Mark some tests as long

.github/workflows/test.yml

@@ -65,8 +65,8 @@ jobs:
 
       - name: PyTest ("not long")
         run: |
-          poetry run pytest tests -v --cov=etna -m "not long" --cov-report=xml
-          poetry run pytest etna -v --doctest-modules
+          poetry run pytest tests -v --cov=etna -m "not long" --cov-report=xml --durations=10
+          poetry run pytest etna -v --doctest-modules --durations=10
 
       - name: Upload coverage
         uses: codecov/codecov-action@v2
@@ -103,7 +103,7 @@ jobs:
 
       - name: PyTest ("long")
         run: |
-          poetry run pytest tests -v --cov=etna -m "long" --cov-report=xml
+          poetry run pytest tests -v --cov=etna -m "long" --cov-report=xml --durations=10
 
       - name: Upload coverage
         uses: codecov/codecov-action@v2
@@ -141,8 +141,8 @@ jobs:
 
       - name: PyTest ("tsdataset transforms")
         run: |
-          poetry run pytest tests/test_datasets -v --cov=etna --cov-report=xml
-          poetry run pytest tests/test_transforms -v --cov=etna --cov-report=xml
+          poetry run pytest tests/test_datasets -v --cov=etna --cov-report=xml --durations=10
+          poetry run pytest tests/test_transforms -v --cov=etna --cov-report=xml --durations=10
 
       - name: Upload coverage
         uses: codecov/codecov-action@v2

CHANGELOG.md

@@ -17,7 +17,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 -
 -
 - Make slicing faster in `TSDataset._merge_exog`, `FilterFeaturesTransform`, `AddConstTransform`, `LambdaTransform`, `LagTransform`, `LogTransform`, `SklearnTransform`, `WindowStatisticsTransform`; make CICD test different pandas versions ([#900](https://github.com/tinkoff-ai/etna/pull/900))
--
+- 
+- 
+- 
+- Mark some tests as long ([#929](https://github.com/tinkoff-ai/etna/pull/929))
 -
 ### Fixed
 -

tests/test_ensembles/test_stacking_ensemble.py

@@ -229,6 +229,7 @@ def test_multiprocessing_ensembles(
     assert (single_jobs_forecast.df == multi_jobs_forecast.df).all().all()
 
 
+@pytest.mark.long
 @pytest.mark.parametrize("n_jobs", (1, 5))
 def test_backtest(stacking_ensemble_pipeline: StackingEnsemble, example_tsds: TSDataset, n_jobs: int):
     """Check that backtest works with StackingEnsemble."""

tests/test_ensembles/test_voting_ensemble.py

@@ -137,6 +137,7 @@ def test_multiprocessing_ensembles(
     assert (single_jobs_forecast.df == multi_jobs_forecast.df).all().all()
 
 
+@pytest.mark.long
 @pytest.mark.parametrize("n_jobs", (1, 5))
 def test_backtest(voting_ensemble_pipeline: VotingEnsemble, example_tsds: TSDataset, n_jobs: int):
     """Check that backtest works with VotingEnsemble."""

tests/test_models/nn/test_rnn.py

@@ -9,6 +9,7 @@
 from etna.transforms import StandardScalerTransform
 
 
+@pytest.mark.long
 @pytest.mark.parametrize("horizon", [8, 13])
 def test_rnn_model_run_weekly_overfit_with_scaler(ts_dataset_weekly_function_with_horizon, horizon):
     """

tests/test_models/test_inference.py

@@ -146,6 +146,7 @@ def _test_forecast_mixed_in_out_sample(ts, model, transforms):
     assert_frame_equal(forecast_out_sample_df, forecast_full_df.iloc[-5:])
 
 
+@pytest.mark.long
 @pytest.mark.parametrize(
     "model, transforms",
     [
@@ -165,6 +166,7 @@ def test_forecast_in_sample_full(model, transforms, example_tsds):
     _test_forecast_in_sample_full(example_tsds, model, transforms)
 
 
+@pytest.mark.long
 @pytest.mark.xfail(strict=True)
 @pytest.mark.parametrize(
     "model, transforms",
@@ -180,6 +182,7 @@ def test_forecast_in_sample_full_failed(model, transforms, example_tsds):
     _test_forecast_in_sample_full(example_tsds, model, transforms)
 
