ocf-data-sampler 0.1.11__py3-none-any.whl → 0.1.16__py3-none-any.whl

ocf_data_sampler/torch_datasets/utils/validate_channels.py

@@ -1,4 +1,4 @@
-import xarray as xr
+"""Functions for checking that normalisation statistics exist for the data channels requested."""
 
 from ocf_data_sampler.config import Configuration
 from ocf_data_sampler.constants import NWP_MEANS, NWP_STDS, RSS_MEAN, RSS_STD
@@ -8,10 +8,9 @@ def validate_channels(
     data_channels: list,
     means_channels: list,
     stds_channels: list,
-    source_name: str | None = None
+    source_name: str | None = None,
 ) -> None:
-    """
-    Validates that all channels in data have corresponding normalisation constants.
+    """Validates that all channels in data have corresponding normalisation constants.
 
     Args:
         data_channels: Set of channels from the data
@@ -22,7 +21,6 @@ def validate_channels(
     Raises:
         ValueError: If there's a mismatch between data channels and normalisation constants
     """
-
     data_set = set(data_channels)
     means_set = set(means_channels)
     stds_set = set(stds_channels)
@@ -32,51 +30,57 @@ def validate_channels(
     if missing_in_means:
         raise ValueError(
             f"The following channels for {source_name} are missing in normalisation means: "
-            f"{missing_in_means}"
+            f"{missing_in_means}",
         )
-            
+
     # Find missing channels in stds
     missing_in_stds = data_set - stds_set
     if missing_in_stds:
         raise ValueError(
             f"The following channels for {source_name} are missing in normalisation stds: "
-            f"{missing_in_stds}"
+            f"{missing_in_stds}",
         )
 
 
 def validate_nwp_channels(config: Configuration) -> None:
     """Validate that NWP channels in config have corresponding normalisation constants.
-    
+
     Args:
         config: Configuration object containing NWP channel information
-        
+
     Raises:
-        ValueError: If there's a mismatch between configured NWP channels and normalisation constants
+        ValueError: If there's a mismatch between configured NWP channels
+        and normalisation constants
     """
-    if hasattr(config.input_data, "nwp"):
-        for nwp_key, nwp_config in config.input_data.nwp.items():
+    if hasattr(config.input_data, "nwp") and (
+        config.input_data.nwp is not None
+        ):
+        for _, nwp_config in config.input_data.nwp.items():
             provider = nwp_config.provider
             validate_channels(
                 data_channels=nwp_config.channels,
                 means_channels=NWP_MEANS[provider].channel.values,
                 stds_channels=NWP_STDS[provider].channel.values,
-                source_name=provider
+                source_name=provider,
             )
 
 
 def validate_satellite_channels(config: Configuration) -> None:
     """Validate that satellite channels in config have corresponding normalisation constants.
-    
+
     Args:
         config: Configuration object containing satellite channel information
-        
+
     Raises:
-        ValueError: If there's a mismatch between configured satellite channels and normalisation constants
+        ValueError: If there's a mismatch between configured satellite channels
+        and normalisation constants
     """
-    if hasattr(config.input_data, "satellite"):
+    if hasattr(config.input_data, "satellite") and (
+        config.input_data.satellite is not None
+        ):
         validate_channels(
             data_channels=config.input_data.satellite.channels,
             means_channels=RSS_MEAN.channel.values,
             stds_channels=RSS_STD.channel.values,
-            source_name="satellite"
+            source_name="satellite",
         )

ocf_data_sampler/utils.py

@@ -1,8 +1,10 @@
+"""Miscellaneous helper functions."""
+
 import pandas as pd
 
 
 def minutes(minutes: int | list[float]) -> pd.Timedelta | pd.TimedeltaIndex:
-    """Timedelta minutes
+    """Timedelta minutes.
 
     Args:
         minutes: the number of minutes, single value or list

{ocf_data_sampler-0.1.11.dist-info → ocf_data_sampler-0.1.16.dist-info}/METADATA

@@ -1,10 +1,8 @@
 Metadata-Version: 2.2
-Name: ocf_data_sampler
-Version: 0.1.11
-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
-Maintainer: Open Climate Fix Ltd
+Name: ocf-data-sampler
+Version: 0.1.16
+Author: James Fulton, Peter Dudfield
+Author-email: Open Climate Fix team <info@openclimatefix.org>
 License: MIT License
         
         Copyright (c) 2023 Open Climate Fix
@@ -27,21 +25,18 @@ License: MIT License
         OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
         SOFTWARE.
         
