ocf-data-sampler 0.5.13__tar.gz → 0.5.14__tar.gz

{ocf_data_sampler-0.5.13 → ocf_data_sampler-0.5.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocf-data-sampler
-Version: 0.5.13
+Version: 0.5.14
 Author: James Fulton, Peter Dudfield
 Author-email: Open Climate Fix team <info@openclimatefix.org>
 License: MIT License

{ocf_data_sampler-0.5.13 → ocf_data_sampler-0.5.14}/ocf_data_sampler/config/model.py

@@ -172,23 +172,6 @@ class NormalisationConstantsMixin(Base):
     """Normalisation constants for multiple channels."""
     normalisation_constants: dict[str, NormalisationValues]
 
-    @property
-    def channel_means(self) -> dict[str, float]:
-        """Return the channel means."""
-        return {
-            channel: norm_values.mean
-            for channel, norm_values in self.normalisation_constants.items()
-        }
-
-
-    @property
-    def channel_stds(self) -> dict[str, float]:
-        """Return the channel standard deviations."""
-        return {
-            channel: norm_values.std
-            for channel, norm_values in self.normalisation_constants.items()
-        }
-
 
 class Satellite(TimeWindowMixin, DropoutMixin, SpatialWindowMixin, NormalisationConstantsMixin):
     """Satellite configuration model."""

{ocf_data_sampler-0.5.13 → ocf_data_sampler-0.5.14}/ocf_data_sampler/torch_datasets/datasets/pvnet_uk.py

@@ -137,10 +137,10 @@ class AbstractPVNetUKDataset(Dataset):
             for nwp_key, da_nwp in dataset_dict["nwp"].items():
 
                 # Standardise and convert to NumpyBatch
-                da_channel_means = self.means_dict["nwp"][nwp_key]
-                da_channel_stds = self.stds_dict["nwp"][nwp_key]
+                channel_means = self.means_dict["nwp"][nwp_key]
+                channel_stds = self.stds_dict["nwp"][nwp_key]
 
-                da_nwp = (da_nwp - da_channel_means) / da_channel_stds
+                da_nwp = (da_nwp - channel_means) / channel_stds
 
                 nwp_numpy_modalities[nwp_key] = convert_nwp_to_numpy_sample(da_nwp)
 
@@ -151,17 +151,17 @@ class AbstractPVNetUKDataset(Dataset):
             da_sat = dataset_dict["sat"]
 
             # Standardise and convert to NumpyBatch
-            da_channel_means = self.means_dict["sat"]
-            da_channel_stds = self.stds_dict["sat"]
+            channel_means = self.means_dict["sat"]
+            channel_stds = self.stds_dict["sat"]
 
-            da_sat = (da_sat - da_channel_means) / da_channel_stds
+            da_sat = (da_sat - channel_means) / channel_stds
 
             numpy_modalities.append(convert_satellite_to_numpy_sample(da_sat))
 
         if "gsp" in dataset_dict:
             gsp_config = self.config.input_data.gsp
             da_gsp = dataset_dict["gsp"]
-            da_gsp = da_gsp / da_gsp.effective_capacity_mwp
+            da_gsp = da_gsp / da_gsp.effective_capacity_mwp.values
 
             # Convert to NumpyBatch
             numpy_modalities.append(

{ocf_data_sampler-0.5.13 → ocf_data_sampler-0.5.14}/ocf_data_sampler/torch_datasets/datasets/site.py

@@ -82,10 +82,10 @@ def process_and_combine_datasets(
 
             # Standardise and convert to NumpyBatch
 
-            da_channel_means = means_dict["nwp"][nwp_key]
-            da_channel_stds = stds_dict["nwp"][nwp_key]
+            channel_means = means_dict["nwp"][nwp_key]
+            channel_stds = stds_dict["nwp"][nwp_key]
 
-            da_nwp = (da_nwp - da_channel_means) / da_channel_stds
+            da_nwp = (da_nwp - channel_means) / channel_stds
 
             nwp_numpy_modalities[nwp_key] = convert_nwp_to_numpy_sample(da_nwp)
 
@@ -96,16 +96,16 @@ def process_and_combine_datasets(
         da_sat = dataset_dict["sat"]
 
         # Standardise and convert to NumpyBatch
-        da_channel_means = means_dict["sat"]
-        da_channel_stds = stds_dict["sat"]
+        channel_means = means_dict["sat"]
+        channel_stds = stds_dict["sat"]
 
-        da_sat = (da_sat - da_channel_means) / da_channel_stds
+        da_sat = (da_sat - channel_means) / channel_stds
 
         numpy_modalities.append(convert_satellite_to_numpy_sample(da_sat))
 
     if "site" in dataset_dict:
         da_sites = dataset_dict["site"]
-        da_sites = da_sites / da_sites.capacity_kwp
+        da_sites = da_sites / da_sites.capacity_kwp.values
 
