12.5. Serialization Recap
# FIXME: Zmienić dane na Userów
# FIXME: Uspójnić zadania z pikle, json, toml
# FIXME: zdefiniuj funkcję load, która czyta z pliku ...
# %% About
# - Name: Serialization Recap String
# - Difficulty: easy
# - Lines: 1
# - Minutes: 3
# %% 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
# %% English
# 1. Convert `DATA` to `result: list[tuple[str]]`
# 2. Do not convert numeric values to `float`, leave them as `str`
# 3. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj `DATA` to `result: list[tuple[str]]`
# 2. Nie konwertuj wartości numerycznych do `float`, zostaw jako `str`
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Example
# >>> result
# [('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')]
# %% Hints
# - `tuple()`
# - `str.splitlines()`
# - `str.split()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> result = list(result)
>>> assert type(result) is list, \
'Variable `result` has invalid type, should be list'
>>> assert all(type(x) is tuple for x in result), \
'All rows in `result` should be tuple'
>>> from pprint import pprint
>>> pprint(result)
[('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')]
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`
# %% Imports
# %% Types
result: list[tuple]
# %% Data
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"""
# %% Result
result = ...
# FIXME: Zmienić dane na Userów
# FIXME: Uspójnić zadania z pikle, json, toml
# FIXME: zdefiniuj funkcję load, która czyta z pliku ...
# %% About
# - Name: Serialization Recap TypeCast
# - Difficulty: easy
# - Lines: 9
# - Minutes: 8
# %% 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
# %% English
# 1. Convert `DATA` to `result: list[tuple[str]]`
# 2. Convert numeric values to `float`
# 3. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj `DATA` to `result: list[tuple[str]]`
# 2. Przekonwertuj wartości numeryczne do `float`
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Example
# >>> result
# [('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')]
# %% Hints
# - `a, *b = ...`
# - `str.splitlines()`
# - `str.split()`
# - `dict.get()`
# - `float()`
# - `tuple()`
# - `tuple() + tuple()`
# - `list.append()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> result = list(result) # expand map object
>>> assert type(result) is list, \
'Variable `result` has invalid type, should be list'
>>> assert all(type(x) is tuple for x in result), \
'All rows in `result` should be tuple'
>>> from pprint import pprint
>>> pprint(result)
[('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')]
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`
# %% Imports
# %% Types
result: list[tuple]
# %% Data
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"""
# %% Result
result = ...
# FIXME: Wywalić, funkcja jest zbyt specyficzna tylko dla jednego usecase
# FIXME: Uspójnić zadania z pikle, json, toml
# FIXME: zdefiniuj funkcję load, która czyta z pliku ...
# %% About
# - Name: Serialization Recap Switch
# - Difficulty: easy
# - Lines: 6
# - Minutes: 5
# %% 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
# %% English
# 1. Convert `DATA` to `result: list[tuple[str]]`
# 2. Convert numeric values to `float`
# 3. Substitute last element (label) with value from `ENCODER`
# 3. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj `DATA` to `result: list[tuple[str]]`
# 2. Przekonwertuj wartości numeryczne do `float`
# 3. Podmień ostatni element (etykietę) z wartością z `ENCODER`
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Example
# >>> result
# [('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')]
# %% Hints
# - `a, *b = ...`
# - `str.splitlines()`
# - `str.split()`
# - `dict.get()`
# - `float()`
# - `tuple()`
# - `tuple() + tuple()`
# - `list.append()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> result = list(result) # expand map object
>>> assert type(result) is list, \
'Variable `result` has invalid type, should be list'
>>> assert all(type(x) is tuple for x in result), \
'All rows in `result` should be tuple'
>>> from pprint import pprint
>>> pprint(result)
[('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')]
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`
# %% Imports
# %% Types
result: list[tuple]
# %% Data
DATA = """sepal_length,sepal_width,petal_length,petal_width,species
5.8,2.7,5.1,1.9,0
5.1,3.5,1.4,0.2,1
5.7,2.8,4.1,1.3,2"""
ENCODER = {
0: 'virginica',
1: 'setosa',
2: 'versicolor',
}
# %% Result
result = ...
