'C') ('C', 'D') ('D', 'D')

1、Python itertools模块combinations(iterable, r)方法可以创建一个迭代器，返回iterable中所有长度为r的子序列，返回的子序列中的项按输入iterable中的顺序排序。

import itertools
list1 = [1, 3, 4, 5]
list2 = list(itertools.combinations(list1, 2))
print(list2)

返回结果：
[(1, 3), (1, 4), (1, 5), (3, 4), (3, 5), (4, 5)]

2、实现一组数据的所有排列组合

import itertools

list1 = [1, 3, 4, 5]
list2 = []
for i in range(1, len(list1)+1):
    iter1 = itertools.combinations(list1, i)
    list2.append(list(iter1))
print(list2)


返回结果：
[[(1,), (3,), (4,), (5,)], [(1, 3), (1, 4), (1, 5), (3, 4), (3, 5), (4, 5)], [(1, 3, 4), (1, 3, 5), (1, 4, 5), (3, 4, 5)], [(1, 3, 4, 5)]]

itertools.accumulate(iterable[, func ])

def accumulate(iterable, func=operator.add):
    'Return running totals'
    # accumulate([1,2,3,4,5]) --> 1 3 6 10 15
    # accumulate([1,2,3,4,5], operator.mul) --> 1 2 6 24 120
    it = iter(iterable)
    try:
        total = next(it)
    except StopIteration:
        return
    yield total
    for element in it:
        total = func(total, element)
        yield total


eg:
>>> data = [3, 4, 6, 2, 1, 9, 0, 7, 5, 8]
>>> list(accumulate(data, operator.mul)) # running product
[3, 12, 72, 144, 144, 1296, 0, 0, 0, 0]
>>> list(accumulate(data, max)) # running maximum
[3, 4, 6, 6, 6, 9, 9, 9, 9, 9]
# Amortize a 5% loan of 1000 with 4 annual payments of 90
>>> cashflows = [1000, -90, -90, -90, -90]
>>> list(accumulate(cashflows, lambda bal, pmt: bal*1.05 + pmt))
[1000, 960.0, 918.0, 873.9000000000001, 827.5950000000001]

itertools.chain 连接多个列表或者迭代器

>>> x = itertools.chain(range(3), range(4), [3,2,1])
>>> print(list(x))
[0, 1, 2, 0, 1, 2, 3, 3, 2, 1]

itertools.combinations 求列表或生成器中指定数目的元素不重复的所有组合

源码：
def combinations(iterable, r):
    # combinations('ABCD', 2) --> AB AC AD BC BD CD
    # combinations(range(4), 3) --> 012 013 023 123
    pool = tuple(iterable)
    n = len(pool)
    if r > n:
        return
    indices = list(range(r))
    yield tuple(pool[i] for i in indices)
    while True:
        for i in reversed(range(r)):
            if indices[i] != i + n - r:
                break
        else:
            return
        indices[i] += 1
        for j in range(i+1, r):
            indices[j] = indices[j-1] + 1
        yield tuple(pool[i] for i in indices)

def combinations(iterable, r):
    pool = tuple(iterable)
    n = len(pool)
    for indices in permutations(range(n), r):
        if sorted(indices) == list(indices):
            yield tuple(pool[i] for i in indices)

>>> x = itertools.combinations(range(4), 3)
>>> print(list(x))
[(0, 1, 2), (0, 1, 3), (0, 2, 3), (1, 2, 3)]

itertools.combinations_with_replacement(iterable, r) 允许重复元素的组合

>>> x = itertools.combinations_with_replacement('ABC', 2)
>>> print(list(x))
[('A', 'A'), ('A', 'B'), ('A', 'C'), ('B', 'B'), ('B', 'C'), ('C', 'C')]

itertools.permutations(iterable, r=None),输出输入序列的全排列
The number of items returned is n! / (n-r)! when 0 <= r <= n or zero when r > n.
根据序列位置进行全排列，而不是值，所以如果输入序列有重复值，输出亦会有

源码模拟：
def permutations(iterable, r=None):
    # permutations('ABCD', 2) --> AB AC AD BA BC BD CA CB CD DA DB DC
    # permutations(range(3)) --> 012 021 102 120 201 210
    pool = tuple(iterable)
    n = len(pool)
    r = n if r is None else r
    if r > n:
        return
    indices = list(range(n))
    cycles = list(range(n, n-r, -1))
    yield tuple(pool[i] for i in indices[:r])
    while n:
        for i in reversed(range(r)):
            cycles[i] -= 1
            if cycles[i] == 0:
                indices[i:] = indices[i+1:] + indices[i:i+1]
                cycles[i] = n - i
            else:
                j = cycles[i]
                indices[i], indices[-j] = indices[-j], indices[i]
                yield tuple(pool[i] for i in indices[:r])
                break
    else:
        return
eg:
>>> import itertools as iters
>>> x = iters.permutations([0,1,2], 3)
>>> x
<itertools.permutations object at 0x0000018B993C40A0>
>>> list(x)
[(0, 1, 2), (0, 2, 1), (1, 0, 2), (1, 2, 0), (2, 0, 1), (2, 1, 0)]
>>>  x = iters.permutations([0,1,1], 3)
>>> x = iters.permutations([0,1,1], 3)
>>> list(x)
[(0, 1, 1), (0, 1, 1), (1, 0, 1), (1, 1, 0), (1, 0, 1), (1, 1, 0)]

itertools.compress(data, selectors) 按照真值表筛选元素

def compress(data, selectors):
    # compress('ABCDEF', [1,0,1,0,1,1]) --> A C E F
    return (d for d, s in zip(data, selectors) if s)

