ocf-data-sampler 0.0.45__tar.gz → 0.0.46__tar.gz

{ocf_data_sampler-0.0.45/ocf_data_sampler.egg-info → ocf_data_sampler-0.0.46}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ocf_data_sampler
-Version: 0.0.45
+Version: 0.0.46
 Summary: Sample from weather data for renewable energy prediction
 Author: James Fulton, Peter Dudfield, and the Open Climate Fix team
 Author-email: info@openclimatefix.org

{ocf_data_sampler-0.0.45 → ocf_data_sampler-0.0.46}/ocf_data_sampler/config/save.py

@@ -9,7 +9,6 @@ Example:
 """
 
 import json
-
 from pathlib import Path
 from typing import Union
 
@@ -18,7 +17,6 @@ import yaml
 
 from ocf_data_sampler.config import Configuration
 
-
 def save_yaml_configuration(
     configuration: Configuration,
     filename: Union[str, Path],
@@ -35,7 +33,7 @@ def save_yaml_configuration(
         Path: The path where the configuration was saved
 
     Raises:
-        ValueError: If filename is None or if writing to the specified path fails
+        ValueError: If filename is None, directory doesn't exist, or if writing to the specified path fails
         TypeError: If the configuration cannot be serialized
     """
     if filename is None:
@@ -50,24 +48,37 @@ def save_yaml_configuration(
 
         filepath = Path(filename)
 
-        # For local files, check if directory exists before proceeding
+        # For local paths, check if parent directory exists before attempting to create
         if filepath.is_absolute():
-            directory = filepath.parent
-            if not directory.exists():
+            if not filepath.parent.exists():
                 raise ValueError("Directory does not exist")
+            
+            # Only try to create directory if it's in a writable location
+            try:
+                filepath.parent.mkdir(parents=True, exist_ok=True)
+            except PermissionError:
+                raise ValueError(f"Permission denied when accessing directory {filepath.parent}")
 
         # Serialize configuration to JSON-compatible dictionary
         config_dict = json.loads(configuration.model_dump_json())
 
-        # Save to YAML file using fsspec
-        with fsspec.open(str(filepath), mode='w') as yaml_file:
-            yaml.safe_dump(config_dict, yaml_file, default_flow_style=False)
+        # Write to file directly for local paths
+        if filepath.is_absolute():
+            try:
+                with open(filepath, 'w') as f:
+                    yaml.safe_dump(config_dict, f, default_flow_style=False)
+            except PermissionError:
+                raise ValueError(f"Permission denied when writing to {filename}")
+        else:
+            # Use fsspec for cloud storage
+            with fsspec.open(str(filepath), mode='w') as yaml_file:
+                yaml.safe_dump(config_dict, yaml_file, default_flow_style=False)
 
         return filepath
 
     except json.JSONDecodeError as e:
         raise TypeError(f"Failed to serialize configuration: {str(e)}") from e
-    except PermissionError as e:
-        raise ValueError(f"Permission denied when writing to {filename}") from e
     except (IOError, OSError) as e:
+        if "Permission denied" in str(e):
+            raise ValueError(f"Permission denied when writing to {filename}") from e
         raise ValueError(f"Failed to write configuration to {filename}: {str(e)}") from e

{ocf_data_sampler-0.0.45/ocf_data_sampler/torch_datasets → ocf_data_sampler-0.0.46/ocf_data_sampler/torch_datasets/datasets}/pvnet_uk_regional.py