-Project-URL: homepage, https://github.com/openclimatefix
 Project-URL: repository, https://github.com/openclimatefix/ocf-data-sampler
-Keywords: weather data,renewable energy prediction,sample weather data
+Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Operating System :: POSIX :: Linux
-Requires-Python: >=3.8
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
-License-File: LICENSE
 Requires-Dist: torch
 Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: xarray
 Requires-Dist: zarr==2.18.3
 Requires-Dist: dask
+Requires-Dist: matplotlib
 Requires-Dist: ocf_blosc2
 Requires-Dist: pvlib
 Requires-Dist: pydantic
@@ -50,11 +45,6 @@ Requires-Dist: pathy
 Requires-Dist: pyaml_env
 Requires-Dist: pyresample
 Requires-Dist: h5netcdf
-Provides-Extra: docs
-Requires-Dist: mkdocs>=1.2; extra == "docs"
-Requires-Dist: mkdocs-material>=8.0; extra == "docs"
-Provides-Extra: plot
-Requires-Dist: matplotlib; extra == "plot"
 
 # ocf-data-sampler
  
@@ -77,7 +67,6 @@ We are currently migrating to this repo from [ocf_datapipes](https://github.com/
 
 **ocf-data-sampler** doesn't have external documentation _yet_; you can read a bit about how our torch datasets work in the README [here](ocf_data_sampler/torch_datasets/README.md).
 
-
 ## FAQ
 
 If you have any questions about this or any other of our repos, don't hesitate to hop to our [Discussions Page](https://github.com/orgs/openclimatefix/discussions)!

