6.1. DataFrame Create
pd.DataFrame(list[dict])pd.DataFrame(dict[str,list])
6.1.1. SetUp
>>> import pandas as pd
>>> import numpy as np
6.1.2. Create from List of Dicts
>>> pd.DataFrame([
... {'A': 1.0, 'B': 2.0},
... {'A': 3.0, 'B': 4.0},
... ])
A B
0 1.0 2.0
1 3.0 4.0
>>> pd.DataFrame([
... {'A': 1.0, 'B': 2.0},
... {'B': 3.0, 'C': 4.0},
... ])
A B C
0 1.0 2.0 NaN
1 NaN 3.0 4.0
>>> pd.DataFrame([
... {'firstname': 'Mark', 'lastname': 'Watney'},
... {'firstname': 'Melissa', 'lastname': 'Lewis'},
... {'firstname': 'Rick', 'lastname': 'Martinez'},
... {'firstname': 'Alex', 'lastname': 'Vogel'},
... ])
firstname lastname
0 Mark Watney
1 Melissa Lewis
2 Rick Martinez
3 Alex Vogel
6.1.3. Create from Dict
>>> pd.DataFrame({
... 'A': ['a', 'b', 'c'],
... 'B': [1.0, 2.0, 3.0],
... 'C': [1, 2, 3],
... })
A B C
0 a 1.0 1
1 b 2.0 2
2 c 3.0 3
>>> pd.DataFrame({
... 'firstname': ['Mark', 'Melissa', 'Rick', 'Alex'],
... 'lastname': ['Watney', 'Lewis', 'Martinez', 'Vogel'],
... })
firstname lastname
0 Mark Watney
1 Melissa Lewis
2 Rick Martinez
3 Alex Vogel
6.1.4. Create from NDArray
>>> import pandas as pd
>>> import numpy as np
>>> np.random.seed(0)
>>>
>>>
>>> df = pd.DataFrame(np.random.randn(7, 4))
>>>
>>> df
0 1 2 3
0 1.764052 0.400157 0.978738 2.240893
1 1.867558 -0.977278 0.950088 -0.151357
2 -0.103219 0.410599 0.144044 1.454274
3 0.761038 0.121675 0.443863 0.333674
4 1.494079 -0.205158 0.313068 -0.854096
5 -2.552990 0.653619 0.864436 -0.742165
6 2.269755 -1.454366 0.045759 -0.187184
6.1.5. Use Case - 1
>>> import pandas as pd
>>> import numpy as np
>>>
>>>
>>> pd.DataFrame({
... 'A': 1.,
... 'B': pd.Timestamp('1961-04-12'),
... 'C': pd.Series(1, index=list(range(4)), dtype='float32'),
... 'D': np.array([3] * 4, dtype='int32'),
... 'E': pd.Categorical(["test", "train", "test", "train"]),
... 'F': 'foo',
... 'G': [1,2,3,4],
... })
A B C D E F G
0 1.0 1961-04-12 1.0 3 test foo 1
1 1.0 1961-04-12 1.0 3 train foo 2
2 1.0 1961-04-12 1.0 3 test foo 3
3 1.0 1961-04-12 1.0 3 train foo 4
6.1.6. Use Case - 2
>>> import pandas as pd
>>> import numpy as np
>>> np.random.seed(0)
>>>
>>>
>>> df = pd.DataFrame(
... columns = ['Morning', 'Noon', 'Evening', 'Midnight'],
... index = pd.date_range('1999-12-30', periods=7),
... data = np.random.randn(7, 4))
...