# FIXME: Wywalić, funkcja jest zbyt specyficzna tylko dla jednego usecase
# FIXME: Uspójnić zadania z pikle, json, toml
# FIXME: zdefiniuj funkcję load, która czyta z pliku ...
# %% About
# - Name: Serialization Recap Encoder
# - Difficulty: medium
# - Lines: 10
# - Minutes: 13
# %% 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
# %% English
# 1. Convert `DATA` to `result: list[tuple[str]]`
# 2. Generate `ENCODER: dict[int,str]` from `header: list[str]`
# 3. Convert numeric values to `float`
# 4. Substitute last element (label) with value from `ENCODER`
# 5. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj `DATA` to `result: list[tuple[str]]`
# 2. Wygeneruj `ENCODER: dict[int,str]` z `header: list[str]`
# 3. Przekonwertuj wartości numeryczne do `float`
# 4. Podmień ostatni element (etykietę) z wartością z `ENCODER`
# 5. Uruchom doctesty - wszystkie muszą się powieść
# %% Example
# >>> result
# [(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')]
# %% Hints
# - `a, *b = ...`
# - `dict(enumerate())`
# - `str.splitlines()`
# - `str.split()`
# - `dict.get()`
# - `float()`
# - `tuple()`
# - `tuple() + tuple()`
# - `list.append()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> result = list(result) # expand map object
>>> assert type(result) is list, \
'Variable `result` has invalid type, should be list'
>>> assert all(type(x) is tuple for x in result), \
'All rows in `result` should be tuple'
>>> from pprint import pprint
>>> pprint(result)
[(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')]
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`
# %% Imports
# %% Types
result: list[tuple]
# %% Data
DATA = """3,4,setosa,virginica,versicolor
5.8,2.7,5.1,1.9,1
5.1,3.5,1.4,0.2,0
5.7,2.8,4.1,1.3,2"""
# %% Result
result = ...
# FIXME: Zmienić dane na Userów
# FIXME: Uspójnić zadania z pikle, json, toml
# FIXME: zdefiniuj funkcję load, która czyta z pliku ...
# %% About
# - Name: Serialization Recap FixedHeader
# - Difficulty: easy
# - Lines: 5
# - Minutes: 5
# %% 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
# %% English
# 1. Convert `DATA` to `result: list[dict]`
# 2. Use `HEADER` as dict keys
# 3. Do not convert numeric values to `float`, leave them as `str`
# 4. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj `DATA` to `result: list[dict]`
# 2. Użyj `HEADER` jako kluczy dictów
# 3. Nie konwertuj wartości numerycznych do `float`, pozostaw je jako `str`
# 4. Uruchom doctesty - wszystkie muszą się powieść
# %% Example
# >>> result
# [{'petal_length': '5.1',
# 'petal_width': '1.9',
# 'sepal_length': '5.8',
# 'sepal_width': '2.7',
# 'species': 'virginica'},
# {'petal_length': '1.4',
# 'petal_width': '0.2',
# 'sepal_length': '5.1',
# 'sepal_width': '3.5',
# 'species': 'setosa'},
# {'petal_length': '4.1',
# 'petal_width': '1.3',
# 'sepal_length': '5.7',
# 'sepal_width': '2.8',
# 'species': 'versicolor'}]
# %% Hints
# - `str.splitlines()`
# - `str.split()`
# - `list.append()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> result = list(result) # expand map object
>>> assert type(result) is list, \
'Variable `result` has invalid type, should be list'
>>> assert all(type(x) is dict for x in result), \
'All rows in `result` should be dict'
>>> from pprint import pprint
>>> pprint(result)
[{'petal_length': '5.1',
'petal_width': '1.9',
'sepal_length': '5.8',
'sepal_width': '2.7',
'species': 'virginica'},
{'petal_length': '1.4',
'petal_width': '0.2',
'sepal_length': '5.1',
'sepal_width': '3.5',
'species': 'setosa'},
{'petal_length': '4.1',
'petal_width': '1.3',
'sepal_length': '5.7',
'sepal_width': '2.8',
'species': 'versicolor'}]
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`
# %% Imports
# %% Types
result: list[dict[str,str]]
# %% Data
DATA = """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"""
HEADER = [
'sepal_length',
'sepal_width',
'petal_length',
'petal_width',
'species',
]
# %% Result
result = ...
