Python itertools recipes for common data tasks

Need efficient iterator-based solutions for grouping, chunking, sliding windows, and flattening.

Essential itertools recipes:

from itertools import islice, chain, groupby, zip_longest, accumulate
from collections import deque

# Chunk an iterable into fixed-size pieces
def chunked(iterable, n):
    it = iter(iterable)
    while chunk := list(islice(it, n)):
        yield chunk

list(chunked(range(10), 3))  # [[0,1,2], [3,4,5], [6,7,8], [9]]

# Sliding window
def sliding_window(iterable, n):
    it = iter(iterable)
    window = deque(islice(it, n), maxlen=n)
    if len(window) == n:
        yield tuple(window)
    for item in it:
        window.append(item)
        yield tuple(window)

list(sliding_window([1,2,3,4,5], 3))  # [(1,2,3), (2,3,4), (3,4,5)]

# Flatten nested iterables
def flatten(nested):
    for item in nested:
        if hasattr(item, '__iter__') and not isinstance(item, (str, bytes)):
            yield from flatten(item)
        else:
            yield item

list(flatten([[1,[2,3]],[4,[5,[6]]]])  # [1,2,3,4,5,6]

# Group consecutive equal elements
data = [1,1,2,2,2,3,1,1]
for key, group in groupby(data):
    print(key, list(group))  # 1 [1,1], 2 [2,2,2], 3 [3], 1 [1,1]

# Running total
list(accumulate([1,2,3,4,5]))  # [1, 3, 6, 10, 15]

# Interleave iterables
def interleave(*iterables):
    for values in zip_longest(*iterables):
        yield from (v for v in values if v is not None)

list(interleave('abc', '12'))  # ['a','1','b','2','c']

# First item matching condition (or default)
def first(iterable, predicate, default=None):
    return next((x for x in iterable if predicate(x)), default)

first(range(100), lambda x: x > 50)  # 51

itertools provides memory-efficient, lazy evaluation for data processing. These recipes avoid loading entire datasets into memory.

Python data processing and transformation