9.12. Iterator Itertools

• Learn more at https://docs.python.org/library/itertools.html

• More information in Itertools

• from itertools import *

• count(start=0, step=1)

• cycle(iterable)

• repeat(object[, times])

• accumulate(iterable[, func, *, initial=None])

• chain(*iterables)

• compress(data, selectors)

• islice(iterable, start, stop[, step])

• starmap(function, iterable)

• product(*iterables, repeat=1)

• permutations(iterable, r=None)

• combinations(iterable, r)

• combinations_with_replacement(iterable, r)

• groupby(iterable, key=None)

9.12.1. Itertools Count

• itertools.count(start=0, step=1)

>>> from itertools import count
>>>
>>>
>>> data = count(3, 2)
>>>
>>> next(data)
3
>>> next(data)
5
>>> next(data)
7

9.12.2. Itertools Repeat

• itertools.repeat(object[, times])

>>> from itertools import repeat
>>>
>>>
>>> data = repeat('Beetlejuice', 3)
>>>
>>> next(data)
'Beetlejuice'
>>> next(data)
'Beetlejuice'
>>> next(data)
'Beetlejuice'
>>> next(data)
Traceback (most recent call last):
StopIteration

9.12.3. Itertools Accumulate

• itertools.accumulate(iterable[, func, *, initial=None])

>>> from itertools import accumulate
>>>
>>>
>>> data = accumulate([1, 2, 3, 4])
>>>
>>> next(data)
1
>>> next(data)
3
>>> next(data)
6
>>> next(data)
10
>>> next(data)
Traceback (most recent call last):
StopIteration

9.12.4. Itertools Compress

itertools.compress(data, selectors):

>>> from itertools import compress
>>>
>>>
>>> # data = compress('ABCDEF', [1,0,1,0,1,1])
>>> data = compress('ABCDEF', [True, False, True, False, True, True])
>>>
>>> next(data)
'A'
>>> next(data)
'C'
>>> next(data)
'E'
>>> next(data)
'F'
>>> next(data)
Traceback (most recent call last):
StopIteration

9.12.5. Itertools ISlice

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

>>> from itertools import islice
>>>
>>>
>>> data = islice('ABCDEFG', 2, 6, 2 )
>>>
>>> next(data)
'C'
>>> next(data)
'E'
>>> next(data)
Traceback (most recent call last):
StopIteration

9.12.6. Itertools Starmap

• itertools.starmap(function, iterable)

>>> from itertools import starmap
>>>
>>>
>>> data = starmap(pow, [(2,5), (3,2), (10,3)])
>>>
>>> next(data)
32
>>> next(data)
9
>>> next(data)
1000
>>> next(data)
Traceback (most recent call last):
StopIteration

9.12.7. Itertools Combinations

• itertools.combinations(iterable, r)

>>> from itertools import combinations
>>>
>>>
>>> data = combinations([1, 2, 3, 4], 2)
>>>
>>> next(data)
(1, 2)
>>> next(data)
(1, 3)
>>> next(data)
(1, 4)
>>> next(data)
(2, 3)
>>> next(data)
(2, 4)
>>> next(data)
(3, 4)
>>> next(data)
Traceback (most recent call last):
StopIteration

9.12.8. Itertools Combinations With Replacement

• itertools.combinations_with_replacement(iterable, r)

>>> from itertools import combinations_with_replacement
>>>
>>>
>>> data = combinations_with_replacement([1,2,3], 2)
>>>
>>> next(data)
(1, 1)
>>> next(data)
(1, 2)
>>> next(data)
(1, 3)
>>> next(data)
(2, 2)
>>> next(data)
(2, 3)
>>> next(data)
(3, 3)
>>> next(data)
Traceback (most recent call last):
StopIteration

9.12.9. Itertools GroupBy

• itertools.groupby(iterable, key=None)

• Make an iterator that returns consecutive keys and groups from the iterable. Generally, the iterable needs to already be sorted on the same key function. The operation of groupby() is similar to the uniq filter in Unix. It generates a break or new group every time the value of the key function changes. That behavior differs from SQL's GROUP BY which aggregates common elements regardless of their input order:

