1、Itertools模塊叠代器的種類

1.1 無限叠代器：

1.2 終止於最短輸入序列的叠代器：

1.3 組合產生器

2、

repeat(object[, times])

創建一個叠代器，它重復返回object對象，無窮盡地運行，除非指定了times參數。用作map()的參數，將不變參數映射到被調用函數。同時，用zip()來創建元組記錄的不變部分。

def repeat(object, times=None):
    # repeat(10, 3) --> 10 10 10
    if times is None:
        while True:
            yield object
    else:
        for i in range(times):
            yield object

cycle(iterable)

創建一個叠代器，它返回可叠代對象中的元素，並且保存每個可叠代對象中元素的副本，當可叠代對象中的元素被耗盡時，返回保存在副本中的元素。無窮無盡地重復這一行為。近似等價於：

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:

count(start=0, step=1)

創建一個叠代器，它返回以start開始的均勻間隔的值。通常用作map()參數產生連續性的數據點。另外，用zip()來添加序列號，近似等價於：

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

compress(data, selectors)

創建一個叠代器，它過濾data的元素，返回僅當selecors為True時相應的data中的元素，當data或selectors可叠代對象中的元素被耗盡時停止。近似等價於：

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)

dropwhile(predicate, iterable)

創建一個叠代器，只要predicate為True就從可叠代對象中移除元素；然後返回每個元素。請註意，叠代器不產生任何輸出，直到predicate第一次變成False，所以它可能有很長的啟動時間。近似等價於：

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

takewhile(predicate, iterable)

創建一個叠代器，只要predicate為True就返回可叠代對象中的元素。近似等價於：

def takewhile(predicate, iterable):
    # takewhile(lambda x: x<5, [1,4,6,4,1]) --> 1 4
    for x in iterable:
        if predicate(x):
            yield x
        else:
            break

tee(iterable, n=2)

從單個可叠代對象中返回n個獨立的叠代器，近似等價於：

def tee(iterable, n=2):
    it = iter(iterable)
    deques = [collections.deque() for i in range(n)]
    def gen(mydeque):
        while True:
            if not mydeque:             # when the local deque is empty
                try:
                    newval = next(it)   # fetch a new value and
                except StopIteration:
                    return
                for d in deques:        # load it to all the deques
                    d.append(newval)
            yield mydeque.popleft()
    return tuple(gen(d) for d in deques)

filterfalse(predicate, iterable) --->filter

創建一個叠代器，它過濾可叠代對象中的元素，返回僅當prediccate為False的元素，如果predicate為None，返回條目為False的元素。近似等價於：

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

starmap(function, iterable) --->map

創建一個叠代器，它使用從可叠代對象中獲取的參數計算函數。當參數已經從單個可叠代對象（數據已經被預壓縮）中分組到元組中時，而不是使用map()。map()和starmap()之間的區別與函數(a,b)和函數(* c)之間的區別相對應。 近似等價於：

def starmap(function, iterable):
    # starmap(pow, [(2,5), (3,2), (10,3)]) --> 32 9 1000
    for args in iterable:
        yield function(*args)

zip_longest(*iterables, fillvalue=None) --->zip

創建一個叠代器，它聚合每個可叠代對象的元素，如果可叠代對象長度不均勻，那麽缺失值將填充為fillvalue。叠代繼續直到最長的可叠代對象被耗盡，近似等價於：

class ZipExhausted(Exception):
    pass

def zip_longest(*args, **kwds):
    # zip_longest(‘ABCD‘, ‘xy‘, fillvalue=‘-‘) --> Ax By C- D-
    fillvalue = kwds.get(‘fillvalue‘)
    counter = len(args) - 1
    def sentinel():
        nonlocal counter
        if not counter:
            raise ZipExhausted
        counter -= 1
        yield fillvalue
    fillers = repeat(fillvalue)
    iterators = [chain(it, sentinel(), fillers) for it in args]
    try:
        while iterators:
            yield tuple(map(next, iterators))
    except ZipExhausted:
        pass

如果其中一個可叠代對象可能是無限的，那麽zip_longest()函數應該使用限制調用次數的東西（例如islice()或takewhile()）來包裝。如果未指定，則fillvalue默認為None。

3、Itertools模塊的配方

def take(n, iterable):
    "Return first n items of the iterable as a list"
    return list(islice(iterable, n))

def tabulate(function, start=0):
    "Return function(0), function(1), ..."
    return map(function, count(start))

def tail(n, iterable):
    "Return an iterator over the last n items"
    # tail(3, ‘ABCDEFG‘) --> E F G
    return iter(collections.deque(iterable, maxlen=n))

def consume(iterator, n):
    "Advance the iterator n-steps ahead. If n is none, consume entirely."
    # Use functions that consume iterators at C speed.
    if n is None:
        # feed the entire iterator into a zero-length deque
        collections.deque(iterator, maxlen=0)
    else:
        # advance to the empty slice starting at position n
        next(islice(iterator, n, n), None)

def nth(iterable, n, default=None):
    "Returns the nth item or a default value"
    return next(islice(iterable, n, None), default)

def all_equal(iterable):
    "Returns True if all the elements are equal to each other"
    g = groupby(iterable)
    return next(g, True) and not next(g, False)

def quantify(iterable, pred=bool):
    "Count how many times the predicate is true"
    return sum(map(pred, iterable))

def padnone(iterable):
    """Returns the sequence elements and then returns None indefinitely.