@@ -5,16 +5,114 @@ import pandas as pd
 import pkg_resources
 import xarray as xr
 from torch.utils.data import Dataset
-
 from ocf_data_sampler.config import Configuration, load_yaml_configuration
 from ocf_data_sampler.load.load_dataset import get_dataset_dict
 from ocf_data_sampler.select import fill_time_periods, Location, slice_datasets_by_space, slice_datasets_by_time
 from ocf_data_sampler.utils import minutes
-from ocf_data_sampler.torch_datasets.process_and_combine import process_and_combine_datasets, compute
-from ocf_data_sampler.torch_datasets.valid_time_periods import find_valid_time_periods
+from ocf_data_sampler.torch_datasets.utils.valid_time_periods import find_valid_time_periods
+from ocf_data_sampler.constants import NWP_MEANS, NWP_STDS, RSS_MEAN, RSS_STD
+from ocf_data_sampler.numpy_sample import (
+    convert_nwp_to_numpy_sample,
+    convert_satellite_to_numpy_sample,
+    convert_gsp_to_numpy_sample,
+    make_sun_position_numpy_sample,
+)
+from ocf_data_sampler.torch_datasets.utils.merge_and_fill_utils import (
+    merge_dicts,
+    fill_nans_in_arrays,
+)
+from ocf_data_sampler.numpy_sample.gsp import GSPSampleKey
+from ocf_data_sampler.numpy_sample.nwp import NWPSampleKey
+from ocf_data_sampler.select.geospatial import osgb_to_lon_lat
 
 xr.set_options(keep_attrs=True)
 
+def process_and_combine_datasets(
+    dataset_dict: dict,
+    config: Configuration,
+    t0: pd.Timestamp,
+    location: Location,
+    target_key: str = 'gsp'
+) -> dict:
+
+    """Normalise and convert data to numpy arrays"""
+    numpy_modalities = []
+
+    if "nwp" in dataset_dict:
+
+        nwp_numpy_modalities = dict()
+
+        for nwp_key, da_nwp in dataset_dict["nwp"].items():
+            # Standardise
+            provider = config.input_data.nwp[nwp_key].provider
+            da_nwp = (da_nwp - NWP_MEANS[provider]) / NWP_STDS[provider]
+
+            # Convert to NumpyBatch
+            nwp_numpy_modalities[nwp_key] = convert_nwp_to_numpy_sample(da_nwp)
+
+        # Combine the NWPs into NumpyBatch
+        numpy_modalities.append({NWPSampleKey.nwp: nwp_numpy_modalities})
+
+
+    if "sat" in dataset_dict:
+        # Standardise
+        da_sat = dataset_dict["sat"]
+        da_sat = (da_sat - RSS_MEAN) / RSS_STD
+
+        # Convert to NumpyBatch
+        numpy_modalities.append(convert_satellite_to_numpy_sample(da_sat))
+
+    gsp_config = config.input_data.gsp
+
+    if "gsp" in dataset_dict:
+        da_gsp = xr.concat([dataset_dict["gsp"], dataset_dict["gsp_future"]], dim="time_utc")
+        da_gsp = da_gsp / da_gsp.effective_capacity_mwp
+
+        numpy_modalities.append(
+            convert_gsp_to_numpy_sample(
+                da_gsp, 
+                t0_idx=-gsp_config.interval_start_minutes / gsp_config.time_resolution_minutes
+            )
+        )
+
+        # Add coordinate data
+        # TODO: Do we need all of these?
+        numpy_modalities.append(
+            {
+                GSPSampleKey.gsp_id: location.id,
+                GSPSampleKey.x_osgb: location.x,
+                GSPSampleKey.y_osgb: location.y,
+            }
+        )
+
+    if target_key == 'gsp':
+        # Make sun coords NumpySample
+        datetimes = pd.date_range(
+            t0+minutes(gsp_config.interval_start_minutes),
+            t0+minutes(gsp_config.interval_end_minutes),
+            freq=minutes(gsp_config.time_resolution_minutes),
+        )
+
+        lon, lat = osgb_to_lon_lat(location.x, location.y)
+
+    numpy_modalities.append(
+        make_sun_position_numpy_sample(datetimes, lon, lat, key_prefix=target_key)
+    )
+
+    # Combine all the modalities and fill NaNs
+    combined_sample = merge_dicts(numpy_modalities)
+    combined_sample = fill_nans_in_arrays(combined_sample)
+
+    return combined_sample
+
+def compute(xarray_dict: dict) -> dict:
+    """Eagerly load a nested dictionary of xarray DataArrays"""
+    for k, v in xarray_dict.items():
+        if isinstance(v, dict):
+            xarray_dict[k] = compute(v)
+        else:
+            xarray_dict[k] = v.compute(scheduler="single-threaded")
+    return xarray_dict
 
 def find_valid_t0_times(
     datasets_dict: dict,
@@ -48,7 +146,7 @@ def get_gsp_locations(gsp_ids: list[int] | None = None) -> list[Location]:
 