ocf_data_sampler-0.1.16.dist-info/RECORD

@@ -0,0 +1,56 @@
+ocf_data_sampler/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+ocf_data_sampler/constants.py,sha256=scyqNXgmbMmZNs9TyIJ-omOOvE0SaPf-UvPxUG7SaSo,8074
+ocf_data_sampler/utils.py,sha256=DjuneGGisl08ENvPZV_lrcX4b2NCKJC1ZpXgIpxuQi4,290
+ocf_data_sampler/config/__init__.py,sha256=O29mbH0XG2gIY1g3BaveGCnpBO2SFqdu-qzJ7a6evl0,223
+ocf_data_sampler/config/load.py,sha256=LL-7wemI8o4KPkx35j-wQ3HjsMvDgqXr7G46IcASfnU,632
+ocf_data_sampler/config/model.py,sha256=LSdBe89nGTzYceA7-Pxc2wHj7HkpghiaM4fUsHUqeT8,7381
+ocf_data_sampler/config/save.py,sha256=m8SPw5rXjkMm1rByjh3pK5StdBi4e8ysnn3jQopdRaI,1064
+ocf_data_sampler/data/uk_gsp_locations.csv,sha256=RSh7DRh55E3n8lVAaWXGTaXXHevZZtI58td4d4DhGos,10415772
+ocf_data_sampler/load/__init__.py,sha256=T5Zj1PGt0aiiNEN7Ra1Ac-cBsNKhphmmHy_8g7XU_w0,219
+ocf_data_sampler/load/gsp.py,sha256=keB3Nv_CNK1P6pS9Kdfc8PoZXTI1_YFN-spsvEv_Ewc,899
+ocf_data_sampler/load/load_dataset.py,sha256=0NyDxCDfgE_esKVW3s-rZEe16WB30FQ74ClWlrIo72M,1602
+ocf_data_sampler/load/satellite.py,sha256=E7Ln7Y60Qr1RTV-_R71YoxXQM-Ca7Y1faIo3oKB2eFk,2292
+ocf_data_sampler/load/site.py,sha256=zOzlWk6pYZBB5daqG8URGksmDXWKrkutUvN8uALAIh8,1468
+ocf_data_sampler/load/utils.py,sha256=Jwbr1rpEa3cefjw-OTVRaxnIHyGixYB3TlTlta0BOdU,1727
+ocf_data_sampler/load/nwp/__init__.py,sha256=SmcrnbygO5xtCKmGR4wtHrj-HI7nOAvnAtfuvRufBGQ,25
+ocf_data_sampler/load/nwp/nwp.py,sha256=0AIHQTJLUtwP2Toz_PskOTYFJXfMvGhk8faAcNvI9jk,922
+ocf_data_sampler/load/nwp/providers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocf_data_sampler/load/nwp/providers/ecmwf.py,sha256=5AzktPJgertCx6oij6aePRosPuZHGFznMxTgtkk_mgc,994
+ocf_data_sampler/load/nwp/providers/gfs.py,sha256=JSDeh4YG1wibV8--P3X-zTO8LP0dsJcpFvIyglBbhi0,979
+ocf_data_sampler/load/nwp/providers/icon.py,sha256=yYUrs5HgjU0C5pMHBB6FGn3tLjswi990IY6QCXS1Zmw,1569
+ocf_data_sampler/load/nwp/providers/ukv.py,sha256=-0v8JCLH8ypz8GMXZ6Rrx-I0LoHuHO8sXFupbC1RpM0,1013
+ocf_data_sampler/load/nwp/providers/utils.py,sha256=cJZ9JA4W_ZeTcLQ5z71w46_DJaPcW_2JMmBdjP9r3qs,835
+ocf_data_sampler/numpy_sample/__init__.py,sha256=nY5C6CcuxiWZ_jrXRzWtN7WyKXhJImSiVTIG6Rz4B_4,401
+ocf_data_sampler/numpy_sample/collate.py,sha256=I9YPcbxOwHYaDGKbzxqdV-3DFEHkzqdhAwnW7_tZH2w,1966
+ocf_data_sampler/numpy_sample/datetime_features.py,sha256=INudxHcoB_c-GvYXe08S4Up_8TU5zOJ39PWRrTKfLp8,1203
+ocf_data_sampler/numpy_sample/gsp.py,sha256=EDaQdOVEDBJGrXsq54UNBfpXTzi0ky_WpgBbmlyxOXM,1074
+ocf_data_sampler/numpy_sample/nwp.py,sha256=iBGOdLMn-F5yR3juX3l4G2oXDpvGNuUdcR6ZCZkCqZk,1037
+ocf_data_sampler/numpy_sample/satellite.py,sha256=oBlyNpO-syoyK4SSghoHqIDNyhcBqyd1L6eXSSw0k3w,1036
+ocf_data_sampler/numpy_sample/site.py,sha256=tpX7j6dTOz2YmOFIzVYqTfWvIduKlOnBcLITsuPMgxU,1250
+ocf_data_sampler/numpy_sample/sun_position.py,sha256=nkfgN6NmiLGoLSuJZrDsM-6nsIzJN75tWfN20Z7n8xo,1480
+ocf_data_sampler/sample/__init__.py,sha256=zdS73NTnxFX_j8uh9tT-IXiURB6635wbneM1koWYV1o,169
+ocf_data_sampler/sample/base.py,sha256=lnr-MNRpAxjVFJHCEvCZL86NrYy9LWnNOsLWBGDL8kc,2359
+ocf_data_sampler/sample/site.py,sha256=4aJys40CQ-2CRKo_dgvm3rINTdfyTGWQGEaXGbh58qQ,1236
+ocf_data_sampler/sample/uk_regional.py,sha256=uMtLdqZCsKttjFmhIC6JITzu2JDZh-VQdYUfbpyhgFM,2409
+ocf_data_sampler/select/__init__.py,sha256=E4AJulEbO2K-o0UlG1fgaEteuf_1ZFjHTvrotXSb4YU,332
+ocf_data_sampler/select/dropout.py,sha256=_rzXl8_4VHTY_JMjbaoWopaFCJmLdaBpqfYF4vr24tk,1638
+ocf_data_sampler/select/fill_time_periods.py,sha256=TlGxp1xiAqnhdWfLy0pv3FuZc00dtimjWdLzr4JoTGA,865
+ocf_data_sampler/select/find_contiguous_time_periods.py,sha256=cEXrQDzk8pXknxB0q3v5DakosagHMoLDAj302B8Xpw0,11537
+ocf_data_sampler/select/geospatial.py,sha256=CDExkl36eZOKmdJPzUr_K0Wn3axHqv5nYo-EkSiINcc,5032
+ocf_data_sampler/select/location.py,sha256=AZvGR8y62opiW7zACGXjoOtBEWRfSLOZIA73O5Deu0c,1037
+ocf_data_sampler/select/select_spatial_slice.py,sha256=qY2Ll00EPA80oBtzwMoR5nk0UIpoWZF9oXl22YwWr0Q,12341
+ocf_data_sampler/select/select_time_slice.py,sha256=q5QdgHPIXQb49uT5NwbOguY1GhjWc_o3c-2cDb5kLAo,5455
+ocf_data_sampler/select/spatial_slice_for_dataset.py,sha256=Hvz0wHSWMYYamf2oHNiGlzJcM4cAH6pL_7ZEvIBL2dE,1882
+ocf_data_sampler/select/time_slice_for_dataset.py,sha256=1DN6VsWWdLvkpJxodZtBRDUgC4vJE2td_RP5J3ZqPNw,4268
+ocf_data_sampler/torch_datasets/datasets/__init__.py,sha256=jfJSFcR0eO1AqeH7S3KnGjsBqVZT5w3oyi784PUR6Q0,146
+ocf_data_sampler/torch_datasets/datasets/pvnet_uk.py,sha256=PW46uq53o84ihrR3vCg0KiqyihV_VKTC_zS67oH1M8Y,12892
+ocf_data_sampler/torch_datasets/datasets/site.py,sha256=Pr9DQszBP6GyS2uTT3unB50FfYsscu4qTiu9kgcQUys,17798
+ocf_data_sampler/torch_datasets/utils/merge_and_fill_utils.py,sha256=we7BTxRH7B7jKayDT7YfNyfI3zZClz2Bk-HXKQIokgU,956
+ocf_data_sampler/torch_datasets/utils/valid_time_periods.py,sha256=LdHgLPAYUVoCRMk2nnFdsMpygGS2kbps3h-7_bZnETw,4718
+ocf_data_sampler/torch_datasets/utils/validate_channels.py,sha256=tFBZqo7hYNkNb5Du8e5JSCKC21XcEuF_mbxZ6kdj0Og,3057
+scripts/refactor_site.py,sha256=pu50bqNH9PCmFnWDcIUsYkrDr6zASpkpBUzbZ48NjnU,3084
+utils/compute_icon_mean_stddev.py,sha256=a1oWMRMnny39rV-dvu8rcx85sb4bXzPFrR1gkUr4Jpg,2296
+ocf_data_sampler-0.1.16.dist-info/METADATA,sha256=NhVC5ZO3PEI4_8HEnrwKl3Jr7GwlUp1dQnSnn4beDTk,11713
+ocf_data_sampler-0.1.16.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+ocf_data_sampler-0.1.16.dist-info/top_level.txt,sha256=LEFU4Uk-PEo72QGLAfnVZIUEm37Q8mKuMeg_Xk-p33g,31
+ocf_data_sampler-0.1.16.dist-info/RECORD,,

