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

Jump to bottom

test(python): More test restructure #6961

Merged
merged 8 commits into from
Feb 17, 2023
Merged

test(python): More test restructure #6961

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
034339a
Add some module level docstrings
stinodego Feb 17, 2023
7879d02
Move test_binary to namespaces
stinodego Feb 17, 2023
7f5047a
Move struct
stinodego Feb 17, 2023
e195d37
Move categorical
stinodego Feb 17, 2023
c709cf1
List namespace
stinodego Feb 17, 2023
694cdf9
Datatypes folder
stinodego Feb 17, 2023
4337eb3
Operations folder
stinodego Feb 17, 2023
5814657
Utils folder
stinodego Feb 17, 2023
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
1 change: 1 addition & 0 deletions py-polars/tests/unit/datatypes/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
"""Test module for testing behaviour of specific data types in various operations."""
0 py-polars/tests/unit/test_bool.py → py-polars/tests/unit/datatypes/test_bool.py
View file
Open in desktop
File renamed without changes.
72 changes: 0 additions & 72 deletions py-polars/tests/unit/test_categorical.py → .../tests/unit/datatypes/test_categorical.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,61 +61,6 @@ def test_read_csv_categorical() -> None:
assert df["col1"].dtype == pl.Categorical


def test_categorical_lexical_sort() -> None:
df = pl.DataFrame(
{"cats": ["z", "z", "k", "a", "b"], "vals": [3, 1, 2, 2, 3]}
).with_columns(
[
pl.col("cats").cast(pl.Categorical).cat.set_ordering("lexical"),
]
)

out = df.sort(["cats"])
assert out["cats"].dtype == pl.Categorical
expected = pl.DataFrame(
{"cats": ["a", "b", "k", "z", "z"], "vals": [2, 3, 2, 3, 1]}
)
assert_frame_equal(out.with_columns(pl.col("cats").cast(pl.Utf8)), expected)
out = df.sort(["cats", "vals"])
expected = pl.DataFrame(
{"cats": ["a", "b", "k", "z", "z"], "vals": [2, 3, 2, 1, 3]}
)
assert_frame_equal(out.with_columns(pl.col("cats").cast(pl.Utf8)), expected)
out = df.sort(["vals", "cats"])

expected = pl.DataFrame(
{"cats": ["z", "a", "k", "b", "z"], "vals": [1, 2, 2, 3, 3]}
)
assert_frame_equal(out.with_columns(pl.col("cats").cast(pl.Utf8)), expected)


def test_categorical_lexical_ordering_after_concat() -> None:
with pl.StringCache():
ldf1 = (
pl.DataFrame([pl.Series("key1", [8, 5]), pl.Series("key2", ["fox", "baz"])])
.lazy()
.with_columns(
pl.col("key2").cast(pl.Categorical).cat.set_ordering("lexical")
)
)
ldf2 = (
pl.DataFrame(
[pl.Series("key1", [6, 8, 6]), pl.Series("key2", ["fox", "foo", "bar"])]
)
.lazy()
.with_columns(
pl.col("key2").cast(pl.Categorical).cat.set_ordering("lexical")
)
)
df = (
pl.concat([ldf1, ldf2])
.with_columns(pl.col("key2").cat.set_ordering("lexical"))
.collect()
)

df.sort(["key1", "key2"])


def test_cat_to_dummies() -> None:
df = pl.DataFrame({"foo": [1, 2, 3, 4], "bar": ["a", "b", "a", "c"]})
df = df.with_columns(pl.col("bar").cast(pl.Categorical))
Expand Down Expand Up @@ -295,23 +240,6 @@ def test_categorical_in_struct_nulls() -> None:
assert s[2] == {"job": "waiter", "counts": 1}


def test_sort_categoricals_6014() -> None:
with pl.StringCache():
# create basic categorical
df1 = pl.DataFrame({"key": ["bbb", "aaa", "ccc"]}).with_columns(
pl.col("key").cast(pl.Categorical)
)
# create lexically-ordered categorical
df2 = pl.DataFrame({"key": ["bbb", "aaa", "ccc"]}).with_columns(
pl.col("key").cast(pl.Categorical).cat.set_ordering("lexical")
)

out = df1.sort("key")
assert out.to_dict(False) == {"key": ["bbb", "aaa", "ccc"]}
out = df2.sort("key")
assert out.to_dict(False) == {"key": ["aaa", "bbb", "ccc"]}


def test_cast_inner_categorical() -> None:
dtype = pl.List(pl.Categorical)
out = pl.Series("foo", [["a"], ["a", "b"]]).cast(dtype)
Expand Down
Loading