>>> df
Morning Noon Evening Midnight
1999-12-30 1.764052 0.400157 0.978738 2.240893
1999-12-31 1.867558 -0.977278 0.950088 -0.151357
2000-01-01 -0.103219 0.410599 0.144044 1.454274
2000-01-02 0.761038 0.121675 0.443863 0.333674
2000-01-03 1.494079 -0.205158 0.313068 -0.854096
2000-01-04 -2.552990 0.653619 0.864436 -0.742165
2000-01-05 2.269755 -1.454366 0.045759 -0.187184
6.1.7. Assignments
# %% About
# - Name: DataFrame Create
# - Difficulty: easy
# - Lines: 1
# - Minutes: 2
# %% 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 `DATA` to Pandas DataFrame
# 2. Define variable `result` with the solution
# 3. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj dane `DATA` do Pandas DataFrame
# 2. Zdefiniuj zmienną `result` z rozwiązaniem
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Expected
# >>> result
# firstname lastname age
# 0 Alice Apricot 30
# 1 Bob Blackthorn 31
# 2 Carol Corn 32
# 3 Dave Durian 33
# 4 Eve Elderberry 34
# 5 Mallory Melon 15
# %% Hints
# - `pd.DataFrame()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python has an is invalid version; expected: `3.9` or newer.'
>>> assert 'result' in globals(), \
'Variable `result` is not defined; assign result of your program to it.'
>>> assert result is not Ellipsis, \
'Variable `result` has an invalid value; assign result of your program to it.'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` has an invalid type; expected: `pd.DataFrame`.'
>>> pd.set_option('display.max_columns', 50)
>>> pd.set_option('display.max_rows', 200)
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.memory_usage', 'deep')
>>> pd.set_option('display.precision', 4)
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname age
0 Alice Apricot 30
1 Bob Blackthorn 31
2 Carol Corn 32
3 Dave Durian 33
4 Eve Elderberry 34
5 Mallory Melon 15
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -f -v myfile.py`
# %% Imports
import pandas as pd
# %% Types
result: pd.DataFrame
# %% Data
DATA = {
'firstname': ['Alice', 'Bob', 'Carol', 'Dave', 'Eve', 'Mallory'],
'lastname': ['Apricot', 'Blackthorn', 'Corn', 'Durian', 'Elderberry', 'Melon'],
'age': [30, 31, 32, 33, 34, 15],
}
# %% Result
result = ...
# %% About
# - Name: DataFrame Create
# - Difficulty: easy
# - Lines: 1
# - Minutes: 2
# %% 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 `DATA` to Pandas DataFrame
# 2. Define variable `result` with the solution
# 3. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj dane `DATA` do Pandas DataFrame
# 2. Zdefiniuj zmienną `result` z rozwiązaniem
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Expected
# >>> result
# firstname lastname age
# 0 Alice Apricot 30
# 1 Bob Blackthorn 31
# 2 Carol Corn 32
# 3 Dave Durian 33
# 4 Eve Elderberry 34
# 5 Mallory Melon 15
# %% Hints
# - `pd.DataFrame()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python has an is invalid version; expected: `3.9` or newer.'
>>> assert 'result' in globals(), \
'Variable `result` is not defined; assign result of your program to it.'
>>> assert result is not Ellipsis, \
'Variable `result` has an invalid value; assign result of your program to it.'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` has an invalid type; expected: `pd.DataFrame`.'
>>> pd.set_option('display.max_columns', 50)
>>> pd.set_option('display.max_rows', 200)
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.memory_usage', 'deep')
>>> pd.set_option('display.precision', 4)
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname age
0 Alice Apricot 30
1 Bob Blackthorn 31
2 Carol Corn 32
3 Dave Durian 33
4 Eve Elderberry 34
5 Mallory Melon 15
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -f -v myfile.py`
# %% Imports
import pandas as pd
# %% Types
result: pd.DataFrame
# %% Data
DATA = [
('firstname', 'lastname', 'age'),
('Alice', 'Apricot', 30),
('Bob', 'Blackthorn', 31),
('Carol', 'Corn', 32),
('Dave', 'Durian', 33),
('Eve', 'Elderberry', 34),
('Mallory', 'Melon', 15),
]
# %% Result
result = ...