{ocf_data_sampler-0.1.11.dist-info → ocf_data_sampler-0.1.16.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (76.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{ocf_data_sampler-0.1.11.dist-info → ocf_data_sampler-0.1.16.dist-info}/top_level.txt

@@ -1,3 +1,3 @@
 ocf_data_sampler
 scripts
-tests
+utils

scripts/refactor_site.py

@@ -1,50 +1,79 @@
-""" Helper functions for refactoring legacy site data """
 import xarray as xr
+import pandas as pd
 
-def legacy_format(data_ds, metadata_df):
-    """This formats old legacy data to the new format.
+def legacy_format(data_ds: xr.Dataset, metadata_df: pd.DataFrame) -> xr.Dataset:
+    """
+    Converts old legacy site data into a more structured format.
+
+    This function does three main things:
+    1. Renames some columns in the metadata to keep things consistent.
+    2. Reshapes site data so that instead of having separate variables for each site,
+       we use a `site_id` dimension—makes life easier for analysis.
+    3. Adds `capacity_kwp` as a time series so that each site has its capacity info.
+    
+    Parameters:
+        data_ds (xr.Dataset): The dataset containing legacy site data.
+        metadata_df (pd.DataFrame): A DataFrame with metadata about the sites.
 
-    1. This renames the columns in the metadata
-    2. Re-formats the site data from data variables named by the site_id to
-    a data array with a site_id dimension. Also adds capacity_kwp to the dataset as a time series for each site_id
+    Returns:
+        xr.Dataset: Reformatted dataset with `generation_kw` and `capacity_kwp`.
     """
 
+    # Step 1: Rename metadata columns to match the new expected format
     if "system_id" in metadata_df.columns:
-        metadata_df["site_id"] = metadata_df["system_id"]
-
+        metadata_df = metadata_df.rename(columns={"system_id": "site_id"})
+    
+    # Convert capacity from megawatts to kilowatts if needed
     if "capacity_megawatts" in metadata_df.columns:
         metadata_df["capacity_kwp"] = metadata_df["capacity_megawatts"] * 1000
 
-    # only site data has the site_id as data variables.
-    # We want to join them all together and create another coordinate called site_id
+    # Quick sanity check to ensure we have what we need
+    if "site_id" not in metadata_df.columns or "capacity_kwp" not in metadata_df.columns:
+        raise ValueError("Metadata is missing required columns: 'site_id' and 'capacity_kwp'.")
+
+    # Step 2: Transform the dataset
+    # Check if we actually have site data in the expected format
     if "0" in data_ds:
-        gen_df = data_ds.to_dataframe()
-        gen_da = xr.DataArray(
-            data=gen_df.values,
-            coords=(
-                ("time_utc", gen_df.index.values),
-                ("site_id", metadata_df["site_id"]),
-            ),
+        # Convert the dataset into a DataFrame so we can manipulate it more easily
+        site_data_df = data_ds.to_dataframe()
+
+        # Create a DataArray for generation data
+        generation_da = xr.DataArray(
+            data=site_data_df.values,
+            coords={
+                "time_utc": site_data_df.index.values,
+                "site_id": metadata_df["site_id"].values,
+            },
+            dims=["time_utc", "site_id"],
             name="generation_kw",
         )
 
-        capacity_df = gen_df
-        for col in capacity_df.columns:
-            capacity_df[col] = metadata_df[metadata_df["site_id"].astype(str) == col][
-                "capacity_kwp"
-            ].iloc[0]
+        # Step 3: Attach capacity information
+        # Map site_ids to their respective capacities
+        site_ids = site_data_df.columns
+        capacities = metadata_df.set_index("site_id").loc[site_ids, "capacity_kwp"]
+
+        # Broadcast capacities across all timestamps
+        capacity_df = pd.DataFrame(
+            {site_id: [capacities[site_id]] * len(site_data_df) for site_id in site_ids},
+            index=site_data_df.index,
+        )
+
+        # Create a DataArray for capacity data
         capacity_da = xr.DataArray(
             data=capacity_df.values,
-            coords=(
-                ("time_utc", gen_df.index.values),
-                ("site_id", metadata_df["site_id"]),
-            ),
+            coords={
+                "time_utc": site_data_df.index.values,
+                "site_id": metadata_df["site_id"].values,
+            },
+            dims=["time_utc", "site_id"],
             name="capacity_kwp",
         )
-        data_ds = xr.Dataset(
-            {
-                "generation_kw": gen_da,
-                "capacity_kwp": capacity_da,
-            }
-        )
-    return data_ds
+
+        # Finally, bundle everything into a single Dataset
+        data_ds = xr.Dataset({
+            "generation_kw": generation_da,
+            "capacity_kwp": capacity_da,
+        })
+
+    return data_ds

