ocf-data-sampler 0.1.10__py3-none-any.whl → 0.1.11__py3-none-any.whl

ocf_data_sampler/sample/uk_regional.py

@@ -1,120 +1,75 @@
-""" 
-PVNet - UK Regional sample / dataset implementation
-"""
+"""PVNet UK Regional sample implementation for dataset handling and visualisation"""
 
-import numpy as np
-import pandas as pd
-import torch
-import logging
+from typing_extensions import override
 
-from typing import Dict, Any, Union, List, Optional
-from pathlib import Path
+import torch
 
+from ocf_data_sampler.sample.base import SampleBase, NumpySample
 from ocf_data_sampler.numpy_sample import (
     NWPSampleKey, 
     GSPSampleKey,
     SatelliteSampleKey
 )
 
-from ocf_data_sampler.sample.base import SampleBase
-
-try:
-    import matplotlib.pyplot as plt
-    MATPLOTLIB_AVAILABLE = True
-except ImportError:
-    MATPLOTLIB_AVAILABLE = False
-    plt = None
-
-
-logger = logging.getLogger(__name__)
-
 
 class UKRegionalSample(SampleBase):
-    """ Sample class specific to UK Regional PVNet """
+    """Handles UK Regional PVNet data operations"""
 
-    def __init__(self):
-        logger.debug("Initialise UKRegionalSample instance")
-        super().__init__()
-        self._data = {}
+    def __init__(self, data: NumpySample):
+        self._data = data
 
-    def to_numpy(self) -> Dict[str, Any]:
-        """ Convert sample data to numpy format """
-        logger.debug("Converting sample data to numpy format")
+    @override
+    def to_numpy(self) -> NumpySample:
         return self._data
 
-    def save(self, path: Union[str, Path]) -> None:
-        """ Save PVNet sample as .pt """
-        logger.debug(f"Saving UKRegionalSample to {path}")
-        path = Path(path)
-        
-        if path.suffix != '.pt':
-            logger.error(f"Invalid file format: {path.suffix}")
-            raise ValueError(f"Only .pt format is supported: {path.suffix}")
+    def save(self, path: str) -> None:
+        """Save PVNet sample as pickle format using torch.save
         
+        Args:
+            path: Path to save the sample data to
+        """        
         torch.save(self._data, path)
-        logger.debug(f"Successfully saved UKRegionalSample to {path}")
 
     @classmethod
-    def load(cls, path: Union[str, Path]) -> 'UKRegionalSample':
-        """ Load PVNet sample data from .pt """
-        logger.debug(f"Attempting to load UKRegionalSample from {path}")
-        path = Path(path)
+    def load(cls, path: str) -> 'UKRegionalSample':
+        """Load PVNet sample data from .pt format
         
-        if path.suffix != '.pt':
-            logger.error(f"Invalid file format: {path.suffix}")
-            raise ValueError(f"Only .pt format is supported: {path.suffix}")
-        
-        instance = cls()
+        Args:
+            path: Path to load the sample data from
+        """
         # TODO: We should move away from using torch.load(..., weights_only=False)
-        # This is not recommended
-        instance._data = torch.load(path, weights_only=False)
-        logger.debug(f"Successfully loaded UKRegionalSample from {path}")
-        return instance
-
-    def plot(self, **kwargs) -> None:
-        """ Sample visualisation definition """
-        logger.debug("Creating UKRegionalSample visualisation")
-
-        if not MATPLOTLIB_AVAILABLE:
-            raise ImportError(
-                "Matplotlib required for plotting"
-                "Install via 'ocf_data_sampler[plot]'"
-            )
-
-        try:
-            fig, axes = plt.subplots(2, 2, figsize=(12, 8))
-            
-            if NWPSampleKey.nwp in self._data:
-                logger.debug("Plotting NWP data")
-                first_nwp = list(self._data[NWPSampleKey.nwp].values())[0]
-                if 'nwp' in first_nwp:
-                    axes[0, 1].imshow(first_nwp['nwp'][0])
-                    axes[0, 1].set_title('NWP (First Channel)')
-                    if NWPSampleKey.channel_names in first_nwp:
-                        channel_names = first_nwp[NWPSampleKey.channel_names]
-                        if len(channel_names) > 0:
-                            axes[0, 1].set_title(f'NWP: {channel_names[0]}')
+        return cls(torch.load(path, weights_only=False))
 
