ocf-data-sampler 0.0.19__py3-none-any.whl → 0.0.43__py3-none-any.whl

tests/select/test_select_spatial_slice.py

@@ -0,0 +1,154 @@
+import numpy as np
+import xarray as xr
+from ocf_data_sampler.select.location import Location
+import pytest
+
+from ocf_data_sampler.select.select_spatial_slice import (
+    select_spatial_slice_pixels, _get_idx_of_pixel_closest_to_poi
+)
+
+@pytest.fixture(scope="module")
+def da():
+    # Create dummy data
+    x = np.arange(-100, 100)
+    y = np.arange(-100, 100)
+
+    da = xr.DataArray(
+        np.random.normal(size=(len(x), len(y))),
+        coords=dict(
+            x_osgb=(["x_osgb"], x),
+            y_osgb=(["y_osgb"], y),
+        )
+    )
+    return da
+
+
+def test_get_idx_of_pixel_closest_to_poi(da):
+    
+    idx_location  = _get_idx_of_pixel_closest_to_poi(
+        da,
+        location=Location(x=10, y=10, coordinate_system="osgb"),
+    )
+
+    assert idx_location.coordinate_system == "idx"
+    assert idx_location.x == 110
+    assert idx_location.y == 110
+
+
+
+
+def test_select_spatial_slice_pixels(da):
+
+    # Select window which lies within x-y bounds of the data
+    da_sliced = select_spatial_slice_pixels(
+        da,
+        location=Location(x=-90, y=-80, coordinate_system="osgb"),
+        width_pixels=10,
+        height_pixels=10,
+        allow_partial_slice=True,
+    )
+
+
+    assert isinstance(da_sliced, xr.DataArray)
+    assert (da_sliced.x_osgb.values == np.arange(-95, -85)).all()
+    assert (da_sliced.y_osgb.values == np.arange(-85, -75)).all()
+    # No padding in this case so no NaNs
+    assert not da_sliced.isnull().any()
+
+
+    # Select window where the edge of the window lies right on the edge of the data
+    da_sliced = select_spatial_slice_pixels(
+        da,
+        location=Location(x=-90, y=-80, coordinate_system="osgb"),
+        width_pixels=20,
+        height_pixels=20,
+        allow_partial_slice=True,
+    )
+
+    assert isinstance(da_sliced, xr.DataArray)
+    assert (da_sliced.x_osgb.values == np.arange(-100, -80)).all()
+    assert (da_sliced.y_osgb.values == np.arange(-90, -70)).all()
+    # No padding in this case so no NaNs
+    assert not da_sliced.isnull().any()
+
+    # Select window which is partially outside the boundary of the data - padded on left
+    da_sliced = select_spatial_slice_pixels(
+        da,
+        location=Location(x=-90, y=-80, coordinate_system="osgb"),
+        width_pixels=30,
+        height_pixels=30,
+        allow_partial_slice=True,
+    )
+
+    assert isinstance(da_sliced, xr.DataArray)
+    assert (da_sliced.x_osgb.values == np.arange(-105, -75)).all()
+    assert (da_sliced.y_osgb.values == np.arange(-95, -65)).all()
+    # Data has been padded on left by 5 NaN pixels
+    assert da_sliced.isnull().sum() == 5*len(da_sliced.y_osgb)
+
+
+    # Select window which is partially outside the boundary of the data - padded on right
+    da_sliced = select_spatial_slice_pixels(
+        da,
+        location=Location(x=90, y=-80, coordinate_system="osgb"),
+        width_pixels=30,
+        height_pixels=30,
+        allow_partial_slice=True,
+    )
+
+    assert isinstance(da_sliced, xr.DataArray)
+    assert (da_sliced.x_osgb.values == np.arange(75, 105)).all()
+    assert (da_sliced.y_osgb.values == np.arange(-95, -65)).all()
+    # Data has been padded on right by 5 NaN pixels
+    assert da_sliced.isnull().sum() == 5*len(da_sliced.y_osgb)
+
+
+    location = Location(x=-90, y=-0, coordinate_system="osgb")
+
+    # Select window which is partially outside the boundary of the data - padded on top
+    da_sliced = select_spatial_slice_pixels(
+        da,
+        location=Location(x=-90, y=95, coordinate_system="osgb"),
+        width_pixels=20,
+        height_pixels=20,