utils/compute_icon_mean_stddev.py

@@ -0,0 +1,72 @@
+"""Script to compute normalisation constants from NWP data."""
+
+import argparse
+import glob
+import logging
+
+import numpy as np
+import xarray as xr
+
+from ocf_data_sampler.load.nwp.providers.icon import open_icon_eu
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Add argument parser
+parser = argparse.ArgumentParser(description="Compute normalization constants from NWP data")
+parser.add_argument("--data-path", type=str, required=True,
+                    help='Path pattern to zarr files (e.g., "/path/to/data/*.zarr.zip")')
+parser.add_argument("--n-samples", type=int, default=2000,
+                    help="Number of random samples to use (default: 2000)")
+
+args = parser.parse_args()
+
+zarr_files = glob.glob(args.data_path)
+n_samples = args.n_samples
+
+ds = open_icon_eu(zarr_files)
+
+n_init_times = ds.sizes["init_time_utc"]
+n_lats = ds.sizes["latitude"]
+n_longs = ds.sizes["longitude"]
+n_steps = ds.sizes["step"]
+
+random_init_times = np.random.choice(n_init_times, size=n_samples, replace=True)
+random_lats = np.random.choice(n_lats, size=n_samples, replace=True)
+random_longs = np.random.choice(n_longs, size=n_samples, replace=True)
+random_steps = np.random.choice(n_steps, size=n_samples, replace=True)
+
+samples = []
+for i in range(n_samples):
+    sample = ds.isel(init_time_utc=random_init_times[i],
+                    latitude=random_lats[i],
+                    longitude=random_longs[i],
+                    step=random_steps[i])
+    samples.append(sample)
+
+samples_stack = xr.concat(samples, dim="samples")
+
+
+available_channels = samples_stack.channel.values.tolist()
+logger.info("Available channels: %s", available_channels)
+
+ICON_EU_MEAN = {}
+ICON_EU_STD = {}
+
+for var in available_channels:
+    if var not in available_channels:
+        logger.warning("Variable '%s' not found in the channel coordinate; skipping.", var)
+        continue
+    var_data = samples_stack.sel(channel=var)
+    var_mean = float(var_data.mean().compute())
+    var_std = float(var_data.std().compute())
+
+    ICON_EU_MEAN[var] = var_mean
+    ICON_EU_STD[var] = var_std
+
+    logger.info("Processed %s: mean=%.4f, std=%.4f", var, var_mean, var_std)
+
+logger.info("\nMean values:\n%s", ICON_EU_MEAN)
+logger.info("\nStandard deviations:\n%s", ICON_EU_STD)
+

ocf_data_sampler-0.1.11.dist-info/LICENSE

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2023 Open Climate Fix
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.