-            if GSPSampleKey.gsp in self._data:
-                logger.debug("Plotting GSP generation data")
-                axes[0, 0].plot(self._data[GSPSampleKey.gsp])
-                axes[0, 0].set_title('GSP Generation')
-            
-            if GSPSampleKey.solar_azimuth in self._data and GSPSampleKey.solar_elevation in self._data:
-                logger.debug("Plotting solar position data")
-                axes[1, 1].plot(self._data[GSPSampleKey.solar_azimuth], label='Azimuth')
-                axes[1, 1].plot(self._data[GSPSampleKey.solar_elevation], label='Elevation')
-                axes[1, 1].set_title('Solar Position')
-                axes[1, 1].legend()
+    def plot(self) -> None:
+        """Creates visualisations for NWP, GSP, solar position, and satellite data"""
+        from matplotlib import pyplot as plt
 
-            if SatelliteSampleKey.satellite_actual in self._data:
-                logger.debug("Plotting satellite data")
-                axes[1, 0].imshow(self._data[SatelliteSampleKey.satellite_actual])
-                axes[1, 0].set_title('Satellite Data')
-            
-            plt.tight_layout()
-            plt.show()
-            logger.debug("Successfully created visualisation")
-        except Exception as e:
-            logger.error(f"Error creating visualisation: {str(e)}")
-            raise
+        fig, axes = plt.subplots(2, 2, figsize=(12, 8))
+        
+        if NWPSampleKey.nwp in self._data:
+            first_nwp = list(self._data[NWPSampleKey.nwp].values())[0]
+            if 'nwp' in first_nwp:
+                axes[0, 1].imshow(first_nwp['nwp'][0])
+                title = 'NWP (First Channel)'
+                if NWPSampleKey.channel_names in first_nwp:
+                    channel_names = first_nwp[NWPSampleKey.channel_names]
+                    if channel_names:
+                        title = f'NWP: {channel_names[0]}'
+                axes[0, 1].set_title(title)
+
+        if GSPSampleKey.gsp in self._data:
+            axes[0, 0].plot(self._data[GSPSampleKey.gsp])
+            axes[0, 0].set_title('GSP Generation')
+        
+        if GSPSampleKey.solar_azimuth in self._data and GSPSampleKey.solar_elevation in self._data:
+            axes[1, 1].plot(self._data[GSPSampleKey.solar_azimuth], label='Azimuth')
+            axes[1, 1].plot(self._data[GSPSampleKey.solar_elevation], label='Elevation')
+            axes[1, 1].set_title('Solar Position')
+            axes[1, 1].legend()
+
+        if SatelliteSampleKey.satellite_actual in self._data:
+            axes[1, 0].imshow(self._data[SatelliteSampleKey.satellite_actual])
+            axes[1, 0].set_title('Satellite Data')
+        
+        plt.tight_layout()
+        plt.show()

ocf_data_sampler/select/dropout.py

@@ -1,39 +1,52 @@
-""" Functions for simulating dropout in time series data """
+"""Functions for simulating dropout in time series data 
+
+This is used for the following types of data: GSP, Satellite and Site
+This is not used for NWP
+"""
 import numpy as np
 import pandas as pd
 import xarray as xr
 
 
 def draw_dropout_time(
-        t0: pd.Timestamp,
-        dropout_timedeltas: list[pd.Timedelta] | pd.Timedelta | None,
-        dropout_frac: float = 0,
-    ):
-
-    if dropout_timedeltas is not None:
-        assert len(dropout_timedeltas) >= 1, "Must include list of relative dropout timedeltas"
-        assert all(
-            [t <= pd.Timedelta("0min") for t in dropout_timedeltas]
-        ), "dropout timedeltas must be negative"
+    t0: pd.Timestamp,
+    dropout_timedeltas: list[pd.Timedelta],
+    dropout_frac: float,
+) -> pd.Timestamp:
+    """Randomly pick a dropout time from a list of timedeltas
+    
+    Args:
+        t0: The forecast init-time
+        dropout_timedeltas: List of timedeltas relative to t0 to pick from
+        dropout_frac: Probability that dropout will be applied. This should be between 0 and 1 
+            inclusive
+    """
+
+    if dropout_frac>0:
+        assert len(dropout_timedeltas) > 0, "To apply dropout dropout_timedeltas must be provided"
+
+    for t in dropout_timedeltas:
+        assert t <= pd.Timedelta("0min"), "Dropout timedeltas must be negative"
+
     assert 0 <= dropout_frac <= 1
 