+        allow_partial_slice=True,
+    )
+
+    assert isinstance(da_sliced, xr.DataArray)
+    assert (da_sliced.x_osgb.values == np.arange(-100, -80)).all()
+    assert (da_sliced.y_osgb.values == np.arange(85, 105)).all()
+    # Data has been padded on top by 5 NaN pixels
+    assert da_sliced.isnull().sum() == 5*len(da_sliced.x_osgb)
+
+    # Select window which is partially outside the boundary of the data - padded on bottom
+    da_sliced = select_spatial_slice_pixels(
+        da,
+        location=Location(x=-90, y=-95, coordinate_system="osgb"),
+        width_pixels=20,
+        height_pixels=20,
+        allow_partial_slice=True,
+    )
+
+    assert isinstance(da_sliced, xr.DataArray)
+    assert (da_sliced.x_osgb.values == np.arange(-100, -80)).all()
+    assert (da_sliced.y_osgb.values == np.arange(-105, -85)).all()
+    # Data has been padded on bottom by 5 NaN pixels
+    assert da_sliced.isnull().sum() == 5*len(da_sliced.x_osgb)
+
+    # Select window which is partially outside the boundary of the data - padded right and bottom
+    da_sliced = select_spatial_slice_pixels(
+        da,
+        location=Location(x=90, y=-80, coordinate_system="osgb"),
+        width_pixels=50,
+        height_pixels=50,
+        allow_partial_slice=True,
+    )
+
+    assert isinstance(da_sliced, xr.DataArray)
+    assert (da_sliced.x_osgb.values == np.arange(65, 115)).all()
+    assert (da_sliced.y_osgb.values == np.arange(-105, -55)).all()
+    # Data has been padded on right by 15 pixels and bottom by 5 NaN pixels
+    assert da_sliced.isnull().sum() == 15*len(da_sliced.y_osgb) + 5*len(da_sliced.x_osgb) - 15*5
+
+
+

tests/select/test_select_time_slice.py

@@ -0,0 +1,272 @@
+from ocf_data_sampler.select.select_time_slice import select_time_slice, select_time_slice_nwp
+
+import numpy as np
+import pandas as pd
+import xarray as xr
+import pytest
+
+
+NWP_FREQ = pd.Timedelta("3h")
+
+@pytest.fixture(scope="module")
+def da_sat_like():
+    """Create dummy data which looks like satellite data"""
+    x = np.arange(-100, 100)
+    y = np.arange(-100, 100)
+    datetimes = pd.date_range("2024-01-02 00:00", "2024-01-03 00:00", freq="5min")
+
+    da_sat = xr.DataArray(
+        np.random.normal(size=(len(datetimes), len(x), len(y))),
+        coords=dict(
+            time_utc=(["time_utc"], datetimes),
+            x_geostationary=(["x_geostationary"], x),
+            y_geostationary=(["y_geostationary"], y),
+        )
+    )
+    return da_sat
+
+
+@pytest.fixture(scope="module")
+def da_nwp_like():
+    """Create dummy data which looks like NWP data"""
+
+    x = np.arange(-100, 100)
+    y = np.arange(-100, 100)
+    datetimes = pd.date_range("2024-01-02 00:00", "2024-01-03 00:00", freq=NWP_FREQ)
+    steps = pd.timedelta_range("0h", "16h", freq="1h")
+    channels = ["t", "dswrf"]
+
+    da_nwp = xr.DataArray(
+        np.random.normal(size=(len(datetimes), len(steps), len(channels), len(x), len(y))),
+        coords=dict(
+            init_time_utc=(["init_time_utc"], datetimes),
+            step=(["step"], steps),
+            channel=(["channel"], channels),
+            x_osgb=(["x_osgb"], x),
+            y_osgb=(["y_osgb"], y),
+        )
+    )
+    return da_nwp
+
+
+@pytest.mark.parametrize("t0_str", ["12:30", "12:40", "12:00"])
+def test_select_time_slice(da_sat_like, t0_str):
+    """Test the basic functionality of select_time_slice"""
+
+    # Slice parameters
+    t0 = pd.Timestamp(f"2024-01-02 {t0_str}")
+    interval_start = pd.Timedelta(-0, "min")
+    interval_end = pd.Timedelta(60, "min")
+    freq = pd.Timedelta("5min")
+
+    # Expect to return these timestamps from the selection
+    expected_datetimes = pd.date_range(t0 +interval_start, t0 + interval_end, freq=freq)
+
+    # Make the selection