ocf_data_sampler-0.1.11.dist-info/RECORD

@@ -1,82 +0,0 @@
-ocf_data_sampler/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-ocf_data_sampler/constants.py,sha256=0HYNmqwBaHVTAEEx9qzk6WD9YInh0gSKLeI3pyq7aNs,5077
-ocf_data_sampler/utils.py,sha256=rKA0BHAyAG4f90zEcgxp25EEYrXS-aOVNzttZ6Mzv2k,250
-ocf_data_sampler/config/__init__.py,sha256=O29mbH0XG2gIY1g3BaveGCnpBO2SFqdu-qzJ7a6evl0,223
-ocf_data_sampler/config/load.py,sha256=sKCKmhkkeFvvkNL5xmnFvdAulaCtV4-rigPsFvVDPDc,634
-ocf_data_sampler/config/model.py,sha256=8PO-23uVy_JjWOJKgaZWdNMehQsAI-Jn8t0lcmBycwg,6992
-ocf_data_sampler/config/save.py,sha256=OqCPT3e0d7vMI2g2iRzmifPD7GscDkFQztU_qE5I0JY,1066
-ocf_data_sampler/data/uk_gsp_locations.csv,sha256=RSh7DRh55E3n8lVAaWXGTaXXHevZZtI58td4d4DhGos,10415772
-ocf_data_sampler/load/__init__.py,sha256=T5Zj1PGt0aiiNEN7Ra1Ac-cBsNKhphmmHy_8g7XU_w0,219
-ocf_data_sampler/load/gsp.py,sha256=uRxEORH7J99JAJ-D38nm0iJFOQh7dkm_NCXcpbYkyvo,857
-ocf_data_sampler/load/load_dataset.py,sha256=PHUGSm4hFHfS9nfIP2KjHHCp325O4br7uGBdQH_DP7g,1603
-ocf_data_sampler/load/satellite.py,sha256=SEQZ9oPe-asEeZeEMDkB1xWK5hErhWMagxohFcBl6KI,2294
-ocf_data_sampler/load/site.py,sha256=hMdoF6sn2PcSBfF2soj7nuQoK9SItaxDXco5nk2n-44,1232
-ocf_data_sampler/load/utils.py,sha256=sAEkPMS9LXVCrc5pANQo97zaoEItVg9hoNj2ZWfx_Ug,1405
-ocf_data_sampler/load/nwp/__init__.py,sha256=SmcrnbygO5xtCKmGR4wtHrj-HI7nOAvnAtfuvRufBGQ,25
-ocf_data_sampler/load/nwp/nwp.py,sha256=Jyq1dE7DN0iSe6iSEGA76uu9LoeJz9FzfEUkq6ZZExQ,565
-ocf_data_sampler/load/nwp/providers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ocf_data_sampler/load/nwp/providers/ecmwf.py,sha256=8rYZKdV62AdczVNSOJ2G0BM4-fRFRV0_y5zkHgNYkQs,1004
-ocf_data_sampler/load/nwp/providers/ukv.py,sha256=dM_kvUI0xk9xEdslXqZGjOPP96PEw3qAci5mPUgUvxA,1014
-ocf_data_sampler/load/nwp/providers/utils.py,sha256=MFOZ5ZXLu3-SxYVJExdlo30b3y3s5ebRx3_6DO-33FQ,780
-ocf_data_sampler/numpy_sample/__init__.py,sha256=nY5C6CcuxiWZ_jrXRzWtN7WyKXhJImSiVTIG6Rz4B_4,401
-ocf_data_sampler/numpy_sample/collate.py,sha256=oX5axq30sCsSquhNbmWAVMjM54HT1v3MCMopYHcO5Q0,1950
-ocf_data_sampler/numpy_sample/datetime_features.py,sha256=D0RajbnBjg15qjYk16h2H0XO4wH3fw-x0--4VC2nq0s,1204
-ocf_data_sampler/numpy_sample/gsp.py,sha256=uBquCFCoWuhJKY8sXpgsTCUDWUuLuv1XeixtFnFw6KU,1115
-ocf_data_sampler/numpy_sample/nwp.py,sha256=Tiba-es23XeyMoEPgZUpLT6EnJCGU9A_1MdY6qkE7bM,1015
-ocf_data_sampler/numpy_sample/satellite.py,sha256=RdXMdGGXysUx-AdL9T33yFOlxprtIdPNBKKX99-mhpY,991
-ocf_data_sampler/numpy_sample/site.py,sha256=TvoEU85fmjYW8pD9UZOyUUACjimdQYxEzulQXunRO6Q,1425
-ocf_data_sampler/numpy_sample/sun_position.py,sha256=ithM--eztAhiIQ1g52tlxgj-tMKbsJzx8mk6CgV2tzk,1613
-ocf_data_sampler/sample/__init__.py,sha256=zdS73NTnxFX_j8uh9tT-IXiURB6635wbneM1koWYV1o,169
-ocf_data_sampler/sample/base.py,sha256=IH3HbfqEUwjHmq-h2eJYLd8Jk-0ZcOylnehMyCPMV38,2223
-ocf_data_sampler/sample/site.py,sha256=ONf2Yz5zi8Ombd_znA4T7NXbO01F76kQsBZv6rfnC74,1343
-ocf_data_sampler/sample/uk_regional.py,sha256=KhJ5Ik1pZRp7PgIJjGIrE4i7SQnIdVjUbBHnfn-7ghg,2649
-ocf_data_sampler/select/__init__.py,sha256=E4AJulEbO2K-o0UlG1fgaEteuf_1ZFjHTvrotXSb4YU,332
-ocf_data_sampler/select/dropout.py,sha256=Pgov9P7rQMkSdqluG_hwm8loGyYNFOg-3PJUBLN_kjU,1526
-ocf_data_sampler/select/fill_time_periods.py,sha256=EIcXG-77aQVOAYNwbDBEv6SGf6DO2p1WMEf96iW4MEM,596
-ocf_data_sampler/select/find_contiguous_time_periods.py,sha256=IwPQwvgu4cOiAZ5Gbjflv3fnQCcs0EVK0g4V6yqqSgw,11129
-ocf_data_sampler/select/geospatial.py,sha256=4xL-9y674jjoaXeqE52NHCHVfknciE4OEGsZtn9DvP4,4911
-ocf_data_sampler/select/location.py,sha256=26Y5ZjfFngShBwXieuWSoOA-RLaRzci4TTmcDk3Wg7U,2015
-ocf_data_sampler/select/select_spatial_slice.py,sha256=WNxwur9Q5oetvogATw8-hNejDuEwrXHzuZIovFDjNJA,11488
-ocf_data_sampler/select/select_time_slice.py,sha256=9M-yvDv9K77XfEys_OIR31_aVB56sNWk3BnCnkCgcPI,4725
-ocf_data_sampler/select/spatial_slice_for_dataset.py,sha256=3tRrMBXr7s4CnClbVSIq7hpls3H4Y3qYTDwswcxCCCE,1763
