Skip to content

add validation for ignore_attributes and default_target_attribute at … #978

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

Merged
PGijsbers merged 7 commits into from
Oct 29, 2020
Merged

add validation for ignore_attributes and default_target_attribute at … #978

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
1c6c5de
add validation for ignore_attributes and default_target_attribute at …
madel0093 Oct 28, 2020
07c85cc
update naming convetions and adding type hints. using pytest parametr…
madel0093 Oct 28, 2020
ff3d27a
formating long lines and update types hint for return values
madel0093 Oct 28, 2020
ace60aa
update test_attribute_validations to use pytest.mark.parametrize
madel0093 Oct 29, 2020
afdd949
add more tests for different input types for attribute validation
madel0093 Oct 29, 2020
4cf640f
update formatting
madel0093 Oct 29, 2020
89c2ada
Merge branch 'develop' into feature/validate_attributes_at_create_dat…
a-moadel Oct 29, 2020
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
Next Next commit
add more tests for different input types for attribute validation
  • Loading branch information
@madel0093
madel0093 committed Oct 29, 2020
commit afdd949186a17a925b1ef3bf11b48546876cc429
55 changes: 53 additions & 2 deletions tests/test_datasets/test_dataset_functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1419,9 +1419,11 @@ def test_data_fork(self):

@pytest.mark.parametrize(
"default_target_attribute,row_id_attribute,ignore_attribute",
[("wrong", None, None), (None, "wrong", None), (None, None, "wrong")],
[("wrong", None, None), (None, "wrong", None), (None, None, "wrong"),
("wrong,sunny", None, None),(None, None, "wrong,sunny"),
(["wrong","sunny"], None, None), (None, None, ["wrong","sunny"])],
)
def test_attribute_validations(default_target_attribute, row_id_attribute, ignore_attribute):
def test_invalid_attribute_validations(default_target_attribute, row_id_attribute, ignore_attribute):
data = [
["a", "sunny", 85.0, 85.0, "FALSE", "no"],
["b", "sunny", 80.0, 90.0, "TRUE", "no"],
Expand Down Expand Up @@ -1464,3 +1466,52 @@ def test_attribute_validations(default_target_attribute, row_id_attribute, ignor
original_data_url=original_data_url,
paper_url=paper_url,
)

@pytest.mark.parametrize(
"default_target_attribute,row_id_attribute,ignore_attribute",
[("outlook", None, None), (None, "outlook", None), (None, None, "outlook"),
("outlook,windy", None, None), (None, None, "outlook,windy"),
(["outlook","windy"], None, None), (None, None, ["outlook","windy"])],
)
def test_valid_attribute_validations(default_target_attribute, row_id_attribute, ignore_attribute):
data = [
["a", "sunny", 85.0, 85.0, "FALSE", "no"],
["b", "sunny", 80.0, 90.0, "TRUE", "no"],
["c", "overcast", 83.0, 86.0, "FALSE", "yes"],
["d", "rainy", 70.0, 96.0, "FALSE", "yes"],
["e", "rainy", 68.0, 80.0, "FALSE", "yes"],
]
column_names = ["rnd_str", "outlook", "temperature", "humidity", "windy", "play"]
df = pd.DataFrame(data, columns=column_names)
# enforce the type of each column
df["outlook"] = df["outlook"].astype("category")
df["windy"] = df["windy"].astype("bool")
df["play"] = df["play"].astype("category")
# meta-information
name = "pandas_testing_dataset"
description = "Synthetic dataset created from a Pandas DataFrame"
creator = "OpenML tester"
collection_date = "01-01-2018"
language = "English"
licence = "MIT"
citation = "None"
original_data_url = "http://openml.github.io/openml-python"
paper_url = "http://openml.github.io/openml-python"
_ = openml.datasets.functions.create_dataset(
name=name,
description=description,
creator=creator,
contributor=None,
collection_date=collection_date,
language=language,
licence=licence,
default_target_attribute=default_target_attribute,
row_id_attribute=row_id_attribute,
ignore_attribute=ignore_attribute,
citation=citation,
attributes="auto",
data=df,
version_label="test",
original_data_url=original_data_url,
paper_url=paper_url,
)