# %% About
# - Name: DataFrame Create
# - Difficulty: easy
# - Lines: 1
# - Minutes: 2
# %% 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 `DATA` to Pandas DataFrame
# 2. Define variable `result` with the solution
# 3. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj dane `DATA` do Pandas DataFrame
# 2. Zdefiniuj zmienną `result` z rozwiązaniem
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Expected
# >>> result
# firstname lastname age
# 0 Alice Apricot 30
# 1 Bob Blackthorn 31
# 2 Carol Corn 32
# 3 Dave Durian 33
# 4 Eve Elderberry 34
# 5 Mallory Melon 15
# %% Hints
# - `pd.DataFrame()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python has an is invalid version; expected: `3.9` or newer.'
>>> assert 'result' in globals(), \
'Variable `result` is not defined; assign result of your program to it.'
>>> assert result is not Ellipsis, \
'Variable `result` has an invalid value; assign result of your program to it.'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` has an invalid type; expected: `pd.DataFrame`.'
>>> pd.set_option('display.max_columns', 50)
>>> pd.set_option('display.max_rows', 200)
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.memory_usage', 'deep')
>>> pd.set_option('display.precision', 4)
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname age
0 Alice Apricot 30
1 Bob Blackthorn 31
2 Carol Corn 32
3 Dave Durian 33
4 Eve Elderberry 34
5 Mallory Melon 15
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -f -v myfile.py`
# %% Imports
import pandas as pd
# %% Types
result: pd.DataFrame
# %% Data
DATA = [
{'firstname': 'Alice', 'lastname': 'Apricot', 'age': 30},
{'firstname': 'Bob', 'lastname': 'Blackthorn', '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
result = ...
# %% About
# - Name: DataFrame Create
# - Difficulty: easy
# - Lines: 7
# - 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 Markdown table to Pandas DataFrame
# 2. Use selection with `alt` key in your IDE
# to convert data to `dict[str,tuple]` format
# 3. Define variable `result` with the solution
# 4. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj tabelkę Markdown do Pandas DataFrame
# 2. Zdefiniuj zmienną `result` z rozwiązaniem
# 3. Użyj zaznaczania z klawiszem `alt` w Twoim IDE
# aby przekonwertować dane do formatu `dict[str,tuple]`
# 4. Uruchom doctesty - wszystkie muszą się powieść
# %% Expected
# >>> result
# firstname lastname age
# 0 Alice Apricot 30
# 1 Bob Blackthorn 31
# 2 Carol Corn 32
# 3 Dave Durian 33
# 4 Eve Elderberry 34
# 5 Mallory Melon 15
# %% Hints
# - `pd.DataFrame()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python has an is invalid version; expected: `3.9` or newer.'
>>> assert 'result' in globals(), \
'Variable `result` is not defined; assign result of your program to it.'
>>> assert result is not Ellipsis, \
'Variable `result` has an invalid value; assign result of your program to it.'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` has an invalid type; expected: `pd.DataFrame`.'
>>> pd.set_option('display.max_columns', 50)
>>> pd.set_option('display.max_rows', 200)
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.memory_usage', 'deep')
>>> pd.set_option('display.precision', 4)
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname age
0 Alice Apricot 30
1 Bob Blackthorn 31
2 Carol Corn 32
3 Dave Durian 33
4 Eve Elderberry 34
5 Mallory Melon 15
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -f -v myfile.py`
# %% Imports
import pandas as pd
# %% Types
result: pd.DataFrame
# %% Data
# | firstname | lastname | age |
# |-----------|------------|-----|
# | Alice | Apricot | 30 |
# | Bob | Blackthorn | 31 |
# | Carol | Corn | 32 |
# | Dave | Durian | 33 |
# | Eve | Elderberry | 34 |
# | Mallory | Melon | 15 |
# %% Result
result = ...