-ocf_data_sampler/select/time_slice_for_dataset.py,sha256=Z7pOiilSHScxmBKZNG18K5J-S4ifdXXAYGZoHRHD3AY,4324
-ocf_data_sampler/torch_datasets/datasets/__init__.py,sha256=jfJSFcR0eO1AqeH7S3KnGjsBqVZT5w3oyi784PUR6Q0,146
-ocf_data_sampler/torch_datasets/datasets/pvnet_uk.py,sha256=ZgfvVCcEU3dj3RoY0zdBdKGppC7Wm81qecqB17gYTmE,12286
-ocf_data_sampler/torch_datasets/datasets/site.py,sha256=_uHmqg-VJu-MHgXc5JFDX1noPfH6E8nY4XhQmsrOav4,16325
-ocf_data_sampler/torch_datasets/utils/merge_and_fill_utils.py,sha256=hIbekql64eXsNDFIoEc--GWxwdVWrh2qKegdOi70Bow,874
-ocf_data_sampler/torch_datasets/utils/valid_time_periods.py,sha256=Qo65qUHtle_bW5tLTYr7empHTRv-lpjvfx_6GNJj3Xg,4371
-ocf_data_sampler/torch_datasets/utils/validate_channels.py,sha256=u2EpiFAKAOHpmvINhOUJCT8Vbc-cle6qJ3YNVse4yLs,2884
-scripts/refactor_site.py,sha256=xaJGxt2_WObIPrPAnRiOMMB68r-5Q51jWRx409AcscM,1747
-tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/conftest.py,sha256=k7nM3u2YJmkMupN4SIbJP3BRoxNR1dpIoo2fPFf0abg,8588
-tests/config/test_config.py,sha256=CzYVhAUpgT4lvQdIddtVxtJeMqYL_TJolfeIwaaohq4,3969
-tests/config/test_load.py,sha256=8nui2UsgK_eufWGD74yXvf-6eY_SxBFKhDmGYUtRQxw,260
-tests/config/test_save.py,sha256=BxSd2S50-bRPIXP_4iX0B6Wt7pRFJnUbLYtzfLaqlAs,915
-tests/load/test_load_gsp.py,sha256=aT_nqaSXmUTcdHzuTT7AmXJr3R31k4OEN-Fv3eLxlQE,424
-tests/load/test_load_nwp.py,sha256=3qyyDkB1q9t3tyAwogfotNrxqUOpXXimco1CImoEWGg,753
-tests/load/test_load_satellite.py,sha256=IQ8ISRZKCEoi8IsJoPpXZJTolD0mwjnl2E7762RM_PM,524
-tests/load/test_load_sites.py,sha256=6V-U3_EtBklkV7w-hOoR4nba3dSaZ_cnjuRWFs8kYVU,405
-tests/numpy_sample/test_collate.py,sha256=RqHCD5_LTRpe4r6kqC_2TKhmhM_IHYM0ZtFUvSjDqcM,654
-tests/numpy_sample/test_datetime_features.py,sha256=iR9WdBLj1nIBNqoaTFE9rkUaH1eKFJSNb96nwiEaQH0,1449
-tests/numpy_sample/test_gsp.py,sha256=FLlq4SlJ-9cSRAepf4_ksA6PsUVKegnKEAc5pUojCJ0,1458
-tests/numpy_sample/test_nwp.py,sha256=Lnd-PMa6gI-fSIJkSZ554QiHFfnwxeXZxLg-rpuBv1U,442
-tests/numpy_sample/test_satellite.py,sha256=cCqtn5See-uSNfh89COGTUQNuFm6sIZ8QmBVHsuUeRI,1189
-tests/numpy_sample/test_sun_position.py,sha256=_ENYzsNBVPdNXf--FI-UUFqw2u5w7_zqw6LcENU2uZM,2504
-tests/select/test_dropout.py,sha256=aQuSSqZF9RxBjN9-ogkQ8O-_zktAM30CrT1Lz7j1hMg,2222
-tests/select/test_fill_time_periods.py,sha256=o59f2YRe5b0vJrG3B0aYZkYeHnpNk4s6EJxdXZluNQg,907
-tests/select/test_find_contiguous_time_periods.py,sha256=kOga_V7er5We7ewMARXaKdM3agOhsvZYx8inXtUn1PM,5976
-tests/select/test_location.py,sha256=_WZk2FPYeJ-nIfCJS6Sp_yaVEEo7m31DmMFoZzgyCts,2712
-tests/select/test_select_spatial_slice.py,sha256=7EX9b6g-pMdACQx3yefjs5do2s-Rho2UmKevV4oglsU,5147
-tests/select/test_select_time_slice.py,sha256=nYrdlmZlGEygJKiE26bADiluNPN1qt5kD4FrI2vtxUw,9686
-tests/test_sample/test_base.py,sha256=sD9NZghYQWbkAcQP9YXypWZowqYkO3xeNMH-_mEoD5I,4833
-tests/test_sample/test_site_sample.py,sha256=8HNenhIWYouCQu4y389PDQGokSPI5jQ4lS4CG-eA1Y8,5382
-tests/test_sample/test_uk_regional_sample.py,sha256=MFibX9-M8mFK7vwMPu58gAG2VoY6y7w7chW5BlZclwk,3962
-tests/torch_datasets/test_merge_and_fill_utils.py,sha256=GtuQg82BM1eHQjT7Ik1x1zaVcuc7KJO4_NC9stXsd4s,1123
-tests/torch_datasets/test_pvnet_uk.py,sha256=hgD_IDa4D8cgc4cgK1UqKYkT6sFlrTMAvgVn_iwD5_4,5086
-tests/torch_datasets/test_site.py,sha256=t57vAR_RRWcbG_kEFk6VrFCYzVxwFG6qJKBnRHF02fM,7000
-tests/torch_datasets/test_validate_channels_utils.py,sha256=Rzdweu98j1of45jCOUrSiBtyPlf-dDaCceulf0H7ml8,2921
-ocf_data_sampler-0.1.11.dist-info/LICENSE,sha256=F-Q3UFCR-BECSocV55BFDpn4YKxve9PKrm-lTt6o_Tg,1073
-ocf_data_sampler-0.1.11.dist-info/METADATA,sha256=d8wctSlRyDbP1_yYHFvIGQgEC8DmOkM8h-ITI4XFuPw,12174
-ocf_data_sampler-0.1.11.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ocf_data_sampler-0.1.11.dist-info/top_level.txt,sha256=Faob6N6cFdPc5eUpCTYcXgCaNhi4XLLteUL5W5ayYmg,31
-ocf_data_sampler-0.1.11.dist-info/RECORD,,