    Useful for emulating the behavior of the built-in map() function.
    """
    return chain(iterable, repeat(None))

def ncycles(iterable, n):
    "Returns the sequence elements n times"
    return chain.from_iterable(repeat(tuple(iterable), n))

def dotproduct(vec1, vec2):
    return sum(map(operator.mul, vec1, vec2))

def flatten(listOfLists):
    "Flatten one level of nesting"
    return chain.from_iterable(listOfLists)

def repeatfunc(func, times=None, *args):
    """Repeat calls to func with specified arguments.

    Example:  repeatfunc(random.random)
    """
    if times is None:
        return starmap(func, repeat(args))
    return starmap(func, repeat(args, times))

def pairwise(iterable):
    "s -> (s0,s1), (s1,s2), (s2, s3), ..."
    a, b = tee(iterable)
    next(b, None)
    return zip(a, b)

def grouper(iterable, n, fillvalue=None):
    "Collect data into fixed-length chunks or blocks"
    # grouper(‘ABCDEFG‘, 3, ‘x‘) --> ABC DEF Gxx"
    args = [iter(iterable)] * n
    return zip_longest(*args, fillvalue=fillvalue)

def roundrobin(*iterables):
    "roundrobin(‘ABC‘, ‘D‘, ‘EF‘) --> A D E B F C"
    # Recipe credited to George Sakkis
    pending = len(iterables)
    nexts = cycle(iter(it).__next__ for it in iterables)
    while pending:
        try:
            for next in nexts:
                yield next()
        except StopIteration:
            pending -= 1
            nexts = cycle(islice(nexts, pending))

def partition(pred, iterable):
    ‘Use a predicate to partition entries into false entries and true entries‘
    # partition(is_odd, range(10)) --> 0 2 4 6 8   and  1 3 5 7 9
    t1, t2 = tee(iterable)
    return filterfalse(pred, t1), filter(pred, t2)

def powerset(iterable):
    "powerset([1,2,3]) --> () (1,) (2,) (3,) (1,2) (1,3) (2,3) (1,2,3)"
    s = list(iterable)
    return chain.from_iterable(combinations(s, r) for r in range(len(s)+1))

def unique_everseen(iterable, key=None):
    "List unique elements, preserving order. Remember all elements ever seen."
    # unique_everseen(‘AAAABBBCCDAABBB‘) --> A B C D
    # unique_everseen(‘ABBCcAD‘, str.lower) --> A B C D
    seen = set()
    seen_add = seen.add
    if key is None:
        for element in filterfalse(seen.__contains__, iterable):
            seen_add(element)
            yield element
    else:
        for element in iterable:
            k = key(element)
            if k not in seen:
                seen_add(k)
                yield element

def unique_justseen(iterable, key=None):
    "List unique elements, preserving order. Remember only the element just seen."
    # unique_justseen(‘AAAABBBCCDAABBB‘) --> A B C D A B
    # unique_justseen(‘ABBCcAD‘, str.lower) --> A B C A D
    return map(next, map(itemgetter(1), groupby(iterable, key)))

def iter_except(func, exception, first=None):
    """ Call a function repeatedly until an exception is raised.

    Converts a call-until-exception interface to an iterator interface.
    Like builtins.iter(func, sentinel) but uses an exception instead
    of a sentinel to end the loop.

    Examples:
        iter_except(functools.partial(heappop, h), IndexError)   # priority queue iterator
        iter_except(d.popitem, KeyError)                         # non-blocking dict iterator
        iter_except(d.popleft, IndexError)                       # non-blocking deque iterator
        iter_except(q.get_nowait, Queue.Empty)                   # loop over a producer Queue
        iter_except(s.pop, KeyError)                             # non-blocking set iterator

    """
    try:
        if first is not None:
            yield first()            # For database APIs needing an initial cast to db.first()
        while True:
            yield func()
    except exception:
        pass

def first_true(iterable, default=False, pred=None):
    """Returns the first true value in the iterable.

    If no true value is found, returns *default*

    If *pred* is not None, returns the first item
    for which pred(item) is true.

    """
    # first_true([a,b,c], x) --> a or b or c or x
    # first_true([a,b], x, f) --> a if f(a) else b if f(b) else x
    return next(filter(pred, iterable), default)

def random_product(*args, repeat=1):
    "Random selection from itertools.product(*args, **kwds)"
    pools = [tuple(pool) for pool in args] * repeat
    return tuple(random.choice(pool) for pool in pools)

def random_permutation(iterable, r=None):
    "Random selection from itertools.permutations(iterable, r)"
    pool = tuple(iterable)
    r = len(pool) if r is None else r
    return tuple(random.sample(pool, r))

def random_combination(iterable, r):
    "Random selection from itertools.combinations(iterable, r)"
    pool = tuple(iterable)
    n = len(pool)
    indices = sorted(random.sample(range(n), r))
    return tuple(pool[i] for i in indices)

def random_combination_with_replacement(iterable, r):
    "Random selection from itertools.combinations_with_replacement(iterable, r)"
    pool = tuple(iterable)
    n = len(pool)
    indices = sorted(random.randrange(n) for i in range(r))
    return tuple(pool[i] for i in indices)

【譯】itertools