         # Convert to NumpyBatch
         numpy_modalities.append(convert_site_to_numpy_sample(da_sites))

ocf_data_sampler-0.5.14/ocf_data_sampler/torch_datasets/utils/config_normalization_values_to_dicts.py

@@ -0,0 +1,59 @@
+"""Utility function for converting normalisation constants in the config to arrays."""
+
+import numpy as np
+
+from ocf_data_sampler.config import Configuration
+
+
+def config_normalization_values_to_dicts(
+    config: Configuration,
+) -> tuple[dict[str, np.ndarray | dict[str, np.ndarray]]]:
+    """Construct numpy arrays of mean and std values from the config normalisation constants.
+
+    Args:
+        config: Data configuration.
+
+    Returns:
+        Means dict
+        Stds dict
+    """
+    means_dict = {}
+    stds_dict = {}
+
+    if config.input_data.nwp is not None:
+
+        means_dict["nwp"] = {}
+        stds_dict["nwp"] = {}
+
+        for nwp_key in config.input_data.nwp:
+            nwp_config = config.input_data.nwp[nwp_key]
+
+            means_list = []
+            stds_list = []
+
+            for channel in list(nwp_config.channels):
+                # These accumulated channels are diffed and renamed
+                if channel in nwp_config.accum_channels:
+                    channel =f"diff_{channel}"
+
+                means_list.append(nwp_config.normalisation_constants[channel].mean)
+                stds_list.append(nwp_config.normalisation_constants[channel].std)
+
+            means_dict["nwp"][nwp_key] = np.array(means_list)[None, :, None, None]
+            stds_dict["nwp"][nwp_key] = np.array(stds_list)[None, :, None, None]
+
+    if config.input_data.satellite is not None:
+        sat_config = config.input_data.satellite
+
+        means_list = []
+        stds_list = []
+
+        for channel in list(config.input_data.satellite.channels):
+            means_list.append(sat_config.normalisation_constants[channel].mean)
+            stds_list.append(sat_config.normalisation_constants[channel].std)
+
+        # Convert to array and expand dimensions so we can normalise the 4D sat and NWP sources
+        means_dict["sat"] = np.array(means_list)[None, :, None, None]
+        stds_dict["sat"] = np.array(stds_list)[None, :, None, None]
+
+    return means_dict, stds_dict

{ocf_data_sampler-0.5.13 → ocf_data_sampler-0.5.14}/ocf_data_sampler.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocf-data-sampler
-Version: 0.5.13
+Version: 0.5.14
 Author: James Fulton, Peter Dudfield
 Author-email: Open Climate Fix team <info@openclimatefix.org>
 License: MIT License

ocf_data_sampler-0.5.13/ocf_data_sampler/torch_datasets/utils/config_normalization_values_to_dicts.py

@@ -1,57 +0,0 @@
-"""Utility function for converting channel dictionaries to xarray DataArrays."""
-
-import xarray as xr
-
-from ocf_data_sampler.config import Configuration
-
-
-def channel_dict_to_dataarray(channel_dict: dict[str, float]) -> xr.DataArray:
-    """Converts a dictionary of channel values to a DataArray.
-
-    Args:
-        channel_dict: Dictionary mapping channel names (str) to their values (float).
-
-    Returns:
-        xr.DataArray: A 1D DataArray with channels as coordinates.
-    """
-    return xr.DataArray(
-        list(channel_dict.values()),
-        coords={"channel": list(channel_dict.keys())},
-    )
-
-def config_normalization_values_to_dicts(
-    config: Configuration,
-) -> tuple[dict[str, xr.DataArray | dict[str, xr.DataArray]]]:
-    """Construct DataArrays of mean and std values from the config normalisation constants.
-
-    Args:
-        config: Data configuration.
-
-    Returns:
-        Means dict
-        Stds dict
-    """
-    means_dict = {}
-    stds_dict = {}
-
-    if config.input_data.nwp is not None:
-
-        means_dict["nwp"] = {}
-        stds_dict["nwp"] = {}
-
-        for nwp_key in config.input_data.nwp:
-            # Standardise and convert to NumpyBatch
-
-            means_dict["nwp"][nwp_key] = channel_dict_to_dataarray(
-                config.input_data.nwp[nwp_key].channel_means,
-            )
-            stds_dict["nwp"][nwp_key] = channel_dict_to_dataarray(
-                config.input_data.nwp[nwp_key].channel_stds,
-            )
-
-    if config.input_data.satellite is not None:
-
-        means_dict["sat"] = channel_dict_to_dataarray(config.input_data.satellite.channel_means)
-        stds_dict["sat"] = channel_dict_to_dataarray(config.input_data.satellite.channel_stds)
-
-    return means_dict, stds_dict