Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat(python): Overhaul parametric test implementations and update Hypothesis to latest version #16062

Merged
merged 4 commits into from
May 13, 2024
Merged

feat(python): Overhaul parametric test implementations and update Hypothesis to latest version #16062

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
da66e00
Bump hypothesis version
stinodego May 13, 2024
02d4400
Update implementation
stinodego May 13, 2024
7312551
Add and update tests
stinodego May 13, 2024
78349e8
Update API reference
stinodego May 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Update API reference
  • Loading branch information
@stinodego
stinodego committed May 13, 2024
commit 78349e865a8d966ce00774a5a46ed17de0e41670
49 changes: 26 additions & 23 deletions py-polars/docs/source/reference/testing.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,17 +40,18 @@ and library integrations:
* `Quick start guide <https://hypothesis.readthedocs.io/en/latest/quickstart.html>`_


Polars primitives
Polars strategies
~~~~~~~~~~~~~~~~~

Polars provides the following `hypothesis <https://hypothesis.readthedocs.io>`_
testing primitives and strategy generators/helpers to make it easy to generate
suitable test DataFrames and Series.
testing strategies:

.. autosummary::
:toctree: api/

testing.parametric.dataframes
testing.parametric.dtypes
testing.parametric.lists
testing.parametric.series


Expand Down Expand Up @@ -112,20 +113,21 @@ of any generated value being ``null`` (this is distinct from ``NaN``).

.. code-block:: python

import polars as pl
from polars.testing.parametric import dataframes
from polars import NUMERIC_DTYPES
from hypothesis import given

from hypothesis import given

@given(
dataframes(
cols=5,
null_probabililty=0.1,
null_probability=0.1,
allowed_dtypes=NUMERIC_DTYPES,
)
)
def test_numeric(df):
assert all(df[col].is_numeric() for col in df.columns)
def test_numeric(df: pl.DataFrame):
assert all(df[col].dtype.is_numeric() for col in df.columns)

# Example frame:
# ┌──────┬────────┬───────┬────────────┬────────────┐
Expand All @@ -145,27 +147,27 @@ conform to the given strategies:

.. code-block:: python

import polars as pl
from polars.testing.parametric import column, dataframes
from hypothesis.strategies import floats, sampled_from, text
from hypothesis import given

import hypothesis.strategies as st
from hypothesis import given
from string import ascii_letters, digits

id_chars = ascii_letters + digits


@given(
dataframes(
cols=[
column("id", strategy=text(min_size=4, max_size=4, alphabet=id_chars)),
column("ccy", strategy=sampled_from(["GBP", "EUR", "JPY", "USD"])),
column("price", strategy=floats(min_value=0.0, max_value=1000.0)),
column("id", strategy=st.text(min_size=4, max_size=4, alphabet=id_chars)),
column("ccy", strategy=st.sampled_from(["GBP", "EUR", "JPY", "USD"])),
column("price", strategy=st.floats(min_value=0.0, max_value=1000.0)),
],
min_size=5,
lazy=True,
)
)
def test_price_calculations(lf):
def test_price_calculations(lf: pl.LazyFrame):
...
print(lf.collect())

Expand All @@ -189,29 +191,30 @@ is always less than or equal to the second value:

.. code-block:: python

from polars.testing.parametric import create_list_strategy, dataframes, column
from hypothesis.strategies import composite
from hypothesis import given
import polars as pl
from polars.testing.parametric import column, dataframes, lists

import hypothesis.strategies as st
from hypothesis import given

@composite
def uint8_pairs(draw, uints=create_list_strategy(pl.UInt8, size=2)):
@st.composite
def uint8_pairs(draw: st.DrawFn):
uints = lists(pl.UInt8, size=2)
pairs = list(zip(draw(uints), draw(uints)))
return [sorted(ints) for ints in pairs]


@given(
dataframes(
cols=[
column("colx", strategy=uint8_pairs()),
column("coly", strategy=uint8_pairs()),
column("colz", strategy=uint8_pairs()),
],
size=3,
min_size=3,
max_size=3,
)
)
def test_miscellaneous(df):
...
def test_miscellaneous(df: pl.DataFrame): ...

# Example frame:
# ┌─────────────────────────┬─────────────────────────┬──────────────────────────┐
Expand Down