     # Load UK GSP locations
     df_gsp_loc = pd.read_csv(
-        pkg_resources.resource_filename(__name__, "../data/uk_gsp_locations.csv"),
+        pkg_resources.resource_filename(__name__, "../../data/uk_gsp_locations.csv"),
         index_col="gsp_id",
     )
 

{ocf_data_sampler-0.0.45/ocf_data_sampler/torch_datasets → ocf_data_sampler-0.0.46/ocf_data_sampler/torch_datasets/datasets}/site.py

@@ -17,8 +17,8 @@ from ocf_data_sampler.select import (
     slice_datasets_by_time, slice_datasets_by_space
 )
 from ocf_data_sampler.utils import minutes
-from ocf_data_sampler.torch_datasets.valid_time_periods import find_valid_time_periods
-from ocf_data_sampler.torch_datasets.process_and_combine import merge_dicts, fill_nans_in_arrays
+from ocf_data_sampler.torch_datasets.utils.valid_time_periods import find_valid_time_periods
+from ocf_data_sampler.torch_datasets.utils.merge_and_fill_utils import merge_dicts, fill_nans_in_arrays
 from ocf_data_sampler.numpy_sample import (
     convert_site_to_numpy_sample, 
     convert_satellite_to_numpy_sample, 

ocf_data_sampler-0.0.46/ocf_data_sampler/torch_datasets/utils/merge_and_fill_utils.py

@@ -0,0 +1,25 @@
+import numpy as np
+
+def merge_dicts(list_of_dicts: list[dict]) -> dict:
+    """Merge a list of dictionaries into a single dictionary"""
+    # TODO: This doesn't account for duplicate keys, which will be overwritten
+    combined_dict = {}
+    for d in list_of_dicts:
+        combined_dict.update(d)
+    return combined_dict
+
+def fill_nans_in_arrays(sample: dict) -> dict:
+    """Fills all NaN values in each np.ndarray in the sample dictionary with zeros.
+
+    Operation is performed in-place on the sample.
+    """
+    for k, v in sample.items():
+        if isinstance(v, np.ndarray) and np.issubdtype(v.dtype, np.number):
+            if np.isnan(v).any():
+                sample[k] = np.nan_to_num(v, copy=False, nan=0.0)
+
+        # Recursion is included to reach NWP arrays in subdict
+        elif isinstance(v, dict):
+            fill_nans_in_arrays(v)
+
+    return sample

{ocf_data_sampler-0.0.45 → ocf_data_sampler-0.0.46/ocf_data_sampler.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ocf_data_sampler
-Version: 0.0.45
+Version: 0.0.46
 Summary: Sample from weather data for renewable energy prediction
 Author: James Fulton, Peter Dudfield, and the Open Climate Fix team
 Author-email: info@openclimatefix.org

{ocf_data_sampler-0.0.45 → ocf_data_sampler-0.0.46}/ocf_data_sampler.egg-info/SOURCES.txt

@@ -45,11 +45,11 @@ ocf_data_sampler/select/select_spatial_slice.py
 ocf_data_sampler/select/select_time_slice.py
 ocf_data_sampler/select/spatial_slice_for_dataset.py
 ocf_data_sampler/select/time_slice_for_dataset.py
-ocf_data_sampler/torch_datasets/__init__.py
-ocf_data_sampler/torch_datasets/process_and_combine.py
-ocf_data_sampler/torch_datasets/pvnet_uk_regional.py
-ocf_data_sampler/torch_datasets/site.py
-ocf_data_sampler/torch_datasets/valid_time_periods.py
+ocf_data_sampler/torch_datasets/datasets/__init__.py
+ocf_data_sampler/torch_datasets/datasets/pvnet_uk_regional.py
+ocf_data_sampler/torch_datasets/datasets/site.py
+ocf_data_sampler/torch_datasets/utils/merge_and_fill_utils.py
+ocf_data_sampler/torch_datasets/utils/valid_time_periods.py
 scripts/refactor_site.py
 tests/__init__.py
 tests/conftest.py
@@ -72,6 +72,6 @@ tests/select/test_location.py
 tests/select/test_select_spatial_slice.py
 tests/select/test_select_time_slice.py
 tests/torch_datasets/conftest.py
-tests/torch_datasets/test_process_and_combine.py
+tests/torch_datasets/test_merge_and_fill_utils.py
 tests/torch_datasets/test_pvnet_uk_regional.py
 tests/torch_datasets/test_site.py