+    sat_sample = select_time_slice(
+        da_sat_like,
+        t0=t0,
+        interval_start=interval_start,
+        interval_end=interval_end,
+        sample_period_duration=freq,
+    )
+
+    # Check the returned times are as expected
+    assert (sat_sample.time_utc == expected_datetimes).all()
+
+
+@pytest.mark.parametrize("t0_str", ["00:00", "00:25", "11:00", "11:55"])
+def test_select_time_slice_out_of_bounds(da_sat_like, t0_str):
+    """Test the behaviour of select_time_slice when the selection is out of bounds"""
+
+    # Slice parameters
+    t0 = pd.Timestamp(f"2024-01-02 {t0_str}")
+    interval_start = pd.Timedelta(-30, "min")
+    interval_end = pd.Timedelta(60, "min")
+    freq = pd.Timedelta("5min")
+
+    # The data is available between these times
+    min_time = da_sat_like.time_utc.min()
+    max_time = da_sat_like.time_utc.max()
+
+    # Expect to return these timestamps from the selection
+    expected_datetimes = pd.date_range(t0 + interval_start, t0 + interval_end, freq=freq)
+
+    # Make the partially out of bounds selection
+    sat_sample = select_time_slice(
+        da_sat_like,
+        t0=t0,
+        interval_start=interval_start,
+        interval_end=interval_end,
+        sample_period_duration=freq,
+        fill_selection=True
+    )
+
+    # Check the returned times are as expected
+    assert (sat_sample.time_utc == expected_datetimes).all()
+
+    
+    # Check all the values before the first timestamp available in the data are NaN
+    all_nan_space = sat_sample.isnull().all(dim=("x_geostationary", "y_geostationary"))
+    if expected_datetimes[0] < min_time:    
+        assert all_nan_space.sel(time_utc=slice(None, min_time-freq)).all(dim="time_utc") 
+
+    # Check all the values before the first timestamp available in the data are NaN
+    if expected_datetimes[-1] > max_time:    
+        assert all_nan_space.sel(time_utc=slice(max_time+freq, None)).all(dim="time_utc")   
+
+    # Check that none of the values between the first and last available timestamp are NaN
+    any_nan_space = sat_sample.isnull().any(dim=("x_geostationary", "y_geostationary"))
+    assert not any_nan_space.sel(time_utc=slice(min_time, max_time)).any(dim="time_utc")
+
+
+@pytest.mark.parametrize("t0_str", ["10:00", "11:00", "12:00"])
+def test_select_time_slice_nwp_basic(da_nwp_like, t0_str):
+    """Test the basic functionality of select_time_slice_nwp"""
+
+    # Slice parameters
+    t0 = pd.Timestamp(f"2024-01-02 {t0_str}")
+    interval_start = pd.Timedelta(-6, "h")
+    interval_end = pd.Timedelta(3, "h")
+    freq = pd.Timedelta("1h")
+
+    # Make the selection
+    da_slice = select_time_slice_nwp(
+        da_nwp_like,
+        t0,
+        sample_period_duration=freq,
+        interval_start=interval_start,
+        interval_end=interval_end,
+        dropout_timedeltas = None,
+        dropout_frac = 0,
+        accum_channels = [],
+        channel_dim_name = "channel",
+    )
+
+    # Check the target-times are as expected
+    expected_target_times = pd.date_range(t0 + interval_start, t0 + interval_end, freq=freq)
+    assert (da_slice.target_time_utc==expected_target_times).all()
+
+    # Check the init-times are as expected
+    # - Forecast frequency is `NWP_FREQ`, and we can't have selected future init-times
+    expected_init_times = pd.to_datetime(
+        [t if t<t0 else t0 for t in expected_target_times]
+    ).floor(NWP_FREQ)
+    assert (da_slice.init_time_utc==expected_init_times).all()
+
+
+@pytest.mark.parametrize("dropout_hours", [1, 2, 5])
+def test_select_time_slice_nwp_with_dropout(da_nwp_like, dropout_hours):
+    """Test the functionality of select_time_slice_nwp with dropout"""
+
+    t0 = pd.Timestamp("2024-01-02 12:00")
+    interval_start = pd.Timedelta(-6, "h")