# %% About
# - Name: DataFrame Create
# - Difficulty: easy
# - Lines: 8
# - 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 Markdown table to Pandas DataFrame
# 2. Use selection with `alt` key in your IDE
# to convert data to `list[tuple]` format
# 3. Define variable `result` with the solution
# 4. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj tabelkę Markdown do Pandas DataFrame
# 2. Zdefiniuj zmienną `result` z rozwiązaniem
# 3. Użyj zaznaczania z klawiszem `alt` w Twoim IDE
# aby przekonwertować dane do formatu `list[tuple]`
# 4. Uruchom doctesty - wszystkie muszą się powieść
# %% Hints
# - `pd.DataFrame()`
# %% Expected
# >>> result
# firstname lastname age
# 0 Alice Apricot 30
# 1 Bob Blackthorn 31
# 2 Carol Corn 32
# 3 Dave Durian 33
# 4 Eve Elderberry 34
# 5 Mallory Melon 15
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python has an is invalid version; expected: `3.9` or newer.'
>>> assert 'result' in globals(), \
'Variable `result` is not defined; assign result of your program to it.'
>>> assert result is not Ellipsis, \
'Variable `result` has an invalid value; assign result of your program to it.'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` has an invalid type; expected: `pd.DataFrame`.'
>>> pd.set_option('display.max_columns', 50)
>>> pd.set_option('display.max_rows', 200)
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.memory_usage', 'deep')
>>> pd.set_option('display.precision', 4)
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname age
0 Alice Apricot 30
1 Bob Blackthorn 31
2 Carol Corn 32
3 Dave Durian 33
4 Eve Elderberry 34
5 Mallory Melon 15
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -f -v myfile.py`
# %% Imports
import pandas as pd
# %% Types
result: pd.DataFrame
# %% Data
# | firstname | lastname | age |
# |-----------|------------|-----|
# | Alice | Apricot | 30 |
# | Bob | Blackthorn | 31 |
# | Carol | Corn | 32 |
# | Dave | Durian | 33 |
# | Eve | Elderberry | 34 |
# | Mallory | Melon | 15 |
# %% Result
result = ...
# %% About
# - Name: DataFrame Create
# - Difficulty: easy
# - Lines: 8
# - 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 Markdown table to Pandas DataFrame
# 2. Use selection with `alt` key in your IDE
# to convert data to `list[dict]` format
# 3. Define variable `result` with the solution
# 4. Run doctests - all must succeed
# %% Polish
# 1. Przekonwertuj tabelkę Markdown do Pandas DataFrame
# 2. Zdefiniuj zmienną `result` z rozwiązaniem
# 3. Użyj zaznaczania z klawiszem `alt` w Twoim IDE
# aby przekonwertować dane do formatu `list[dict]`
# 4. Uruchom doctesty - wszystkie muszą się powieść
# %% Expected
# >>> result
# firstname lastname age
# 0 Alice Apricot 30
# 1 Bob Blackthorn 31
# 2 Carol Corn 32
# 3 Dave Durian 33
# 4 Eve Elderberry 34
# 5 Mallory Melon 15
# %% Hints
# - `pd.DataFrame()`
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python has an is invalid version; expected: `3.9` or newer.'
>>> assert 'result' in globals(), \
'Variable `result` is not defined; assign result of your program to it.'
>>> assert result is not Ellipsis, \
'Variable `result` has an invalid value; assign result of your program to it.'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` has an invalid type; expected: `pd.DataFrame`.'
>>> pd.set_option('display.max_columns', 50)
>>> pd.set_option('display.max_rows', 200)
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.memory_usage', 'deep')
>>> pd.set_option('display.precision', 4)
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname age
0 Alice Apricot 30
1 Bob Blackthorn 31
2 Carol Corn 32
3 Dave Durian 33
4 Eve Elderberry 34
5 Mallory Melon 15
"""
# %% Run
# - PyCharm: right-click in the editor and `Run Doctest in ...`
# - PyCharm: keyboard shortcut `Control + Shift + F10`
# - Terminal: `python -m doctest -f -v myfile.py`
# %% Imports
import pandas as pd
# %% Types
result: pd.DataFrame
# %% Data
# | firstname | lastname | age |
# |-----------|------------|-----|
# | Alice | Apricot | 30 |
# | Bob | Blackthorn | 31 |
# | Carol | Corn | 32 |
# | Dave | Durian | 33 |
# | Eve | Elderberry | 34 |
# | Mallory | Melon | 15 |
# %% Result
result = ...