# FIXME: Zmienić dane na Userów
# FIXME: Uspójnić zadania z pikle, json, toml
# FIXME: zdefiniuj funkcję load, która czyta z pliku ...
# %% About
# - Name: Serialization Recap GenerateHeader
# - Difficulty: hard
# - Lines: 7
# - Minutes: 8
# %% 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
# %% English
# 1. Generate `header: list[str]` from first line `DATA`
# 2. Convert `DATA` to `result: list[dict]`
# 3. Use `header` as keys
# 4. Convert numeric values to `float`
# 5. Run doctests - all must succeed
# %% Polish
# 1. Wygeneruj `header: list[str]` z pierwszej linii `DATA`
# 2. Przekonwertuj `DATA` to `result: list[dict]`
# 3. Użyj nagłówka jako kluczy
# 4. Przekonwertuj wartości numeryczne do `float`
# 5. Uruchom doctesty - wszystkie muszą się powieść
# %% Example
# >>> result
# [{'petal_length': 5.1,
# 'petal_width': 1.9,
# 'sepal_length': 5.8,
# 'sepal_width': 2.7,
# 'species': 'virginica'},
# {'petal_length': 1.4,
# 'petal_width': 0.2,
# 'sepal_length': 5.1,
# 'sepal_width': 3.5,
# 'species': 'setosa'},
# {'petal_length': 4.1,
# 'petal_width': 1.3,
# 'sepal_length': 5.7,
# 'sepal_width': 2.8,
# 'species': 'versicolor'}]
# %% Hints
# - `str.split()`
# - `list() + list()`
# - `list.append()`
# - `tuple()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> result = list(result)
>>> assert type(result) is list, \
'Variable `result` has invalid type, should be list'
>>> assert all(type(x) is dict for x in result), \
'All rows in `result` should be dict'
>>> from pprint import pprint
>>> pprint(result)
[{'petal_length': 5.1,
'petal_width': 1.9,
'sepal_length': 5.8,
'sepal_width': 2.7,
'species': 'virginica'},
{'petal_length': 1.4,
'petal_width': 0.2,
'sepal_length': 5.1,
'sepal_width': 3.5,
'species': 'setosa'},
{'petal_length': 4.1,
'petal_width': 1.3,
'sepal_length': 5.7,
'sepal_width': 2.8,
'species': 'versicolor'}]
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`
# %% Imports
# %% Types
result: list[dict]
# %% Data
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"""
# %% Result
result = ...