{ocf_data_sampler-0.0.45 → ocf_data_sampler-0.0.46}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ocf_data_sampler"
-version = "0.0.45"
+version = "0.0.46"
 license = { file = "LICENSE" }
 readme = "README.md"
 description = "Sample from weather data for renewable energy prediction"

{ocf_data_sampler-0.0.45 → ocf_data_sampler-0.0.46}/tests/config/test_config.py

@@ -2,7 +2,7 @@ import tempfile
 
 import pytest
 from pydantic import ValidationError
-
+from pathlib import Path
 from ocf_data_sampler.config import (
     load_yaml_configuration,
     Configuration,
@@ -21,39 +21,37 @@ def test_load_yaml_configuration(test_config_filename):
     Test that yaml loading works for 'test_config.yaml'
     and fails for an empty .yaml file
     """
-
-    # check we get an error if loading a file with no config
-    with tempfile.NamedTemporaryFile(suffix=".yaml") as fp:
-        filename = fp.name
-
-        # check that temp file can't be loaded
+    # Create temporary directory instead of file
+    with tempfile.TemporaryDirectory() as temp_dir:
+        # Create path for empty file
+        empty_file = Path(temp_dir) / "empty.yaml"
+        
+        # Create an empty file
+        empty_file.touch()
+        
+        # Test loading empty file
         with pytest.raises(TypeError):
-            _ = load_yaml_configuration(filename)
-
-    # test can load test_config.yaml
-    config = load_yaml_configuration(test_config_filename)
-
-    assert isinstance(config, Configuration)
-
+            _ = load_yaml_configuration(str(empty_file))
 
 def test_yaml_save(test_config_filename):
     """
     Check configuration can be saved to a .yaml file
     """
-
     test_config = load_yaml_configuration(test_config_filename)
-
-    with tempfile.NamedTemporaryFile(suffix=".yaml") as fp:
-        filename = fp.name
-
-        # save default config to file
-        save_yaml_configuration(test_config, filename)
-
-        # check the file can be loaded back
-        tmp_config = load_yaml_configuration(filename)
-
-        # check loaded configuration is the same as the one passed to save
-        assert test_config == tmp_config
+    
+    with tempfile.TemporaryDirectory() as temp_dir:
+        # Create path for config file
+        config_path = Path(temp_dir) / "test_config.yaml"
+        
+        # Save configuration
+        saved_path = save_yaml_configuration(test_config, config_path)
+        
+        # Verify file exists
+        assert saved_path.exists()
+        
+        # Test loading saved configuration
+        loaded_config = load_yaml_configuration(str(saved_path))
+        assert loaded_config == test_config
 
 
 def test_extra_field_error():

{ocf_data_sampler-0.0.45 → ocf_data_sampler-0.0.46}/tests/conftest.py

@@ -1,10 +1,10 @@
 import os
-
 import numpy as np
 import pandas as pd
 import pytest
 import xarray as xr
 import tempfile
+from typing import Generator
 
 from ocf_data_sampler.config.model import Site
 from ocf_data_sampler.config import load_yaml_configuration, save_yaml_configuration
@@ -201,7 +201,7 @@ def ds_uk_gsp():
 
 
 @pytest.fixture(scope="session")
-def data_sites() -> Site:
+def data_sites() -> Generator[Site, None, None]:
     """
     Make fake data for sites
     Returns: filename for netcdf file, and csv metadata

