Skip to content

Commit

Permalink
fix: remove unnecessary comments
Browse files Browse the repository at this point in the history
  • Loading branch information
@d-a-bunin
d-a-bunin committed Aug 29, 2024
1 parent 4f6973d commit bd23912
Show file tree
Hide file tree
Showing 2 changed files with 169 additions and 176 deletions.
1 change: 1 addition & 0 deletions etna/datasets/internal_datasets.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -347,6 +347,7 @@ def read_data(path: Path, part: str) -> np.ndarray:
targets = np.concatenate([targets_train, targets_test], axis=0)
targets = targets[np.argsort(ts_indecies)].reshape(-1, 963)

# federal holidays and days with anomalies
drop_days = [

Check warning on line 351 in etna/datasets/internal_datasets.py

View check run for this annotation

Codecov / codecov/patch

etna/datasets/internal_datasets.py#L351 

Added line #L351 was not covered by tests
date(2008, 1, 1),
date(2008, 1, 21),
Expand Down
344 changes: 168 additions & 176 deletions tests/test_datasets/test_internal_datasets.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -81,189 +81,181 @@ def test_not_present_part():
@pytest.mark.parametrize(
"dataset_name, expected_shape, expected_min_timestamp, expected_max_timestamp, dataset_parts",
[
# pytest.param(
# "electricity_15T",
# (139896 + 360, 370),
# pd.to_datetime("2011-01-01 00:15:00"),
# pd.to_datetime("2015-01-01 00:00:00"),
# ("train", "test"),
# marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
# ),
# (
# "m4_hourly",
# (960 + 48, 414),
# 0,
# 1007,
# ("train", "test"),
# ),
# pytest.param(
# "m4_daily",
# (9919 + 14, 4227),
# 0,
# 9932,
# ("train", "test"),
# marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
# ),
# (
# "m4_weekly",
# (2597 + 13, 359),
# 0,
# 2609,
# ("train", "test"),
# ),
# pytest.param(
# "m4_monthly",
# (2794 + 18, 48000),
# 0,
# 2811,
# ("train", "test"),
# marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
# ),
# (
# "m4_quarterly",
# (866 + 8, 24000),
# 0,
# 873,
# ("train", "test"),
# ),
# (
# "m4_yearly",
# (835 + 6, 23000),
# 0,
# 840,
# ("train", "test"),
# ),
# pytest.param(
# "traffic_2008_10T",
# (65376 + 144, 963),
# pd.to_datetime("2008-01-01 00:00:00"),
# pd.to_datetime("2009-03-30 23:50:00"),
# ("train", "test"),
# marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
# ),
pytest.param(
"electricity_15T",
(139896 + 360, 370),
pd.to_datetime("2011-01-01 00:15:00"),
pd.to_datetime("2015-01-01 00:00:00"),
("train", "test"),
marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
),
(
"m4_hourly",
(960 + 48, 414),
0,
1007,
("train", "test"),
),
pytest.param(
"m4_daily",
(9919 + 14, 4227),
0,
9932,
("train", "test"),
marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
),
(
"m4_weekly",
(2597 + 13, 359),
0,
2609,
("train", "test"),
),
pytest.param(
"m4_monthly",
(2794 + 18, 48000),
0,
2811,
("train", "test"),
marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
),
(
"m4_quarterly",
(866 + 8, 24000),
0,
873,
("train", "test"),
),
(
"m4_yearly",
(835 + 6, 23000),
0,
840,
("train", "test"),
),
pytest.param(
"traffic_2008_10T",
(65376 + 144, 963),
pd.to_datetime("2008-01-01 00:00:00"),
pd.to_datetime("2009-03-30 23:50:00"),
("train", "test"),
marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
),
pytest.param(
"traffic_2008_hourly",
(10896 + 24, 963),
pd.to_datetime("2008-01-01 00:00:00"),
pd.to_datetime("2009-03-30 23:00:00"),
("train", "test"),
marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
),
pytest.param(
"traffic_2015_hourly",
(17520 + 24, 862),
pd.to_datetime("2015-01-01 00:00:00"),
pd.to_datetime("2016-12-31 23:00:00"),
("train", "test"),
marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
),
(
"m3_monthly",
(126 + 18, 2856),
0,
143,
("train", "test"),
),
(
"m3_quarterly",
(64 + 8, 1512),
0,
71,
("train", "test"),
),
(
"m3_other",
(96 + 8, 348),
0,
103,
("train", "test"),
),
(
"m3_yearly",
(41 + 6, 1290),
0,
46,
("train", "test"),
),
(
"tourism_monthly",
(309 + 24, 732),
0,
332,
("train", "test"),
),
(
"tourism_quarterly",
(122 + 8, 854),
0,
129,
("train", "test"),
),
(
"tourism_yearly",
(43 + 4, 1036),
0,
46,
("train", "test"),
),
(
"weather_10T",
(52560 + 144, 21),
pd.to_datetime("2020-01-01 00:10:00"),
pd.to_datetime("2021-01-01 00:00:00"),
("train", "test"),
),
(
"ETTm1",
(66800 + 2880, 7),
pd.to_datetime("2016-07-01 00:00:00"),
pd.to_datetime("2018-06-26 19:45:00"),
("train", "test"),
),
(
"ETTm2",
(66800 + 2880, 7),
pd.to_datetime("2016-07-01 00:00:00"),
pd.to_datetime("2018-06-26 19:45:00"),
("train", "test"),
),
(
"ETTh1",
(16700 + 720, 7),
pd.to_datetime("2016-07-01 00:00:00"),
pd.to_datetime("2018-06-26 19:00:00"),
("train", "test"),
),
(
"ETTh2",
(16700 + 720, 7),
pd.to_datetime("2016-07-01 00:00:00"),
pd.to_datetime("2018-06-26 19:00:00"),
("train", "test"),
),
pytest.param(
"IHEPC_T",
(2075259, 7),
pd.to_datetime("2006-12-16 17:24:00"),
pd.to_datetime("2010-11-26 21:02:00"),
tuple(),
marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
),
(
"australian_wine_sales_monthly",
(176, 1),
pd.to_datetime("1980-01-01 00:00:00"),
pd.to_datetime("1994-08-01 00:00:00"),
tuple(),
),
# TODO: revert
# pytest.param(
# "traffic_2008_hourly",
# (10896 + 24, 963),
# pd.to_datetime("2008-01-01 00:00:00"),
# pd.to_datetime("2009-03-30 23:00:00"),
# ("train", "test"),
# marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
# ),
# pytest.param(
# "traffic_2015_hourly",
# (17520 + 24, 862),
# pd.to_datetime("2015-01-01 00:00:00"),
# pd.to_datetime("2016-12-31 23:00:00"),
# ("train", "test"),
# marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
# ),
# (
# "m3_monthly",
# (126 + 18, 2856),
# 0,
# 143,
# ("train", "test"),
# ),
# (
# "m3_quarterly",
# (64 + 8, 1512),
# 0,
# 71,
# ("train", "test"),
# ),
# (
# "m3_other",
# (96 + 8, 348),
# 0,
# 103,
# ("train", "test"),
# ),
# (
# "m3_yearly",
# (41 + 6, 1290),
# 0,
# 46,
# ("train", "test"),
# ),
# (
# "tourism_monthly",
# (309 + 24, 732),
# 0,
# 332,
# ("train", "test"),
# ),
# (
# "tourism_quarterly",
# (122 + 8, 854),
# 0,
# 129,
# ("train", "test"),
# ),
# (
# "tourism_yearly",
# (43 + 4, 1036),
# 0,
# 46,
# ("train", "test"),
# ),
# (
# "weather_10T",
# (52560 + 144, 21),
# pd.to_datetime("2020-01-01 00:10:00"),
# pd.to_datetime("2021-01-01 00:00:00"),
# ("train", "test"),
# ),
# (
# "ETTm1",
# (66800 + 2880, 7),
# pd.to_datetime("2016-07-01 00:00:00"),
# pd.to_datetime("2018-06-26 19:45:00"),
# ("train", "test"),
# ),
# (
# "ETTm2",
# (66800 + 2880, 7),
# pd.to_datetime("2016-07-01 00:00:00"),
# pd.to_datetime("2018-06-26 19:45:00"),
# ("train", "test"),
# ),
# (
# "ETTh1",
# (16700 + 720, 7),
# pd.to_datetime("2016-07-01 00:00:00"),
# pd.to_datetime("2018-06-26 19:00:00"),
# ("train", "test"),
# ),
# (
# "ETTh2",
# (16700 + 720, 7),
# pd.to_datetime("2016-07-01 00:00:00"),
# pd.to_datetime("2018-06-26 19:00:00"),
# ("train", "test"),
# ),
# pytest.param(
# "IHEPC_T",
# (2075259, 7),
# pd.to_datetime("2006-12-16 17:24:00"),
# pd.to_datetime("2010-11-26 21:02:00"),
# tuple(),
# marks=pytest.mark.skip(reason="Dataset is too large for testing in GitHub."),
# ),
# (
# "australian_wine_sales_monthly",
# (176, 1),
# pd.to_datetime("1980-01-01 00:00:00"),
# pd.to_datetime("1994-08-01 00:00:00"),
# tuple(),
# ),
],
)
def test_dataset_statistics(
Expand Down

0 comments on commit bd23912

Please sign in to comment.