代码：

def split_list(the_list, chunk_size):
    result_list = []
    while the_list:
        result_list.append(the_list[:chunk_size])
        the_list = the_list[chunk_size:]
    return result_list

a_list = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]

print split_list(a_list, 3)

结果：

[[1, 2, 3], [4, 5, 6], [7, 8, 9], [10]]

下面是一个处理任意可迭代项的生成器：

def split_seq(iterable, size):
    it = iter(iterable)
    item = list(itertools.islice(it, size))
    while item:
        yield item
        item = list(itertools.islice(it, size))

例子：

>>> import pprint
>>> pprint.pprint(list(split_seq(xrange(75), 10)))
[[0, 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]]

任何可迭代的通用分块器，使用户可以选择如何在结尾处处理部分分块。

在Python 3上测试。

分块.py

from enum import Enum

class PartialChunkOptions(Enum):
    INCLUDE = 0
    EXCLUDE = 1
    PAD = 2
    ERROR = 3

class PartialChunkException(Exception):
    pass

def chunker(iterable, n, on_partial=PartialChunkOptions.INCLUDE, pad=None):
    """
    A chunker yielding n-element lists from an iterable, with various options
    about what to do about a partial chunk at the end.

    on_partial=PartialChunkOptions.INCLUDE (the default):
                     include the partial chunk as a short (<n) element list

    on_partial=PartialChunkOptions.EXCLUDE
                     do not include the partial chunk

    on_partial=PartialChunkOptions.PAD
                     pad to an n-element list 
                     (also pass pad=<pad_value>, default None)

    on_partial=PartialChunkOptions.ERROR
                     raise a RuntimeError if a partial chunk is encountered
    """

    on_partial = PartialChunkOptions(on_partial)        

    iterator = iter(iterable)
    while True:
        vals = []
        for i in range(n):
            try:
                vals.append(next(iterator))
            except StopIteration:
                if vals:
                    if on_partial == PartialChunkOptions.INCLUDE:
                        yield vals
                    elif on_partial == PartialChunkOptions.EXCLUDE:
                        pass
                    elif on_partial == PartialChunkOptions.PAD:
                        yield vals + [pad] * (n - len(vals))
                    elif on_partial == PartialChunkOptions.ERROR:
                        raise PartialChunkException
                    return
                return
        yield vals

测试.py

import chunker

chunk_size = 3

for it in (range(100, 107),
          range(100, 109)):

    print("\nITERABLE TO CHUNK: {}".format(it))
    print("CHUNK SIZE: {}".format(chunk_size))

    for option in chunker.PartialChunkOptions.__members__.values():
        print("\noption {} used".format(option))
        try:
            for chunk in chunker.chunker(it, chunk_size, on_partial=option):
                print(chunk)
        except chunker.PartialChunkException:
            print("PartialChunkException was raised")
    print("")

test.py的输出

ITERABLE TO CHUNK: range(100, 107)
CHUNK SIZE: 3

option PartialChunkOptions.INCLUDE used
[100, 101, 102]
[103, 104, 105]
[106]

option PartialChunkOptions.EXCLUDE used
[100, 101, 102]
[103, 104, 105]

option PartialChunkOptions.PAD used
[100, 101, 102]
[103, 104, 105]
[106, None, None]

option PartialChunkOptions.ERROR used
[100, 101, 102]
[103, 104, 105]
PartialChunkException was raised


ITERABLE TO CHUNK: range(100, 109)
CHUNK SIZE: 3

option PartialChunkOptions.INCLUDE used
[100, 101, 102]
[103, 104, 105]
[106, 107, 108]

option PartialChunkOptions.EXCLUDE used
[100, 101, 102]
[103, 104, 105]
[106, 107, 108]

option PartialChunkOptions.PAD used
[100, 101, 102]
[103, 104, 105]
[106, 107, 108]

option PartialChunkOptions.ERROR used
[100, 101, 102]
[103, 104, 105]
[106, 107, 108]

您可以使用numpy的array_split函数，例如np.array_split（np.array（data），20），将其拆分为20个大小几乎相等的块。

要确保块的大小完全相等，请使用np.split。

a = [1, 2, 3, 4, 5, 6, 7, 8, 9]
CHUNK = 4
[a[i*CHUNK:(i+1)*CHUNK] for i in xrange((len(a) + CHUNK - 1) / CHUNK )]

由于我必须这样做，下面是我的解决方案，给出了一个生成器和一个批量大小：

def pop_n_elems_from_generator(g, n):
    elems = []
    try:
        for idx in xrange(0, n):
            elems.append(g.next())
        return elems
    except StopIteration:
        return elems