+    interval_end = pd.Timedelta(3, "h")
+    freq = pd.Timedelta("1h")
+    dropout_timedelta = pd.Timedelta(f"-{dropout_hours}h")
+
+    da_slice = select_time_slice_nwp(
+        da_nwp_like,
+        t0,
+        sample_period_duration=freq,
+        interval_start=interval_start,
+        interval_end=interval_end,
+        dropout_timedeltas = [dropout_timedelta],
+        dropout_frac = 1,
+        accum_channels = [],
+        channel_dim_name = "channel",
+    )
+
+    # Check the target-times are as expected
+    expected_target_times = pd.date_range(t0 + interval_start, t0 + interval_end, freq=freq)
+    assert (da_slice.target_time_utc==expected_target_times).all()
+
+    # Check the init-times are as expected considering the delay
+    t0_delayed = t0 + dropout_timedelta
+    expected_init_times = pd.to_datetime(
+        [t if t<t0_delayed else t0_delayed for t in expected_target_times]
+    ).floor(NWP_FREQ)
+    assert (da_slice.init_time_utc==expected_init_times).all()
+
+
+@pytest.mark.parametrize("t0_str", ["10:00", "11:00", "12:00"])
+def test_select_time_slice_nwp_with_dropout_and_accum(da_nwp_like, t0_str):
+    """Test the functionality of select_time_slice_nwp with dropout and accumulated variables"""
+
+    # Slice parameters
+    t0 = pd.Timestamp(f"2024-01-02 {t0_str}")
+    interval_start = pd.Timedelta(-6, "h")
+    interval_end = pd.Timedelta(3, "h")
+    freq = pd.Timedelta("1h")
+    dropout_timedelta = pd.Timedelta("-2h")
+
+    t0_delayed = (t0 + dropout_timedelta).floor(NWP_FREQ)
+
+    da_slice = select_time_slice_nwp(
+        da_nwp_like,
+        t0,
+        sample_period_duration=freq,
+        interval_start=interval_start,
+        interval_end=interval_end,
+        dropout_timedeltas=[dropout_timedelta],
+        dropout_frac=1,
+        accum_channels=["dswrf"],
+        channel_dim_name="channel",
+    )
+
+    # Check the target-times are as expected
+    expected_target_times = pd.date_range(t0 + interval_start, t0 + interval_end, freq=freq)
+    assert (da_slice.target_time_utc==expected_target_times).all()
+
+    # Check the init-times are as expected considering the delay
+    expected_init_times = pd.to_datetime(
+        [t if t<t0_delayed else t0_delayed for t in expected_target_times]
+    ).floor(NWP_FREQ)
+    assert (da_slice.init_time_utc==expected_init_times).all()
+
+    # Check channels are as expected
+    assert (da_slice.channel.values == ["t", "diff_dswrf"]).all()
+
+    # Check the accummulated channel has been differenced correctly
+
+    # This part of the data is pulled from the init-time: t0_delayed
+    da_slice_accum = da_slice.sel(
+        target_time_utc=slice(t0_delayed, None), 
+        channel="diff_dswrf"
+    )
+
+    # Get the original data for the t0_delayed init-time, and diff it along steps
+    # then select the steps which are expected to be used in the above slice
+    da_orig_diffed = (
+        da_nwp_like.sel(
+            init_time_utc=t0_delayed, 
+            channel="dswrf", 
+        ).diff(dim="step", label="lower")
+        .sel(step=slice(t0-t0_delayed + interval_start, t0-t0_delayed + interval_end))
+    )
+
+    # Check the values are the same
+    assert (da_slice_accum.values == da_orig_diffed.values).all()
+
+    # Check the non-accummulated channel has not been differenced
+
+    # This part of the data is pulled from the init-time: t0_delayed
+    da_slice_nonaccum = da_slice.sel(
+        target_time_utc=slice(t0_delayed, None), 
+        channel="t"
+    )
+
+    # Get the original data for the t0_delayed init-time, and select the steps which are expected 
+    # to be used in the above slice
+    da_orig = (
+        da_nwp_like.sel(
+            init_time_utc=t0_delayed, 
+            channel="t", 
+        )
