6.11. DataFrame Query
DataFrame.query()
6.11.1. SetUp
>>> import pandas as pd
>>>
>>> df = pd.DataFrame([
... {'firstname': 'Alice', 'lastname': 'Apricot', 'age': 30},
... {'firstname': 'Bob', 'lastname': 'Blackthorn', 'age': 31},
... {'firstname': 'Carol', 'lastname': 'Corn', 'age': 32},
... ], index=['a', 'b', 'c'])
>>> df
firstname lastname age
a Alice Apricot 30
b Bob Blackthorn 31
c Carol Corn 32
6.11.2. Equals
>>> df.query('firstname == "Alice"')
firstname lastname age
a Alice Apricot 30
>>> df.query('firstname != "Alice"')
firstname lastname age
b Bob Blackthorn 31
c Carol Corn 32
6.11.3. Compare
>>> df.query('age < 31')
firstname lastname age
a Alice Apricot 30
>>> df.query('age >= 31')
firstname lastname age
b Bob Blackthorn 31
c Carol Corn 32
6.11.4. Contains
>>> df.query('firstname in ("Alice", "Bob")')
firstname lastname age
a Alice Apricot 30
b Bob Blackthorn 31
>>> users = ("Alice", "Bob")
>>> df.query('firstname in @users')
firstname lastname age
a Alice Apricot 30
b Bob Blackthorn 31
6.11.5. Index
>>> df.query('index == "a"')
firstname lastname age
a Alice Apricot 30
>>> df.query('index in ("a", "b")')
firstname lastname age
a Alice Apricot 30
b Bob Blackthorn 31
6.11.6. Variables
>>> avg = df['age'].mean()
>>>
>>>
>>> df.query('age < @avg')
firstname lastname age
a Alice Apricot 30
>>>
>>> df.query('age >= @avg')
firstname lastname age
b Bob Blackthorn 31
c Carol Corn 32
6.11.7. References
6.11.8. Assignments
# FIXME: English translation
# %% About
# - Name: DataFrame Select
# - Difficulty: easy
# - Lines: 5
# - 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
# TODO: English translation
# %% Polish
# 1. Wczytaj dane z `DATA` jako `df: pd.DataFrame`
# 2. Wybierz wiersze, gdzie wartość 'petal_length' jest powyżej 2.0
# 3. Wyświetl 5 pierwszych wierszy
# 4. Użyj `.query()`
# 5. Uruchom doctesty - wszystkie muszą się powieść
# %% Expected
# >>> result # doctest: +NORMALIZE_WHITESPACE
# sepal_length sepal_width petal_length petal_width species
# 1 5.9 3.0 5.1 1.8 virginica
# 2 6.0 3.4 4.5 1.6 versicolor
# 3 7.3 2.9 6.3 1.8 virginica
# 4 5.6 2.5 3.9 1.1 versicolor
# 6 5.5 2.6 4.4 1.2 versicolor
# %% Doctests
"""
>>> import sys; sys.tracebacklimit = 0
>>> assert sys.version_info >= (3, 9), \
'Python has an is invalid version; expected: `3.9` or newer.'
>>> pd.set_option('display.width', 500)
>>> pd.set_option('display.max_columns', 10)
>>> pd.set_option('display.max_rows', 10)
>>> 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`.'
>>> result # doctest: +NORMALIZE_WHITESPACE
sepal_length sepal_width petal_length petal_width species
1 5.9 3.0 5.1 1.8 virginica
2 6.0 3.4 4.5 1.6 versicolor
3 7.3 2.9 6.3 1.8 virginica
4 5.6 2.5 3.9 1.1 versicolor
6 5.5 2.6 4.4 1.2 versicolor
"""
# %% 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 = 'https://python3.info/_static/iris-clean.csv'
# %% Result
result = ...