def test_join(self, tmp_path, monkeypatch): expected_files, expected_vars = _setup(tmp_path) def mock_init(self, data_folder): self.name = "dummy" self.interim_folder = data_folder / "interim" monkeypatch.setattr(Engineer, "__init__", mock_init) engineer = Engineer(tmp_path) joined_ds = engineer._make_dataset(static=False) dims = ["lon", "lat", "time"] output_vars = [var for var in joined_ds.variables if var not in dims] assert set(output_vars) == set( expected_vars), f"Did not retrieve all the expected variables!"
engineer = Engineer(data_path) engineer.engineer(test_year=1990, target_variable="VHI", pred_months=3, expected_length=3) # wrong shapes! datasets = engineer._get_preprocessed_files() ds_list = [xr.open_dataset(ds) for ds in datasets] dims_list = [[dim for dim in ds.dims] for ds in ds_list] variable_list = [[var for var in ds.variables if var not in dims_list[i]][0] for i, ds in enumerate(ds_list)] da_list = [ds[variable_list[i]] for i, ds in enumerate(ds_list)] # ds = engineer._make_dataset() years = [1990] train_ds, test_dict train_ds = engineer._train_test_split(ds, years, target_variable="VHI", pred_months=3, expected_length=3) xy_test, min_test_date = engineer.stratify_xy( ds, years[0], target_variable="VHI", target_month=7, pred_months=3, expected_length=3, )