>>> list(itertools.compress(s,[1,0,1,0,1,1]))
['a', 'c', 'e', 'f']

1、 计数、几步
　　itertools.count(start=0, step=1)

start：计数起始值。
step：计数间隔。

说明：生成一个迭代器，该迭代器从start开始迭代，第i次迭代返回start+i*step。
itertools.count(start=0, step=1)

def count(start=0, step=1):
    # count(10) --> 10 11 12 13 14 ...
    # count(2.5, 0.5) -> 2.5 3.0 3.5 ...
    n = start
    while True:
        yield n
        n += step
>>> x = itertools.count(start=20, step=-1)
>>> print(list(itertools.islice(x, 0, 10, 1)))
[20, 19, 18, 17, 16, 15, 14, 13, 12, 11]

2、无限循环（往复）迭代
　　itertools.cycle(iterable)

iterable：可迭代对象。

说明： 把iterable变成无限循环迭代的迭代器，让iter不再只能迭代一轮。
itertools.cycle(iterable) 循环指定的列表和迭代器

def cycle(iterable):
    # cycle('ABCD') --> A B C D A B C D A B C D ...
    saved = []
    for element in iterable:
        yield element
        saved.append(element)
    while saved:
        for element in saved:
            yield element

>>> x = itertools.cycle('ABC')
>>> print(list(itertools.islice(x, 0, 10, 1)))
['A', 'B', 'C', 'A', 'B', 'C', 'A', 'B', 'C', 'A']

3、重复
　　itertools.repeat(object,times=None)

object：一个对象用于重复。
times：重复次数。

说明： 生成一个重复times次object的迭代器，若times=None则无限次重复。

import itertools

for i in itertools.repeat('练习',3):
    print(i)


'''
结果：
练习
练习
练习
'''

itertools.dropwhile(predicate, iterable) 根据真值表舍弃第一个不满足条件前面的值

def dropwhile(predicate, iterable):
    # dropwhile(lambda x: x<5, [1,4,6,4,1]) --> 6 4 1
    iterable = iter(iterable)
    for x in iterable:
        if not predicate(x):
            yield x
            break
    for x in iterable:
        yield x

>>> x = itertools.dropwhile(lambda e: e < 5, range(10))
>>> print(list(x))
[5, 6, 7, 8, 9]

itertools.filterfalse 保留对应真值为False的元素

def filterfalse(predicate, iterable):
    # filterfalse(lambda x: x%2, range(10)) --> 0 2 4 6 8
    if predicate is None:
        predicate = bool
    for x in iterable:
        if not predicate(x):
            yield x

>>> x = itertools.filterfalse(lambda e: e < 5, (1, 5, 3, 6, 9, 4))
>>> print(list(x))
[5, 6, 9]

itertools.groupby(iterable, key=None) 按照分组函数的值对元素进行分组

class groupby:
    # [k for k, g in groupby('AAAABBBCCDAABBB')] --> A B C D A B
    # [list(g) for k, g in groupby('AAAABBBCCD')] --> AAAA BBB CC D
    def __init__(self, iterable, key=None):
        if key is None:
            key = lambda x: x
        self.keyfunc = key
        self.it = iter(iterable)
        self.tgtkey = self.currkey = self.currvalue = object()
    def __iter__(self):
        return self
    def __next__(self):
        self.id = object()
        while self.currkey == self.tgtkey:
            self.currvalue = next(self.it) # Exit on StopIteration
            self.currkey = self.keyfunc(self.currvalue)
        self.tgtkey = self.currkey
    return (self.currkey, self._grouper(self.tgtkey, self.id))
    def _grouper(self, tgtkey, id):
        while self.id is id and self.currkey == tgtkey:
            yield self.currvalue
            try:
                self.currvalue = next(self.it)
            except StopIteration:
                return
            self.currkey = self.keyfunc(self.currvalue)

>>> x = itertools.groupby(range(10), lambda x: x < 5 or x > 8)
>>> for condition, numbers in x:
    print(condition, list(numbers))
True [0, 1, 2, 3, 4]
False [5, 6, 7, 8]
True [9]

itertools.islice(iterable, stop)
itertools.islice(iterable, start, stop[, step ])

def islice(iterable, *args):
    # islice('ABCDEFG', 2) --> A B
    # islice('ABCDEFG', 2, 4) --> C D

    # islice('ABCDEFG', 2, None) --> C D E F G
    # islice('ABCDEFG', 0, None, 2) --> A C E G
    s = slice(*args)
    it = iter(range(s.start or 0, s.stop or sys.maxsize, s.step or 1))
    try:
        nexti = next(it)
    except StopIteration:
        return
    for i, element in enumerate(iterable):
        if i == nexti:
            yield element
            nexti = next(it)

>>> x = itertools.islice(range(10), 0, 9, 2)
>list(x)
>[0, 2, 4, 6, 8]