Python itertools 模块

itertools 提供高效迭代工具函数，避免创建中间列表，提升内存效率。

chain：连接迭代器

将多个迭代器连接为一个：

from itertools import chain

# 连接多个列表
result = list(chain([1, 2], [3, 4], [5]))
print(result)  # [1, 2, 3, 4, 5]

# 连接不同类型
result = list(chain('ABC', [1, 2], range(3)))
print(result)  # ['A', 'B', 'C', 1, 2, 0, 1, 2]

# chain.from_iterable：从单个可迭代对象展开
nested = [[1, 2], [3, 4], [5]]
result = list(chain.from_iterable(nested))
print(result)  # [1, 2, 3, 4, 5]

扁平化嵌套列表

from itertools import chain

def flatten(matrix):
    return chain.from_iterable(matrix)

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

zip_longest：不等长配对

不等长迭代器配对，用填充值补齐：

from itertools import zip_longest

# 默认用 None 填充
result = list(zip_longest([1, 2, 3], ['a', 'b']))
print(result)  # [(1, 'a'), (2, 'b'), (3, None)]

# 自定义填充值
result = list(zip_longest([1, 2, 3], ['a', 'b'], fillvalue='-'))
print(result)  # [(1, 'a'), (2, 'b'), (3, '-')]

# 多个序列配对
result = list(zip_longest([1, 2], [10, 20, 30], [100], fillvalue=0))
print(result)  # [(1, 10, 100), (2, 20, 0), (0, 30, 0)]

islice：迭代器切片

对迭代器进行切片，不创建完整列表：

from itertools import islice

# 取前n个
result = list(islice(range(100), 5))
print(result)  # [0, 1, 2, 3, 4]

# 指定起点和终点
result = list(islice(range(10), 2, 6))
print(result)  # [2, 3, 4, 5]

# 指定步长
result = list(islice(range(20), 0, 10, 2))
print(result)  # [0, 2, 4, 6, 8]

# 切片无限迭代器
from itertools import count
result = list(islice(count(10, 2), 5))
print(result)  # [10, 12, 14, 16, 18]

starmap：映射解包

对每个元素解包后应用函数：

from itertools import starmap

# 相当于 map(pow, [2, 3], [5, 2])
result = list(starmap(pow, [(2, 5), (3, 2)]))
print(result)  # [32, 9]

# 多参数函数
data = [(1, 2, 3), (4, 5, 6), (7, 8, 9)]
result = list(starmap(lambda a, b, c: a + b + c, data))
print(result)  # [6, 15, 24]

filterfalse：反向过滤

保留不满足条件的元素：

from itertools import filterfalse

# 过滤偶数（保留奇数）
result = list(filterfalse(lambda x: x % 2 == 0, range(10)))
print(result)  # [1, 3, 5, 7, 9]

# 过滤空值
data = ['', 'a', None, 'b', '', 'c']
result = list(filterfalse(lambda x: not x, data))
print(result)  # ['a', 'b', 'c']

dropwhile/takewhile：条件跳过/取值

from itertools import dropwhile, takewhile

# dropwhile：跳过直到条件不满足
data = [1, 3, 5, 7, 2, 4, 6]
result = list(dropwhile(lambda x: x < 5, data))
print(result)  # [7, 2, 4, 6]（跳过1,3,5）

# takewhile：取值直到条件不满足
result = list(takewhile(lambda x: x < 5, data))
print(result)  # [1, 3]（只取满足条件的连续元素）

accumulate：累积计算

累积应用二元函数：

from itertools import accumulate

# 默认累积求和
result = list(accumulate([1, 2, 3, 4, 5]))
print(result)  # [1, 3, 6, 10, 15]

# 累积乘积
result = list(accumulate([1, 2, 3, 4], initial=1, func=lambda a, b: a * b))
print(result)  # [1, 1, 2, 6, 24]

# 累积最大值
result = list(accumulate([3, 1, 4, 1, 5], max))
print(result)  # [3, 3, 4, 4, 5]

# 指定初始值
result = list(accumulate([1, 2, 3], initial=10))
print(result)  # [10, 11, 13, 16]

product：笛卡尔积

生成多个序列的所有组合：

from itertools import product

# 两序列组合
result = list(product(['A', 'B'], [1, 2]))
print(result)  # [('A', 1), ('A', 2), ('B', 1), ('B', 2)]

# 单序列重复组合
result = list(product(['A', 'B'], repeat=2))
print(result)  # [('A', 'A'), ('A', 'B'), ('B', 'A'), ('B', 'B')]

permutations：排列

生成指定长度的排列：

from itertools import permutations

# 全排列
result = list(permutations(['A', 'B', 'C']))
print(result)  # [('A', 'B', 'C'), ('A', 'C', 'B'), ('B', 'A', 'C'), ...]

# 指定长度
result = list(permutations(['A', 'B', 'C'], 2))
print(result)  # [('A', 'B'), ('A', 'C'), ('B', 'A'), ('B', 'C'), ('C', 'A'), ('C', 'B')]

combinations：组合

生成指定长度的组合（无重复）：

from itertools import combinations

result = list(combinations(['A', 'B', 'C', 'D'], 2))
print(result)  # [('A', 'B'), ('A', 'C'), ('A', 'D'), ('B', 'C'), ('B', 'D'), ('C', 'D')]

combinations_with_replacement：允许重复的组合

from itertools import combinations_with_replacement

result = list(combinations_with_replacement(['A', 'B'], 2))
print(result)  # [('A', 'A'), ('A', 'B'), ('B', 'B')]

groupby：分组

按连续相同元素分组：

from itertools import groupby

# 简单分组
data = [1, 1, 1, 2, 2, 3, 3, 3, 3]
for key, group in groupby(data):
    print(key, list(group))
# 1 [1, 1, 1]
# 2 [2, 2]
# 3 [3, 3, 3, 3]

# 使用键函数分组
data = [('a', 1), ('a', 2), ('b', 3), ('b', 4)]
for key, group in groupby(data, key=lambda x: x[0]):
    print(key, list(group))
# a [('a', 1), ('a', 2)]
# b [('b', 3), ('b', 4)]

# 需要先排序
data = ['apple', 'banana', 'apricot', 'blueberry', 'cherry']
sorted_data = sorted(data, key=lambda x: x[0])
for key, group in groupby(sorted_data, key=lambda x: x[0]):
    print(key, list(group))
# a ['apple', 'apricot']
# b ['banana', 'blueberry']
# c ['cherry']

常用函数分类

要点总结

D:\git2\jwdev\articles\PYTHON\进阶\迭代器与生成器\itertools模块.md