5.1. DataFrame Create
pd.DataFrame(list[dict])pd.DataFrame(dict[str,list])
5.1.1. SetUp
>>> import pandas as pd
>>> import numpy as np
5.1.2. 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
5.1.3. 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
5.1.4. 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
5.1.5. 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
5.1.6. 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
5.1.7. 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: DataFrame Create
# - Difficulty: easy
# - Lines: 1
# - Minutes: 2
# %% English
# 1. Define variabl `result: with
# dataframe of `DATA` with columns named `firstname`, `lastname`, `role`
# 2. Run doctests - all must succeed
# %% Polish
# 1. Zdefiniuj variabl `result` with
# dataframe z `DATA` z kolumnami nazwanymi `firstname`, `lastname`, `role`
# 2. Uruchom doctesty - wszystkie muszą się powieść
# %% Hints
# - `pd.DataFrame()`
# %% Tests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.max_columns', 10)
>>> pd.set_option('display.max_rows', 10)
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` must be a `pd.DataFrame` type'
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname role
0 Mark Watney botanist
1 Melissa Lewis commander
2 Rick Martinez pilot
3 Alex Vogel chemist
4 Beth Johanssen engineer
5 Chris Back medic
"""
import pandas as pd
DATA = {
'firstname': ('Mark', 'Melissa', 'Rick', 'Alex', 'Beth', 'Chris'),
'lastname': ('Watney', 'Lewis', 'Martinez', 'Vogel', 'Johanssen', 'Back'),
'role': ('botanist', 'commander', 'pilot', 'chemist', 'engineer', 'medic'),
}
# Dataframe of `DATA` with columns named `firstname`, `lastname`, `role`
# type: pd.DataFrame
result = ...
# %% 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: DataFrame Create
# - Difficulty: easy
# - Lines: 1
# - Minutes: 2
# %% English
# 1. Define variabl `result: with
# dataframe of `DATA` with columns named `firstname`, `lastname`, `role`
# 2. Run doctests - all must succeed
# %% Polish
# 1. Zdefiniuj variabl `result` with
# dataframe z `DATA` z kolumnami nazwanymi `firstname`, `lastname`, `role`
# 2. Uruchom doctesty - wszystkie muszą się powieść
# %% Hints
# - `pd.DataFrame()`
# %% Tests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.max_columns', 10)
>>> pd.set_option('display.max_rows', 10)
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` must be a `pd.DataFrame` type'
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname role
0 Mark Watney botanist
1 Melissa Lewis commander
2 Rick Martinez pilot
3 Alex Vogel chemist
4 Beth Johanssen engineer
5 Chris Back medic
"""
import pandas as pd
DATA = [
('Mark', 'Watney', 'botanist', ),
('Melissa', 'Lewis', 'commander', ),
('Rick', 'Martinez', 'pilot', ),
('Alex', 'Vogel', 'chemist', ),
('Beth', 'Johanssen', 'engineer', ),
('Chris', 'Back', 'medic', ),
]
COLUMNS = ['firstname', 'lastname', 'role']
# Dataframe of `DATA` with columns named `firstname`, `lastname`, `role`
# type: pd.DataFrame
result = ...
# %% 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: DataFrame Create
# - Difficulty: easy
# - Lines: 1
# - Minutes: 2
# %% English
# 1. Define variabl `result: with
# dataframe of `DATA` with columns named `firstname`, `lastname`, `role`
# 2. Run doctests - all must succeed
# %% Polish
# 1. Zdefiniuj variabl `result` with
# dataframe z `DATA` z kolumnami nazwanymi `firstname`, `lastname`, `role`
# 2. Uruchom doctesty - wszystkie muszą się powieść
# %% Hints
# - `pd.DataFrame()`
# %% Tests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.max_columns', 10)
>>> pd.set_option('display.max_rows', 10)
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` must be a `pd.DataFrame` type'
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname role
0 Mark Watney botanist
1 Melissa Lewis commander
2 Rick Martinez pilot
3 Alex Vogel chemist
4 Beth Johanssen engineer
5 Chris Back medic
"""
import pandas as pd
DATA = [
{'firstname': 'Mark', 'lastname': 'Watney', 'role': 'botanist'},
{'firstname': 'Melissa', 'lastname': 'Lewis', 'role': 'commander'},
{'firstname': 'Rick', 'lastname': 'Martinez', 'role': 'pilot'},
{'firstname': 'Alex', 'lastname': 'Vogel', 'role': 'chemist'},
{'firstname': 'Beth', 'lastname': 'Johanssen', 'role': 'engineer'},
{'firstname': 'Chris', 'lastname': 'Back', 'role': 'medic'},
]
# Dataframe of `DATA` with columns named `firstname`, `lastname`, `role`
# type: pd.DataFrame
result = ...
