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

Bugfix: Update drop invalid logic to handle multi-index dfs #1320

Merged
merged 4 commits into from
Aug 18, 2023
Merged

Bugfix: Update drop invalid logic to handle multi-index dfs #1320

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3417764
Update drop invalid logic to handle multi-index cases
kykyi Aug 18, 2023
9c59b2c
Remove un-needed code
kykyi Aug 18, 2023
2970a5e
Add note in docs about uniqueness
kykyi Aug 18, 2023
dfe8c47
Fix typo
kykyi Aug 18, 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
3 changes: 3 additions & 0 deletions docs/source/drop_invalid_rows.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,9 @@ remove the rows which causes the failure.
This functionality is available on ``DataFrameSchema``, ``SeriesSchema``, ``Column``,
as well as ``DataFrameModel`` schemas.

**Note** that this functionality works by identifying the index or multi-index of the failing rows.
If the index is not unique on the dataframe, this could result in incorrect rows being dropped.

Dropping invalid rows with :class:`~pandera.api.pandas.container.DataFrameSchema`:

.. testcode:: drop_invalid_rows_data_frame_schema
Expand Down
14 changes: 11 additions & 3 deletions pandera/backends/pandas/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -155,7 +155,15 @@ def drop_invalid_rows(self, check_obj, error_handler: SchemaErrorHandler):
"""Remove invalid elements in a check obj according to failures in caught by the error handler."""
errors = error_handler.collected_errors
for err in errors:
check_obj = check_obj.loc[
~check_obj.index.isin(err.failure_cases["index"])
]
index_values = err.failure_cases["index"]
if isinstance(check_obj.index, pd.MultiIndex):
# MultiIndex values are saved on the error as strings so need to be cast back
# to their original types
index_tuples = err.failure_cases["index"].apply(eval)
index_values = pd.MultiIndex.from_tuples(index_tuples)

mask = ~check_obj.index.isin(index_values)

check_obj = check_obj.loc[mask]

return check_obj
135 changes: 135 additions & 0 deletions tests/core/test_schemas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2330,6 +2330,141 @@ class Config:
MySchema.validate(actual_obj, lazy=False)


@pytest.mark.parametrize(
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Chat GPT can be credited with the LOTR specifics 🧝 💍

"schema, obj, expected_obj",
[
(
DataFrameSchema(
columns={
"name": Column(str),
"occupation": Column(str, nullable=False),
},
index=MultiIndex(
[
Index(str, name="state"),
Index(str, name="city"),
]
),
drop_invalid_rows=True,
),
pd.DataFrame(
{
"name": ["Frodo", "Boromir"],
"occupation": ["Ring bearer", None],
},
index=pd.MultiIndex.from_tuples(
(("MiddleEarth", "TheShire"), ("MiddleEarth", "Gondor")),
names=["state", "city"],
),
),
pd.DataFrame(
{"name": ["Frodo"], "occupation": ["Ring bearer"]},
index=pd.MultiIndex.from_tuples(
(("MiddleEarth", "TheShire"),), names=["state", "city"]
),
),
),
(
DataFrameSchema(
columns={
"path_description": Column(str, nullable=False),
"days_to_travel": Column(float, nullable=False),
},
index=MultiIndex(
[
Index(str, name="character_name"),
Index(int, name="path_id"),
]
),
drop_invalid_rows=True,
),
pd.DataFrame(
{
"path_description": [
"To Rivendell",
"To Mordor",
"To Gondor",
None,
],
"days_to_travel": [30.0, 60.5, None, 15.9],
},
index=pd.MultiIndex.from_tuples(
(("Frodo", 1), ("Sam", 2), ("Boromir", 3), ("Legolas", 4)),
names=["character_name", "path_id"],
),
),
pd.DataFrame(
{
"path_description": [
"To Rivendell",
"To Mordor",
],
"days_to_travel": [30.0, 60.5],
},
index=pd.MultiIndex.from_tuples(
(("Frodo", 1), ("Sam", 2)),
names=["character_name", "path_id"],
),
),
),
(
DataFrameSchema(
columns={
"battle_name": Column(str, nullable=False),
"victor": Column(str, nullable=False),
},
index=MultiIndex(
[
Index(int, name="year"),
Index(float, name="coordinates"),
]
),
drop_invalid_rows=True,
),
pd.DataFrame(
{
"battle_name": [
"Battle of Helm's Deep",
"Battle of the Black Gate",
"Siege of Gondor",
"Skirmish at Weathertop",
],
"victor": [
"Rohan & Allies",
"Free Peoples",
None,
"Nazgûl",
],
},
index=pd.MultiIndex.from_tuples(
((3019, 42.5), (3019, 42.6), (3019, 42.7), (3018, 42.8)),
names=["year", "coordinates"],
),
),
pd.DataFrame(
{
"battle_name": [
"Battle of Helm's Deep",
"Battle of the Black Gate",
"Skirmish at Weathertop",
],
"victor": ["Rohan & Allies", "Free Peoples", "Nazgûl"],
},
index=pd.MultiIndex.from_tuples(
((3019, 42.5), (3019, 42.6), (3018, 42.8)),
names=["year", "coordinates"],
),
),
),
],
)
def test_drop_invalid_for_multi_index(schema, obj, expected_obj):
"""Test drop_invalid_rows works as expected on multi-index dataframes"""
actual_obj = schema.validate(obj, lazy=True)

pd.testing.assert_frame_equal(actual_obj, expected_obj)


def test_get_schema_metadata():
"""Test fetching schema metadata."""

Expand Down
Loading