ocf-data-sampler 0.0.17__tar.gz → 0.0.19__tar.gz

{ocf_data_sampler-0.0.17/ocf_data_sampler.egg-info → ocf_data_sampler-0.0.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ocf_data_sampler
-Version: 0.0.17
+Version: 0.0.19
 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-0.0.17 → ocf_data_sampler-0.0.19}/ocf_data_sampler/numpy_batch/gsp.py

@@ -9,12 +9,9 @@ def convert_gsp_to_numpy_batch(da: xr.DataArray, t0_idx: int | None = None) -> N
 
     example: NumpyBatch = {
         BatchKey.gsp: da.values,
-        BatchKey.gsp_id: da.gsp_id.values,
         BatchKey.gsp_nominal_capacity_mwp: da.isel(time_utc=0)["nominal_capacity_mwp"].values,
         BatchKey.gsp_effective_capacity_mwp: da.isel(time_utc=0)["effective_capacity_mwp"].values,
         BatchKey.gsp_time_utc: da["time_utc"].values.astype(float),
-        BatchKey.gsp_x_osgb: da.x_osgb.item(),
-        BatchKey.gsp_y_osgb: da.y_osgb.item(),
     }
 
     if t0_idx is not None:

{ocf_data_sampler-0.0.17 → ocf_data_sampler-0.0.19}/ocf_data_sampler/torch_datasets/pvnet_uk_regional.py

@@ -69,7 +69,7 @@ def get_dataset_dict(config: Configuration) -> dict[xr.DataArray, dict[xr.DataAr
 
     # Load GSP data unless the path is None
     if in_config.gsp.gsp_zarr_path:
-        da_gsp = open_gsp(zarr_path=in_config.gsp.gsp_zarr_path)
+        da_gsp = open_gsp(zarr_path=in_config.gsp.gsp_zarr_path).compute()
 
         # Remove national GSP
         datasets_dict["gsp"] = da_gsp.sel(gsp_id=slice(1, None))
@@ -344,6 +344,24 @@ def slice_datasets_by_time(
     return sliced_datasets_dict
 
 
+def fill_nans_in_arrays(batch: NumpyBatch) -> NumpyBatch:
+    """Fills all NaN values in each np.ndarray in the batch dictionary with zeros.
+
+    Operation is performed in-place on the batch.
+    """
+    for k, v in batch.items():
+        if isinstance(v, np.ndarray) and np.issubdtype(v.dtype, np.number):
+            if np.isnan(v).any():
+                batch[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 batch
+
+
+
 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
@@ -385,6 +403,7 @@ def process_and_combine_datasets(
         numpy_modalities.append(convert_satellite_to_numpy_batch(da_sat))
 
     gsp_config = config.input_data.gsp
+    
     if "gsp" in dataset_dict:
         da_gsp = concat_xr_time_utc([dataset_dict["gsp"], dataset_dict["gsp_future"]])
         da_gsp = normalize_gsp(da_gsp)
@@ -406,9 +425,18 @@ def process_and_combine_datasets(
     lon, lat = osgb_to_lon_lat(location.x, location.y)
 
     numpy_modalities.append(make_sun_position_numpy_batch(datetimes, lon, lat))
-
-    # Combine all the modalities
+    
+    # Add coordinate data
+    # TODO: Do we need all of these?
+    numpy_modalities.append({
+        BatchKey.gsp_id: location.id,
+        BatchKey.gsp_x_osgb: location.x,
+        BatchKey.gsp_y_osgb: location.y,
+    })
+
+    # Combine all the modalities and fill NaNs
     combined_sample = merge_dicts(numpy_modalities)
+    combined_sample = fill_nans_in_arrays(combined_sample)
 
     return combined_sample
 
@@ -423,24 +451,12 @@ def compute(xarray_dict: dict) -> dict:
     return xarray_dict
 
 
-def get_locations(ga_gsp: xr.DataArray) -> list[Location]:
-    """Get list of locations of GSP"""
-    locations = []
-    for gsp_id in ga_gsp.gsp_id.values:
-        da = ga_gsp.sel(gsp_id=gsp_id)
-        locations.append(
-            Location(
-                coordinate_system = "osgb",
-                x=da.x_osgb.item(),
-                y=da.y_osgb.item(),
-                id=gsp_id,
-            )
-        )
-    return locations
-
-
-def get_gsp_locations() -> list[Location]:
+def get_gsp_locations(gsp_ids: list[int] | None = None) -> list[Location]:
     """Get list of locations of all GSPs"""
+    
+    if gsp_ids is None:
+        gsp_ids = [i for i in range(1, 318)]
+    
     locations = []
 
     # Load UK GSP locations
@@ -449,7 +465,7 @@ def get_gsp_locations() -> list[Location]:
         index_col="gsp_id",
     )
 
-    for gsp_id in np.arange(1, 318):
+    for gsp_id in gsp_ids:
         locations.append(
             Location(
                 coordinate_system = "osgb",
@@ -468,6 +484,7 @@ class PVNetUKRegionalDataset(Dataset):
         config_filename: str, 
         start_time: str | None = None,
         end_time: str| None = None,
+        gsp_ids: list[int] | None = None,
     ):
         """A torch Dataset for creating PVNet UK GSP samples
 
@@ -475,6 +492,7 @@ class PVNetUKRegionalDataset(Dataset):
             config_filename: Path to the configuration file
             start_time: Limit the init-times to be after this
             end_time: Limit the init-times to be before this
+            gsp_ids: List of GSP IDs to create samples for. Defaults to all
         """
         
         config = load_yaml_configuration(config_filename)
@@ -492,7 +510,7 @@ class PVNetUKRegionalDataset(Dataset):
             valid_t0_times = valid_t0_times[valid_t0_times<=pd.Timestamp(end_time)]
 
         # Construct list of locations to sample from
-        locations = get_gsp_locations()
+        locations = get_gsp_locations(gsp_ids)
 
         # Construct a lookup for locations - useful for users to construct sample by GSP ID
         location_lookup = {loc.id: loc for loc in locations}

{ocf_data_sampler-0.0.17 → ocf_data_sampler-0.0.19/ocf_data_sampler.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ocf_data_sampler
-Version: 0.0.17
+Version: 0.0.19
 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-0.0.17 → ocf_data_sampler-0.0.19}/setup.py

@@ -10,7 +10,7 @@ install_requires = (this_directory / "requirements.txt").read_text().splitlines(
 
 setup(
     name="ocf_data_sampler",
-    version="0.0.17",
+    version="0.0.19",
     license="MIT",
     description="Sample from weather data for renewable energy prediction",
     author="James Fulton, Peter Dudfield, and the Open Climate Fix team",