# %% About
# - Name: Serialization Recap FixedSchema
# - Difficulty: hard
# - Lines: 7
# - Minutes: 13
# %% 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
# %% English
# 1. Define function `dump()`:
# - Argument: `data: list[dict]`, `file: str`
# - Returns: `None`
# - Function writes `data` to `file` in CSV format
# - Add quote characters to values
# - Sort header
# 2. Non-functional requirements:
# - Do not use `import` and any module
# - Quotechar: `"`
# - Quoting: always
# - Delimiter: `,`
# - Lineseparator: `\n`
# - Sort `fieldnames`
# 3. Run doctests - all must succeed
# %% Polish
# 1. Zdefiniuj funkcję `dump()`:
# - Argument: `data: list[dict]`, `file: str`
# - Zwraca: `None`
# - Funkcja zapisuje `data` do `file` w formacie CSV
# - Dodaj znaki cudzysłowu do wartości
# - Posortuj header
# 2. Wymagania niefunkcjonalne:
# - Nie używaj `import` ani żadnych modułów
# - Quotechar: `"`
# - Quoting: zawsze
# - Delimiter: `,`
# - Lineseparator: `\n`
# - Posortuj `fieldnames`
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Example
# >>> result
# "age","firstname","lastname"
# "30","Alice","Apricot"
# "31","Bob","Banana"
# "32","Carol","Corn"
# "33","Dave","Durian"
# "34","Eve","Elderberry"
# "15","Mallory","Melon"
# <BLANKLINE>
# %% Hints
# - `sorted()`
# - `str.join()`
# - `dict.get(..., default)`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> dump(DATA, file=FILE)
>>> result = open(FILE).read()
>>> from os import remove
>>> remove(FILE)
>>> assert type(result) is str, \
'Variable `result` has invalid type, should be str'
>>> assert result != '', \
'File content is empty'
>>> print(result)
"age","firstname","lastname"
"30","Alice","Apricot"
"31","Bob","Banana"
"32","Carol","Corn"
"33","Dave","Durian"
"34","Eve","Elderberry"
"15","Mallory","Melon"
<BLANKLINE>
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`
# %% Imports
# %% Types
from typing import Callable
dump: Callable[[list[dict[str, float]], str], None]
# %% Data
FILE = '_temporary.csv'
DATA = [
{'firstname': 'Alice', 'lastname': 'Apricot', 'age': 30},
{'firstname': 'Bob', 'lastname': 'Banana', 'age': 31},
{'firstname': 'Carol', 'lastname': 'Corn', 'age': 32},
{'firstname': 'Dave', 'lastname': 'Durian', 'age': 33},
{'firstname': 'Eve', 'lastname': 'Elderberry', 'age': 34},
{'firstname': 'Mallory', 'lastname': 'Melon', 'age': 15},
]
# %% Result
def dump(data, file):
...
# %% About
# - Name: Serialization Recap Schemaless
# - Difficulty: hard
# - Lines: 7
# - Minutes: 13
# %% 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
# %% English
# 1. Define function `dump()`:
# - Argument: `data: list[dict]`, `file: str`
# - Returns: `None`
# - Function writes `data` to `file` in CSV format
# - Add quote characters to values
# - Sort header
# 2. Non-functional requirements:
# - Do not use `import` and any module
# - Quotechar: `"`
# - Quoting: always
# - Delimiter: `,`
# - Lineseparator: `\n`
# - Sort `fieldnames`
# 3. Run doctests - all must succeed
# %% Polish
# 1. Zdefiniuj funkcję `dump()`:
# - Argument: `data: list[dict]`, `file: str`
# - Zwraca: `None`
# - Funkcja zapisuje `data` do `file` w formacie CSV
# - Dodaj znaki cudzysłowu do wartości
# - Posortuj header
# 2. Wymagania niefunkcjonalne:
# - Nie używaj `import` ani żadnych modułów
# - Quotechar: `"`
# - Quoting: zawsze
# - Delimiter: `,`
# - Lineseparator: `\n`
# - Posortuj `fieldnames`
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Example
# >>> result
# "age","firstname","lastname"
# "","Alice","Apricot"
# "31","Bob",""
# "","Carol","Corn"
# "33","","Durian"
# "34","Eve",""
# "15","","Mallory"
# <BLANKLINE>
# %% Hints
# - `sorted()`
# - `set()`
# - `set.update()`
# - `str.join()`
# - `dict.get(..., default)`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> dump(DATA, file=FILE)
>>> result = open(FILE).read()
>>> from os import remove
>>> remove(FILE)
>>> assert type(result) is str, \
'Variable `result` has invalid type, should be str'
>>> assert result != '', \
'File content is empty'
>>> print(result)
"age","firstname","lastname"
"","Alice","Apricot"
"31","Bob",""
"","Carol","Corn"
"33","","Durian"
"34","Eve",""
"15","","Mallory"
<BLANKLINE>
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`
# %% Imports
# %% Types
from typing import Callable
dump: Callable[[list[dict[str, float]], str], None]
# %% Data
FILE = '_temporary.csv'
DATA = [
{'firstname': 'Alice', 'lastname': 'Apricot'},
{'firstname': 'Bob', 'age': 31},
{'lastname': 'Corn', 'firstname': 'Carol'},
{'lastname': 'Durian', 'age': 33},
{'age': 34, 'firstname': 'Eve'},
{'age': 15, 'lastname': 'Mallory'},
]
# %% Result
def dump(data, file):
...