tests/config/test_config.py

@@ -1,113 +0,0 @@
-import pytest
-from pydantic import ValidationError
-from ocf_data_sampler.config import load_yaml_configuration, Configuration
-
-
-def test_default_configuration():
-    """Test default pydantic class"""
-    _ = Configuration()
-
-
-def test_extra_field_error():
-    """
-    Check an extra parameters in config causes error
-    """
-
-    configuration = Configuration()
-    configuration_dict = configuration.model_dump()
-    configuration_dict["extra_field"] = "extra_value"
-    with pytest.raises(ValidationError, match="Extra inputs are not permitted"):
-        _ = Configuration(**configuration_dict)
-
-
-def test_incorrect_interval_start_minutes(test_config_filename):
-    """
-    Check a history length not divisible by time resolution causes error
-    """
-
-    configuration = load_yaml_configuration(test_config_filename)
-
-    configuration.input_data.nwp['ukv'].interval_start_minutes = -1111
-    with pytest.raises(
-        ValueError, 
-        match="interval_start_minutes.*must be divisible.*time_resolution_minutes.*"
-    ):
-        _ = Configuration(**configuration.model_dump())
-
-
-def test_incorrect_interval_end_minutes(test_config_filename):
-    """
-    Check a forecast length not divisible by time resolution causes error
-    """
-
-    configuration = load_yaml_configuration(test_config_filename)
-
-    configuration.input_data.nwp['ukv'].interval_end_minutes = 1111
-    with pytest.raises(
-        ValueError, 
-        match="interval_end_minutes.*must be divisible.*time_resolution_minutes.*"
-    ):
-        _ = Configuration(**configuration.model_dump())
-
-
-def test_incorrect_nwp_provider(test_config_filename):
-    """
-    Check an unexpected nwp provider causes error
-    """
-
-    configuration = load_yaml_configuration(test_config_filename)
-
-    configuration.input_data.nwp['ukv'].provider = "unexpected_provider"
-    with pytest.raises(Exception, match="NWP provider"):
-        _ = Configuration(**configuration.model_dump())
-
-
-def test_incorrect_dropout(test_config_filename):
-    """
-    Check a dropout timedelta over 0 causes error and 0 doesn't
-    """
-
-    configuration = load_yaml_configuration(test_config_filename)
-
-    # check a positive number is not allowed
-    configuration.input_data.nwp['ukv'].dropout_timedeltas_minutes = [120]
-    with pytest.raises(Exception, match="Dropout timedeltas must be negative"):
-        _ = Configuration(**configuration.model_dump())
-
-    # check 0 is allowed
-    configuration.input_data.nwp['ukv'].dropout_timedeltas_minutes = [0]
-    _ = Configuration(**configuration.model_dump())
-
-
-def test_incorrect_dropout_fraction(test_config_filename):
-    """
-    Check dropout fraction outside of range causes error
-    """
-
-    configuration = load_yaml_configuration(test_config_filename)
-
-    configuration.input_data.nwp['ukv'].dropout_fraction= 1.1
-
-    with pytest.raises(ValidationError,  match="Input should be less than or equal to 1"):
-        _ = Configuration(**configuration.model_dump())
-
-    configuration.input_data.nwp['ukv'].dropout_fraction= -0.1
-    with pytest.raises(ValidationError, match="Input should be greater than or equal to 0"):
-        _ = Configuration(**configuration.model_dump())
-
-
-def test_inconsistent_dropout_use(test_config_filename):
-    """
-    Check dropout fraction outside of range causes error
-    """
-
-    configuration = load_yaml_configuration(test_config_filename)
-    configuration.input_data.satellite.dropout_fraction= 1.0
-    configuration.input_data.satellite.dropout_timedeltas_minutes = []
-
-    with pytest.raises(ValueError, match="To dropout fraction > 0 requires a list of dropout timedeltas"):
-        _ = Configuration(**configuration.model_dump())
-    configuration.input_data.satellite.dropout_fraction= 0.0
-    configuration.input_data.satellite.dropout_timedeltas_minutes = [-120, -60]
-    with pytest.raises(ValueError, match="To use dropout timedeltas dropout fraction should be > 0"):
-        _ = Configuration(**configuration.model_dump())