>>> from itertools import groupby
>>>
>>>
>>> data = groupby('AAAABBBCCDAABBB')
>>>
>>> next(data)  
('A', <itertools._grouper object at 0x...>)
>>> next(data)  
('B', <itertools._grouper object at 0x...>)
>>> next(data)  
('C', <itertools._grouper object at 0x...>)
>>> next(data)  
('D', <itertools._grouper object at 0x...>)
>>> next(data)  
('A', <itertools._grouper object at 0x...>)
>>> next(data)  
('B', <itertools._grouper object at 0x...>)
>>> next(data)
Traceback (most recent call last):
StopIteration
>>> [k for k, g in groupby('AAAABBBCCDAABBB')]
['A', 'B', 'C', 'D', 'A', 'B']
>>> [list(g) for k, g in groupby('AAAABBBCCD')]
[['A', 'A', 'A', 'A'], ['B', 'B', 'B'], ['C', 'C'], ['D']]

9.12.10. Use Case - 1

>>> from itertools import combinations
>>> from pprint import pprint
>>>
>>>
>>> colors = ['red', 'orange', 'yellow', 'green', 'blue']
>>>
>>> result = combinations(colors, 3)
>>> pprint(list(result))
[('red', 'orange', 'yellow'),
 ('red', 'orange', 'green'),
 ('red', 'orange', 'blue'),
 ('red', 'yellow', 'green'),
 ('red', 'yellow', 'blue'),
 ('red', 'green', 'blue'),
 ('orange', 'yellow', 'green'),
 ('orange', 'yellow', 'blue'),
 ('orange', 'green', 'blue'),
 ('yellow', 'green', 'blue')]

• https://docs.python.org/3/library/unittest.html#distinguishing-test-iterations-using-subtests

class NumbersTest(unittest.TestCase):

    def test_even(self):
        """
        Test that numbers between 0 and 5 are all even.
        """
        for i in range(0, 6):
            with self.subTest(i=i):
                self.assertEqual(i % 2, 0)

9.12.11. Use Case - 2

>>> from itertools import chain
>>> from pprint import pprint
>>>
>>>
>>> def powerset(iterable):
...     """
...     >>> powerset ([1,2,31])
...     () (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))
...
>>>
>>> users = ['Mark', 'Melissa', 'Rick', 'Alex']
>>>
>>> result = powerset(users)
>>> pprint(list(result))
[(),
 ('Mark',),
 ('Melissa',),
 ('Rick',),
 ('Alex',),
 ('Mark', 'Melissa'),
 ('Mark', 'Rick'),
 ('Mark', 'Alex'),
 ('Melissa', 'Rick'),
 ('Melissa', 'Alex'),
 ('Rick', 'Alex'),
 ('Mark', 'Melissa', 'Rick'),
 ('Mark', 'Melissa', 'Alex'),
 ('Mark', 'Rick', 'Alex'),
 ('Melissa', 'Rick', 'Alex'),
 ('Mark', 'Melissa', 'Rick', 'Alex')]

9.12.12. Use Case - 3

>>> from itertools import starmap
>>> from dataclasses import dataclass
>>>
>>>
>>> DATA = [
...     ('sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species'),
...     (5.8, 2.7, 5.1, 1.9, 'virginica'),
...     (5.1, 3.5, 1.4, 0.2, 'setosa'),
...     (5.7, 2.8, 4.1, 1.3, 'versicolor'),
...     (6.3, 2.9, 5.6, 1.8, 'virginica'),
...     (6.4, 3.2, 4.5, 1.5, 'versicolor'),
...     (4.7, 3.2, 1.3, 0.2, 'setosa'),
... ]
>>>
>>>
>>> @dataclass
... class Iris:
...     sl: float
...     sw: float
...     pl: float
...     pw: float
...     species: str
...
...     def save(self):
...         return 'success'

