Skip to content

Hotfix/test audiodataset #275

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
Gautzilla merged 14 commits into from
Sep 15, 2025
Merged

Hotfix/test audiodataset #275

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
26008f3
test basedataset datetime mismatch
mathieudpnt Sep 8, 2025
d9401d2
test basedataset datetime mismatch
mathieudpnt Sep 8, 2025
fda31bf
condition fix
mathieudpnt Sep 11, 2025
f6ac7cf
Merge branch 'main' into hotfix/test-audiodataset
mathieudpnt Sep 11, 2025
46845ca
implement begin/end condition on event class
mathieudpnt Sep 12, 2025
7d5947e
update event and test_event
mathieudpnt Sep 15, 2025
9845a26
Merge branch 'main' into hotfix/test-audiodataset
mathieudpnt Sep 15, 2025
ba0fe4c
test event typehint
mathieudpnt Sep 15, 2025
1d43a27
Merge branch 'hotfix/test-audiodataset' of https://github.com/mathieu…
mathieudpnt Sep 15, 2025
c584498
update test_event
mathieudpnt Sep 15, 2025
2a8aa9d
optimization imports
mathieudpnt Sep 15, 2025
ea2803a
add event init error tests
Gautzilla Sep 15, 2025
5c082c5
Merge branch 'main' into hotfix/test-audiodataset
mathieudpnt Sep 15, 2025
10304c0
Merge pull request #5 from Gautzilla/events-boundaries
mathieudpnt Sep 15, 2025
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 src/osekit/core_api/base_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -299,6 +299,9 @@ def from_files( # noqa: PLR0913
begin = min(file.begin for file in files)
if not end:
end = max(file.end for file in files)
if begin > end:
msg = (f"`begin` ({begin}) must be smaller than `end`({end})")
raise ValueError(msg)
Copy link
Copy Markdown
Contributor

@Gautzilla Gautzilla Sep 8, 2025

Choose a reason for hiding this comment

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

Shouldn't it be if begin >= end, as the error message specifies must be smaller than? (And that a 0s-long dataset wouldn't make much sense)

Copy link
Copy Markdown
Contributor Author

@mathieudpnt mathieudpnt Sep 11, 2025

Choose a reason for hiding this comment

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

ron-swanson-done

if data_duration:
data_base = (
cls._get_base_data_from_files_timedelta_total(
Expand Down
41 changes: 41 additions & 0 deletions tests/test_audio.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1045,6 +1045,8 @@ def test_audio_dataset_from_files(
"corrupted_audio_files",
"non_audio_files",
"error",
"begin",
"end",
),
[
pytest.param(
Expand All @@ -1056,6 +1058,8 @@ def test_audio_dataset_from_files(
FileNotFoundError,
match="No valid file found in ",
),
None,
None,
id="no_file",
),
pytest.param(
Expand All @@ -1076,6 +1080,8 @@ def test_audio_dataset_from_files(
FileNotFoundError,
match="No valid file found in ",
),
None,
None,
id="corrupted_audio_files",
),
pytest.param(
Expand Down Expand Up @@ -1103,6 +1109,8 @@ def test_audio_dataset_from_files(
],
[],
None,
None,
None,
id="mixed_audio_files",
),
pytest.param(
Expand All @@ -1126,6 +1134,8 @@ def test_audio_dataset_from_files(
+ ".csv",
],
None,
None,
None,
id="non_audio_files_are_not_logged",
),
pytest.param(
Expand All @@ -1151,6 +1161,8 @@ def test_audio_dataset_from_files(
FileNotFoundError,
match="No valid file found in ",
),
None,
None,
id="all_but_ok_audio",
),
pytest.param(
Expand Down Expand Up @@ -1183,15 +1195,42 @@ def test_audio_dataset_from_files(
+ ".csv",
],
None,
None,
None,
id="full_mix",
),
pytest.param(
{
"duration": 1,
"sample_rate": 48_000,
"nb_files": 3,
"date_begin": pd.Timestamp("2024-01-01 12:00:00"),
"series_type": "increase",
},
generate_sample_audio(
nb_files=1,
nb_samples=144_000,
series_type="increase",
),
[],
[],
pytest.raises(
ValueError,
match=r"`begin` .* must be smaller than `end`",
),
pd.Timestamp("2024-01-01 12:01:00"),
pd.Timestamp("2024-01-01 12:00:00"),
id="datetime_mismatch",
),
],
indirect=["audio_files"],
)
def test_audio_dataset_from_folder_errors_warnings(
tmp_path: Path,
caplog: pytest.LogCaptureFixture,
audio_files: tuple[list[Path], pytest.fixtures.Subrequest],
begin: pd.Timestamp | None,
end: pd.Timestamp | None,
expected_audio_data: list[np.ndarray],
corrupted_audio_files: list[str],
non_audio_files: list[str],
Expand All @@ -1207,6 +1246,8 @@ def test_audio_dataset_from_folder_errors_warnings(
AudioDataset.from_folder(
tmp_path,
strptime_format=TIMESTAMP_FORMAT_EXPORTED_FILES_UNLOCALIZED,
begin=begin,
end=end,
)
== e
)
Expand Down