{ocf_data_sampler-0.0.45 → ocf_data_sampler-0.0.46}/tests/numpy_sample/test_collate.py

@@ -1,6 +1,6 @@
 from ocf_data_sampler.numpy_sample import GSPSampleKey, SatelliteSampleKey
 from ocf_data_sampler.numpy_sample.collate import stack_np_samples_into_batch
-from ocf_data_sampler.torch_datasets import PVNetUKRegionalDataset
+from ocf_data_sampler.torch_datasets.datasets.pvnet_uk_regional import PVNetUKRegionalDataset
 
 
 def test_pvnet(pvnet_config_filename):

ocf_data_sampler-0.0.46/tests/torch_datasets/test_merge_and_fill_utils.py

@@ -0,0 +1,42 @@
+import numpy as np
+
+from ocf_data_sampler.torch_datasets.utils.merge_and_fill_utils import (
+    merge_dicts,
+    fill_nans_in_arrays,
+)
+
+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"
+
+

ocf_data_sampler-0.0.45/tests/torch_datasets/test_process_and_combine.py → ocf_data_sampler-0.0.46/tests/torch_datasets/test_pvnet_uk_regional.py

@@ -2,19 +2,14 @@ import numpy as np
 import pandas as pd
 import xarray as xr
 import dask.array as da
+import tempfile
 
-from ocf_data_sampler.config import load_yaml_configuration
-from ocf_data_sampler.select.location import Location
+from ocf_data_sampler.torch_datasets.datasets.pvnet_uk_regional import PVNetUKRegionalDataset
+from ocf_data_sampler.config.save import save_yaml_configuration
+from ocf_data_sampler.config.load import load_yaml_configuration
 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,
-)
-
+from ocf_data_sampler.torch_datasets.datasets.pvnet_uk_regional import process_and_combine_datasets, compute
+from ocf_data_sampler.select.location import Location
 
 def test_process_and_combine_datasets(pvnet_config_filename):
 
@@ -60,42 +55,6 @@ def test_process_and_combine_datasets(pvnet_config_filename):
     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)))
@@ -124,3 +83,54 @@ def test_compute():
     # 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()
+
+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]

{ocf_data_sampler-0.0.45 → ocf_data_sampler-0.0.46}/tests/torch_datasets/test_site.py

@@ -1,8 +1,6 @@
 import pandas as pd
-
-from ocf_data_sampler.torch_datasets import SitesDataset
-from ocf_data_sampler.torch_datasets.site import convert_from_dataset_to_dict_datasets
 import numpy as np
+from ocf_data_sampler.torch_datasets.datasets.site import SitesDataset, convert_from_dataset_to_dict_datasets
 from xarray import Dataset, DataArray
 
 