 
+@pytest.mark.long
 @pytest.mark.parametrize(
     "model, transforms",
     [
@@ -218,6 +221,7 @@ def test_forecast_in_sample_full_not_implemented(model, transforms, example_tsds
         _test_forecast_in_sample_full(example_tsds, model, transforms)
 
 
+@pytest.mark.long
 @pytest.mark.parametrize(
     "model, transforms",
     [
@@ -242,6 +246,7 @@ def test_forecast_in_sample_suffix(model, transforms, example_tsds):
     _test_forecast_in_sample_suffix(example_tsds, model, transforms)
 
 
+@pytest.mark.long
 @pytest.mark.parametrize(
     "model, transforms",
     [
@@ -280,6 +285,7 @@ def test_forecast_in_sample_suffix_not_implemented(model, transforms, example_ts
         _test_forecast_in_sample_suffix(example_tsds, model, transforms)
 
 
+@pytest.mark.long
 @pytest.mark.parametrize(
     "model, transforms",
     [
@@ -332,6 +338,7 @@ def test_forecast_out_sample_prefix(model, transforms, example_tsds):
     _test_forecast_out_sample_prefix(example_tsds, model, transforms)
 
 
+@pytest.mark.long
 @pytest.mark.parametrize(
     "model, transforms",
     [
@@ -355,6 +362,7 @@ def test_forecast_out_sample_suffix(model, transforms, example_tsds):
     _test_forecast_out_sample_suffix(example_tsds, model, transforms)
 
 
+@pytest.mark.long
 @pytest.mark.parametrize(
     "model, transforms",
     [
@@ -391,6 +399,7 @@ def test_forecast_out_sample_suffix_not_implemented(model, transforms, example_t
         _test_forecast_out_sample_suffix(example_tsds, model, transforms)
 
 
+@pytest.mark.long
 @pytest.mark.xfail(strict=True)
 @pytest.mark.parametrize(
     "model, transforms",
@@ -404,6 +413,7 @@ def test_forecast_out_sample_suffix_failed(model, transforms, example_tsds):
     _test_forecast_out_sample_suffix(example_tsds, model, transforms)
 
 
+@pytest.mark.long
 @pytest.mark.parametrize(
     "model, transforms",
     [
@@ -425,6 +435,7 @@ def test_forecast_mixed_in_out_sample(model, transforms, example_tsds):
     _test_forecast_mixed_in_out_sample(example_tsds, model, transforms)
 
 
+@pytest.mark.long
 @pytest.mark.parametrize(
     "model, transforms",
     [

tests/test_models/test_tbats.py

@@ -45,7 +45,7 @@ def sinusoid_ts():
     "model_class, model_class_repr",
     ((TBATSModel, "TBATSModel"), (BATSModel, "BATSModel")),
 )
-def test_reper(model_class, model_class_repr):
+def test_repr(model_class, model_class_repr):
     kwargs = {
         "use_box_cox": None,
         "box_cox_bounds": None,
@@ -84,6 +84,7 @@ def test_not_fitted(model, linear_segments_ts_unique):
         model.forecast(to_forecast)
 
 
+@pytest.mark.long
 @pytest.mark.parametrize("model", [TBATSModel(), BATSModel()])
 def test_format(model, new_format_df):
     df = new_format_df
@@ -96,6 +97,7 @@ def test_format(model, new_format_df):
     assert not future_ts.isnull().values.any()
 
 
+@pytest.mark.long
 @pytest.mark.parametrize("model", [TBATSModel(), BATSModel()])
 def test_dummy(model, sinusoid_ts):
     train, test = sinusoid_ts
@@ -107,6 +109,7 @@ def test_dummy(model, sinusoid_ts):
     assert value_metric < 0.33
 
 
+@pytest.mark.long
 @pytest.mark.parametrize("model", [TBATSModel(), BATSModel()])
 def test_prediction_interval(model, example_tsds):
     model.fit(example_tsds)

tests/test_pipeline/test_pipeline.py

@@ -530,6 +530,7 @@ def test_sanity_backtest_naive_with_intervals(weekly_period_ts):
     assert f"target_{quantiles[1]}" in features
 
 
+@pytest.mark.long
 def test_backtest_pass_with_filter_transform(ts_with_feature):
     ts = ts_with_feature