>>> result = starmap(Iris, DATA[1:])
>>>
>>> list(result)  
[Iris(sl=5.8, sw=2.7, pl=5.1, pw=1.9, species='virginica'),
 Iris(sl=5.1, sw=3.5, pl=1.4, pw=0.2, species='setosa'),
 Iris(sl=5.7, sw=2.8, pl=4.1, pw=1.3, species='versicolor'),
 Iris(sl=6.3, sw=2.9, pl=5.6, pw=1.8, species='virginica'),
 Iris(sl=6.4, sw=3.2, pl=4.5, pw=1.5, species='versicolor'),
 Iris(sl=4.7, sw=3.2, pl=1.3, pw=0.2, species='setosa')]

>>> result = starmap(Iris, DATA[1:])
>>> result = map(Iris.save, result)
>>>
>>> list(result)
['success', 'success', 'success', 'success', 'success', 'success']

>>> for iris in starmap(Iris, DATA[1:]):
...     print(f'Saving to database...', end=' ')
...     result = iris.save()
...     print(result)
...
Saving to database... success
Saving to database... success
Saving to database... success
Saving to database... success
Saving to database... success
Saving to database... success

9.12.13. Use Case - 4

>>> from unittest import TestCase
>>> from itertools import product
>>>
>>>
>>> def parse(encoding, delimiter, lineterminator):
...     return ...
>>>
>>>
>>> class ParserTest(TestCase):
...     def test_parse(self):
...         encoding = ['utf-8', 'cp1250', 'iso-8859-2', 'utf-16', 'utf-32']
...         delimiter = [',', ';']
...         lineterminator = ['\n', '\r\n']
...         for option in product(encoding, delimiter, lineterminator):
...             with self.subTest(option):
...                 result = parse(*option)
...                 self.assertEqual(result, ...)

9.12.14. Assignments

# %% License
# - Copyright 2025, Matt Harasymczuk <matt@python3.info>
# - This code can be used only for learning by humans
# - This code cannot be used for teaching others
# - This code cannot be used for teaching LLMs and AI algorithms
# - This code cannot be used in commercial or proprietary products
# - This code cannot be distributed in any form
# - This code cannot be changed in any form outside of training course
# - This code cannot have its license changed
# - If you use this code in your product, you must open-source it under GPLv2
# - Exception can be granted only by the author

# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`

# %% About
# - Name: Generator Itertools Count
# - Difficulty: medium
# - Lines: 3
# - Minutes: 3

# %% English
# 1. Algorithm `Label encoder` encodes labels (str) to numbers (int).
#    Each unique label will assign autoincremented numbers.
#    example: {'virginica': 0, 'setosa': 1, 'versicolor': 2}
# 2. Modify code below and use `itertools.count()` instead of `i`
# 3. Function resut must be `dict[str,int]`

# %% Polish
# 1. Algorytm `label_encoder` koduje etykiety (str) do liczb (int).
#    Kolejnym wystąpieniom unikalnych etykiet przyporządkowuje liczby.
#    przykład: {'virginica': 0, 'setosa': 1, 'versicolor': 2}
# 2. Zmodyfikuj kod poniżej i użyj `itertools.count()` zamiast `i`
# 3. Wynik funkcji ma być `dict[str,int]`

# %% Tests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'

>>> from inspect import isfunction, isgeneratorfunction

>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> assert type(result) is dict, \
'Result must be a dict'
>>> assert len(result) > 0, \
'Result cannot be empty'
>>> assert all(type(element) is str for element in result), \
'All elements in result must be a str'

>>> from pprint import pprint
>>> pprint(result, sort_dicts=False, width=30)
{'virginica': 0,
 'setosa': 1,
 'versicolor': 2}
"""
from itertools import count


DATA = [
    ('sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species'),
    (5.8, 2.7, 5.1, 1.9, 'virginica'),
    (5.1, 3.5, 1.4, 0.2, 'setosa'),
    (5.7, 2.8, 4.1, 1.3, 'versicolor'),
    (6.3, 2.9, 5.6, 1.8, 'virginica'),
    (6.4, 3.2, 4.5, 1.5, 'versicolor'),
    (4.7, 3.2, 1.3, 0.2, 'setosa'),
]


result = {}
i = 0

for *_, species in DATA[1:]:
    if species not in result:
        result[species] = i
        i += 1