ocf_data_sampler-0.0.45/ocf_data_sampler/torch_datasets/process_and_combine.py

@@ -1,132 +0,0 @@
-import numpy as np
-import pandas as pd
-import xarray as xr
-from typing import Optional
-
-from ocf_data_sampler.config import Configuration
-from ocf_data_sampler.constants import NWP_MEANS, NWP_STDS,RSS_MEAN,RSS_STD
-from ocf_data_sampler.numpy_sample import (
-    convert_nwp_to_numpy_sample,
-    convert_satellite_to_numpy_sample,
-    convert_gsp_to_numpy_sample,
-    make_sun_position_numpy_sample,
-
-)
-from ocf_data_sampler.numpy_sample.gsp import GSPSampleKey
-from ocf_data_sampler.numpy_sample.nwp import NWPSampleKey
-from ocf_data_sampler.select.geospatial import osgb_to_lon_lat
-from ocf_data_sampler.select.location import Location
-from ocf_data_sampler.utils import minutes
-
-
-def process_and_combine_datasets(
-    dataset_dict: dict,
-    config: Configuration,
-    t0: Optional[pd.Timestamp] = None,
-    location: Optional[Location] = None,
-    target_key: str = 'gsp'
-) -> dict:
-
-    """Normalise and convert data to numpy arrays"""
-    numpy_modalities = []
-
-    if "nwp" in dataset_dict:
-
-        nwp_numpy_modalities = dict()
-
-        for nwp_key, da_nwp in dataset_dict["nwp"].items():
-            # Standardise
-            provider = config.input_data.nwp[nwp_key].provider
-            da_nwp = (da_nwp - NWP_MEANS[provider]) / NWP_STDS[provider]
-            # Convert to NumpySample
-            nwp_numpy_modalities[nwp_key] = convert_nwp_to_numpy_sample(da_nwp)
-
-        # Combine the NWPs into NumpySample
-        numpy_modalities.append({NWPSampleKey.nwp: nwp_numpy_modalities})
-
-
-    if "sat" in dataset_dict:
-        # Standardise
-        da_sat = dataset_dict["sat"]
-        da_sat = (da_sat - RSS_MEAN) / RSS_STD
-
-        # Convert to NumpySample
-        numpy_modalities.append(convert_satellite_to_numpy_sample(da_sat))
-
-
-    gsp_config = config.input_data.gsp
-
-    if "gsp" in dataset_dict:
-        da_gsp = xr.concat([dataset_dict["gsp"], dataset_dict["gsp_future"]], dim="time_utc")
-        da_gsp = da_gsp / da_gsp.effective_capacity_mwp
-
-        numpy_modalities.append(
-            convert_gsp_to_numpy_sample(
-                da_gsp, 
-                t0_idx=-gsp_config.interval_start_minutes / gsp_config.time_resolution_minutes
-            )
-        )
-
-        # Add coordinate data
-        # TODO: Do we need all of these?
-        numpy_modalities.append(
-            {
-                GSPSampleKey.gsp_id: location.id,
-                GSPSampleKey.x_osgb: location.x,
-                GSPSampleKey.y_osgb: location.y,
-            }
-        )
-
-    if target_key == 'gsp':
-        # Make sun coords NumpySample
-        datetimes = pd.date_range(
-            t0+minutes(gsp_config.interval_start_minutes),
-            t0+minutes(gsp_config.interval_end_minutes),
-            freq=minutes(gsp_config.time_resolution_minutes),
-        )
-
-        lon, lat = osgb_to_lon_lat(location.x, location.y)
-
-    numpy_modalities.append(
-        make_sun_position_numpy_sample(datetimes, lon, lat, key_prefix=target_key)
-    )
-
-    # Combine all the modalities and fill NaNs
-    combined_sample = merge_dicts(numpy_modalities)
-    combined_sample = fill_nans_in_arrays(combined_sample)
-
-    return combined_sample
-
-def merge_dicts(list_of_dicts: list[dict]) -> dict:
-    """Merge a list of dictionaries into a single dictionary"""
-    # TODO: This doesn't account for duplicate keys, which will be overwritten
-    combined_dict = {}
-    for d in list_of_dicts:
-        combined_dict.update(d)
-    return combined_dict
-
-def fill_nans_in_arrays(sample: dict) -> dict:
-    """Fills all NaN values in each np.ndarray in the sample dictionary with zeros.
-
-    Operation is performed in-place on the sample.
-    """
-    for k, v in sample.items():
-        if isinstance(v, np.ndarray) and np.issubdtype(v.dtype, np.number):
-            if np.isnan(v).any():
-                sample[k] = np.nan_to_num(v, copy=False, nan=0.0)
-
-        # Recursion is included to reach NWP arrays in subdict
-        elif isinstance(v, dict):
-            fill_nans_in_arrays(v)
-
-    return sample
-
-
-def compute(xarray_dict: dict) -> dict:
-    """Eagerly load a nested dictionary of xarray DataArrays"""
-    for k, v in xarray_dict.items():
-        if isinstance(v, dict):
-            xarray_dict[k] = compute(v)
-        else:
-            xarray_dict[k] = v.compute(scheduler="single-threaded")
-    return xarray_dict

ocf_data_sampler-0.0.45/tests/torch_datasets/test_pvnet_uk_regional.py

@@ -1,59 +0,0 @@
-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]