+        .sel(step=slice(t0-t0_delayed + interval_start, t0-t0_delayed + interval_end))
+    )
+
+    # Check the values are the same
+    assert (da_slice_nonaccum.values == da_orig.values).all()
+
+

tests/torch_datasets/conftest.py

@@ -0,0 +1,18 @@
+import pytest
+
+from ocf_data_sampler.config import load_yaml_configuration, save_yaml_configuration
+
+
+@pytest.fixture()
+def site_config_filename(tmp_path, config_filename, nwp_ukv_zarr_path, sat_zarr_path, data_sites):
+
+    # adjust config to point to the zarr file
+    config = load_yaml_configuration(config_filename)
+    config.input_data.nwp["ukv"].zarr_path = nwp_ukv_zarr_path
+    config.input_data.satellite.zarr_path = sat_zarr_path
+    config.input_data.site = data_sites
+    config.input_data.gsp = None
+
+    filename = f"{tmp_path}/configuration.yaml"
+    save_yaml_configuration(config, filename)
+    return filename

tests/torch_datasets/test_process_and_combine.py

@@ -0,0 +1,126 @@
+import numpy as np
+import pandas as pd
+import xarray as xr
+import dask.array as da
+
+from ocf_data_sampler.config import load_yaml_configuration
+from ocf_data_sampler.select.location import Location
+from ocf_data_sampler.numpy_sample import NWPSampleKey, GSPSampleKey, SatelliteSampleKey
+from ocf_data_sampler.torch_datasets import PVNetUKRegionalDataset
+
+from ocf_data_sampler.torch_datasets.process_and_combine import (
+    process_and_combine_datasets,
+    merge_dicts,
+    fill_nans_in_arrays,
+    compute,
+)
+
+
+def test_process_and_combine_datasets(pvnet_config_filename):
+
+    # Load in config for function and define location 
+    config = load_yaml_configuration(pvnet_config_filename)
+    t0 = pd.Timestamp("2024-01-01 00:00")
+    location = Location(coordinate_system="osgb", x=1234, y=5678, id=1)
+
+    nwp_data = xr.DataArray(
+        np.random.rand(4, 2, 2, 2),
+        dims=["time_utc", "channel", "y", "x"],
+        coords={
+            "time_utc": pd.date_range("2024-01-01 00:00", periods=4, freq="h"),
+            "channel": ["t2m", "dswrf"],
+            "step": ("time_utc", pd.timedelta_range(start='0h', periods=4, freq='h')),
+            "init_time_utc": pd.Timestamp("2024-01-01 00:00")
+        }
+    )
+
+    sat_data = xr.DataArray(
+        np.random.rand(7, 1, 2, 2),
+        dims=["time_utc", "channel", "y", "x"],
+        coords={
+            "time_utc": pd.date_range("2024-01-01 00:00", periods=7, freq="5min"),
+            "channel": ["HRV"],
+            "x_geostationary": (["y", "x"], np.array([[1, 2], [1, 2]])),
+            "y_geostationary": (["y", "x"], np.array([[1, 1], [2, 2]]))
+        }
+    )
+
+    # Combine as dict
+    dataset_dict = {
+        "nwp": {"ukv": nwp_data},
+        "sat": sat_data
+    }
+
+    # Call relevant function
+    result = process_and_combine_datasets(dataset_dict, config, t0, location)
+
+    # Assert result is dict - check and validate
+    assert isinstance(result, dict)
+    assert NWPSampleKey.nwp in result
+    assert result[SatelliteSampleKey.satellite_actual].shape == (7, 1, 2, 2)
+    assert result[NWPSampleKey.nwp]["ukv"][NWPSampleKey.nwp].shape == (4, 1, 2, 2)
+
+
+def test_merge_dicts():
+    """Test merge_dicts function"""
+    dict1 = {"a": 1, "b": 2}
+    dict2 = {"c": 3, "d": 4}
+    dict3 = {"e": 5}
+    
+    result = merge_dicts([dict1, dict2, dict3])
+    assert result == {"a": 1, "b": 2, "c": 3, "d": 4, "e": 5}
+    
+    # Test key overwriting
+    dict4 = {"a": 10, "f": 6}
+    result = merge_dicts([dict1, dict4])
+    assert result["a"] == 10
+
+
+def test_fill_nans_in_arrays():
+    """Test the fill_nans_in_arrays function"""
+    array_with_nans = np.array([1.0, np.nan, 3.0, np.nan])
+    nested_dict = {
+        "array1": array_with_nans,
+        "nested": {