# %% About
# - Name: Serialization Dumps ListObjects
# - Difficulty: medium
# - Lines: 7
# - Minutes: 8
# %% 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
# %% English
# 1. Modify function `dumps()`:
# - Argument: `data: list[User]`
# - Returns: `str`
# - Function converts `data` to CSV format
# - Add quotes to values
# - First line is a header
# 2. Define `result: str` with
# result of `dumps()` function for `DATA`
# 3. Non-functional requirements:
# - Do not use `import` and any module
# - Quotechar: `"`
# - Quoting: all
# - Delimiter: `,`
# - Lineseparator: `\n`
# 4. Run doctests - all must succeed
# %% Polish
# 1. Zmodyfikuj funkcję `dumps()`:
# - Argument: `data: list[User]`
# - Zwraca: `str`
# - Funkcja konwertuje `data` do formatu CSV
# - Dodaj cudzysłowie do wartości
# - Pierwsza linia to nagłówek
# 2. Zdefiniuj `result: str` z
# wynikiem funkcji `dumps()` dla `DATA`
# 3. Wymagania niefunkcjonalne:
# - Nie używaj `import` ani żadnych modułów
# - Quotechar: `"`
# - Quoting: wszystkie
# - Delimiter: `,`
# - Lineseparator: `\n`
# 4. Uruchom doctesty - wszystkie muszą się powieść
# %% Example
# >>> result
# "age","firstname","groups","lastname"
# "30","Alice","[users, staff]","Apricot"
# "31","Bob","[users, staff]","Banana"
# "32","Carol","[users]","Corn"
# "33","Dave","[users]","Durian"
# "34","Eve","[users, staff, admins]","Elderberry"
# "15","Mallory","[]","Melon"
# <BLANKLINE>
# %% Hints
# - `str.join()`
# - `dict.keys()`
# - `dict.values()`
# - `[x for x in data]`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 12), \
'Python 3.12+ required'
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> assert type(result) is str, \
'Variable `result` has invalid type, should be str'
>>> print(result)
"age","firstname","groups","lastname"
"30","Alice","[users, staff]","Apricot"
"31","Bob","[users, staff]","Banana"
"32","Carol","[users]","Corn"
"33","Dave","[users]","Durian"
"34","Eve","[users, staff, admins]","Elderberry"
"15","Mallory","[]","Melon"
<BLANKLINE>
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -v myfile.py`
# %% Imports
# %% Types
from typing import Callable
type data = list[User]
dumps: Callable[[data], str]
result: str
# %% Data
class Group:
def __init__(self, name):
self.name = name
def __repr__(self):
return f'{self.name}'
class User:
def __init__(self, firstname, lastname, age=None, groups=None):
self.firstname = firstname
self.lastname = lastname
self.age = age
self.groups = groups if groups else []
def __repr__(self):
clsname = self.__class__.__qualname__
arguments = ', '.join(f'{k}={v!r}' for k,v in vars(self).items())
return f'{clsname}({arguments})'
DATA = [
User(firstname='Alice', lastname='Apricot', age=30, groups=[
Group('users'),
Group('staff'),
]),
User(firstname='Bob', lastname='Banana', age=31, groups=[
Group('users'),
Group('staff'),
]),
User(firstname='Carol', lastname='Corn', age=32, groups=[
Group('users'),
]),
User(firstname='Dave', lastname='Durian', age=33, groups=[
Group('users'),
]),
User(firstname='Eve', lastname='Elderberry', age=34, groups=[
Group('users'),
Group('staff'),
Group('admins'),
]),
User(firstname='Mallory', lastname='Melon', age=15, groups=[]),
]
# %% Result
def dumps(data):
...
result = ...