# %% 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: DataFrame Create
# - Difficulty: easy
# - Lines: 7
# - Minutes: 3
# %% English
# 1. Define variabl `result: with
# dataframe with columns named `firstname`, `lastname`, `role`
# 2. Use selection with `alt` key in your IDE
# to convert data to `dict[str,tuple]` format
# 3. Run doctests - all must succeed
# %% Polish
# 1. Zdefiniuj variabl `result` with
# dataframe z kolumnami nazwanymi `firstname`, `lastname`, `role`
# 2. Użyj zaznaczania z klawiszem `alt` w Twoim IDE
# aby przekonwertować dane do formatu `dict[str,tuple]`
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Hints
# - `pd.DataFrame()`
# %% Tests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.max_columns', 10)
>>> pd.set_option('display.max_rows', 10)
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` must be a `pd.DataFrame` type'
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname role
0 Mark Watney botanist
1 Melissa Lewis commander
2 Rick Martinez pilot
3 Alex Vogel chemist
4 Beth Johanssen engineer
5 Chris Back medic
"""
import pandas as pd
# firstname lastname role
# Mark Watney botanist
# Melissa Lewis commander
# Rick Martinez pilot
# Alex Vogel chemist
# Beth Johanssen engineer
# Chris Back medic
# Dataframe with columns named `firstname`, `lastname`, `role`
# Use selection with `alt` key in your IDE
# To convert data to `dict[str,tuple]` format
# type: pd.DataFrame
result = ...
# %% 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: DataFrame Create
# - Difficulty: easy
# - Lines: 8
# - Minutes: 3
# %% English
# 1. Define variabl `result: with
# dataframe with columns named `firstname`, `lastname`, `role`
# 2. Use selection with `alt` key in your IDE
# to convert data to `list[tuple]` format
# 3. Run doctests - all must succeed
# %% Polish
# 1. Zdefiniuj variabl `result` with
# dataframe z kolumnami nazwanymi `firstname`, `lastname`, `role`
# 2. Użyj zaznaczania z klawiszem `alt` w Twoim IDE
# aby przekonwertować dane do formatu `list[tuple]`
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Hints
# - `pd.DataFrame()`
# %% Tests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.max_columns', 10)
>>> pd.set_option('display.max_rows', 10)
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` must be a `pd.DataFrame` type'
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname role
0 Mark Watney botanist
1 Melissa Lewis commander
2 Rick Martinez pilot
3 Alex Vogel chemist
4 Beth Johanssen engineer
5 Chris Back medic
"""
import pandas as pd
# firstname lastname role
# Mark Watney botanist
# Melissa Lewis commander
# Rick Martinez pilot
# Alex Vogel chemist
# Beth Johanssen engineer
# Chris Back medic
# Dataframe with columns named `firstname`, `lastname`, `role`
# Use selection with `alt` key in your IDE
# To convert data to `list[tuple]` format
# type: pd.DataFrame
result = ...
# %% 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: DataFrame Create
# - Difficulty: easy
# - Lines: 8
# - Minutes: 3
# %% English
# 1. Define variabl `result: with
# dataframe with columns named `firstname`, `lastname`, `role`
# 2. Use selection with `alt` key in your IDE
# to convert data to `list[dict]` format
# 3. Run doctests - all must succeed
# %% Polish
# 1. Zdefiniuj variabl `result` with
# dataframe z kolumnami nazwanymi `firstname`, `lastname`, `role`
# 2. Użyj zaznaczania z klawiszem `alt` w Twoim IDE
# aby przekonwertować dane do formatu `list[dict]`
# 3. Uruchom doctesty - wszystkie muszą się powieść
# %% Hints
# - `pd.DataFrame()`
# %% Tests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python 3.9+ required'
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.max_columns', 10)
>>> pd.set_option('display.max_rows', 10)
>>> assert result is not Ellipsis, \
'Assign result to variable: `result`'
>>> assert type(result) is pd.DataFrame, \
'Variable `result` must be a `pd.DataFrame` type'
>>> result # doctest: +NORMALIZE_WHITESPACE
firstname lastname role
0 Mark Watney botanist
1 Melissa Lewis commander
2 Rick Martinez pilot
3 Alex Vogel chemist
4 Beth Johanssen engineer
5 Chris Back medic
"""
import pandas as pd
# firstname lastname role
# Mark Watney botanist
# Melissa Lewis commander
# Rick Martinez pilot
# Alex Vogel chemist
# Beth Johanssen engineer
# Chris Back medic
# Dataframe with columns named `firstname`, `lastname`, `role`
# Use selection with `alt` key in your IDE
# To convert data to `list[dict]` format
# type: pd.DataFrame
result = ...