+            "array2": np.array([np.nan, 2.0, np.nan, 4.0])
+        },
+        "string_key": "not_an_array"
+    }
+    
+    result = fill_nans_in_arrays(nested_dict)
+    
+    assert not np.isnan(result["array1"]).any()
+    assert np.array_equal(result["array1"], np.array([1.0, 0.0, 3.0, 0.0]))
+    assert not np.isnan(result["nested"]["array2"]).any()
+    assert np.array_equal(result["nested"]["array2"], np.array([0.0, 2.0, 0.0, 4.0]))
+    assert result["string_key"] == "not_an_array"
+
+
+def test_compute():
+    """Test compute function with dask array"""
+    da_dask = xr.DataArray(da.random.random((5, 5)))
+
+    # Create a nested dictionary with dask array
+    nested_dict = {
+        "array1": da_dask,
+        "nested": {
+            "array2": da_dask
+        }
+    }
+
+    # Ensure initial data is lazy - i.e. not yet computed
+    assert not isinstance(nested_dict["array1"].data, np.ndarray)
+    assert not isinstance(nested_dict["nested"]["array2"].data, np.ndarray)
+
+    # Call the compute function
+    result = compute(nested_dict)
+
+    # Assert that the result is an xarray DataArray and no longer lazy
+    assert isinstance(result["array1"], xr.DataArray)
+    assert isinstance(result["nested"]["array2"], xr.DataArray)
+    assert isinstance(result["array1"].data, np.ndarray)
+    assert isinstance(result["nested"]["array2"].data, np.ndarray)
+
+    # Ensure there no NaN values in computed data
+    assert not np.isnan(result["array1"].data).any()
+    assert not np.isnan(result["nested"]["array2"].data).any()

tests/torch_datasets/test_pvnet_uk_regional.py

@@ -0,0 +1,59 @@
+import pytest
+import tempfile
+
+from ocf_data_sampler.torch_datasets import PVNetUKRegionalDataset
+from ocf_data_sampler.config import load_yaml_configuration, save_yaml_configuration
+from ocf_data_sampler.numpy_sample import NWPSampleKey, GSPSampleKey, SatelliteSampleKey
+
+
+
+def test_pvnet(pvnet_config_filename):
+
+    # Create dataset object
+    dataset = PVNetUKRegionalDataset(pvnet_config_filename)
+
+    assert len(dataset.locations) == 317 # no of GSPs not including the National level
+    # NB. I have not checked this value is in fact correct, but it does seem to stay constant
+    assert len(dataset.valid_t0_times) == 39
+    assert len(dataset) == 317*39
+
+    # Generate a sample
+    sample = dataset[0]
+
+    assert isinstance(sample, dict)
+
+    for key in [
+        NWPSampleKey.nwp, SatelliteSampleKey.satellite_actual, GSPSampleKey.gsp,
+        GSPSampleKey.solar_azimuth, GSPSampleKey.solar_elevation,
+    ]:
+        assert key in sample
+    
+    for nwp_source in ["ukv"]:
+        assert nwp_source in sample[NWPSampleKey.nwp]
+
+    # check the shape of the data is correct
+    # 30 minutes of 5 minute data (inclusive), one channel, 2x2 pixels
+    assert sample[SatelliteSampleKey.satellite_actual].shape == (7, 1, 2, 2)
+    # 3 hours of 60 minute data (inclusive), one channel, 2x2 pixels
+    assert sample[NWPSampleKey.nwp]["ukv"][NWPSampleKey.nwp].shape == (4, 1, 2, 2)
+    # 3 hours of 30 minute data (inclusive)
+    assert sample[GSPSampleKey.gsp].shape == (7,)
+    # Solar angles have same shape as GSP data
+    assert sample[GSPSampleKey.solar_azimuth].shape == (7,)
+    assert sample[GSPSampleKey.solar_elevation].shape == (7,)
+
+def test_pvnet_no_gsp(pvnet_config_filename):
+
+    # load config
+    config = load_yaml_configuration(pvnet_config_filename)
+    # remove gsp
+    config.input_data.gsp.zarr_path = ''
+
+    # save temp config file
+    with tempfile.NamedTemporaryFile() as temp_config_file:
+        save_yaml_configuration(config, temp_config_file.name)
+        # Create dataset object
+        dataset = PVNetUKRegionalDataset(temp_config_file.name)
+
+        # Generate a sample
+        _ = dataset[0]