-    if (dropout_timedeltas is None) or (np.random.uniform() >= dropout_frac):
-        dropout_time = None
+    if (len(dropout_timedeltas) == 0) or (np.random.uniform() >= dropout_frac):
+        dropout_time = t0
     else:
-        t0_datetime_utc = pd.Timestamp(t0)
-        dt = np.random.choice(dropout_timedeltas)
-        dropout_time = t0_datetime_utc + dt
+        dropout_time = t0 + np.random.choice(dropout_timedeltas)
 
     return dropout_time
 
 
 def apply_dropout_time(
-        ds: xr.DataArray,
-        dropout_time: pd.Timestamp | None,
-    ):
-
-    if dropout_time is None:
-        return ds
-    else:
-        # This replaces the times after the dropout with NaNs
-        return ds.where(ds.time_utc <= dropout_time)
+    ds: xr.DataArray,
+    dropout_time: pd.Timestamp,
+ ) -> xr.DataArray:
+    """Apply dropout time to the data
+    
+    Args:
+        ds: Xarray DataArray with 'time_utc' coordiante 
+        dropout_time: Time after which data is set to NaN
+    """
+    # This replaces the times after the dropout with NaNs
+    return ds.where(ds.time_utc <= dropout_time)

ocf_data_sampler/select/fill_time_periods.py

@@ -1,10 +1,12 @@
-"""fill time periods"""
+"""Fill time periods between start and end dates at specified frequency"""
 
 import pandas as pd
 import numpy as np
 
 
 def fill_time_periods(time_periods: pd.DataFrame, freq: pd.Timedelta) -> pd.DatetimeIndex:
+    """Generate DatetimeIndex for all timestamps between start and end dates"""
+    
     start_dts = pd.to_datetime(time_periods["start_dt"].values).ceil(freq)
     end_dts = pd.to_datetime(time_periods["end_dt"].values)
     date_ranges = [pd.date_range(start_dt, end_dt, freq=freq) for start_dt, end_dt in zip(start_dts, end_dts)]

ocf_data_sampler/select/find_contiguous_time_periods.py

@@ -5,7 +5,6 @@ import pandas as pd
 from ocf_data_sampler.load.utils import check_time_unique_increasing
 
 
-
 def find_contiguous_time_periods(
     datetimes: pd.DatetimeIndex,
     min_seq_length: int,

{ocf_data_sampler-0.1.10.dist-info → ocf_data_sampler-0.1.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ocf_data_sampler
-Version: 0.1.10
+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

{ocf_data_sampler-0.1.10.dist-info → ocf_data_sampler-0.1.11.dist-info}/RECORD

@@ -3,14 +3,14 @@ ocf_data_sampler/constants.py,sha256=0HYNmqwBaHVTAEEx9qzk6WD9YInh0gSKLeI3pyq7aNs
 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=IMJhsjL_oGh2c50q8pBnCnArY4qHQcBc_M8jqlEeD0c,7129
+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=4MRJBFDHxx5WXu_6X71wEBznJTIuldEVnu9d6DVoLPI,2436
-ocf_data_sampler/load/site.py,sha256=74M_7RYwEc1bU4idjs3ZmQrx9I8mJXm6H4lwEL-h9n0,1226
+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
@@ -21,19 +21,19 @@ ocf_data_sampler/load/nwp/providers/utils.py,sha256=MFOZ5ZXLu3-SxYVJExdlo30b3y3s
 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=5UaWO_aGRRVQo82wnDaT4zBKHihOnIsXiwgPjM8vGFM,1005
-ocf_data_sampler/numpy_sample/nwp.py,sha256=_seQNWsut3IzPsrpipqImjnaM3XNHZCy5_5be6syivk,1297
-ocf_data_sampler/numpy_sample/satellite.py,sha256=8OaTvkPjzSjotcdKsa6BKmmlBKDBunbhDN4Pjo0Grxs,910
-ocf_data_sampler/numpy_sample/site.py,sha256=I-cAXCOF0SDdm5Hx43lFqYZ3jh61kltLQK-fc4_nNu0,1314
-ocf_data_sampler/numpy_sample/sun_position.py,sha256=UklhucCxCT6GMlAhCWL6c4cfWrdc1cWgegrYaqUoHOY,1611
-ocf_data_sampler/sample/__init__.py,sha256=02CM7E5nKkGiYbVW-kvzjNd4RaqGuHCkDChtmDBDUoA,248
-ocf_data_sampler/sample/base.py,sha256=q3wpqoW4JXRmzfar6ed7UMn1nxBxSJXNvMLJmHXy1dw,2856
-ocf_data_sampler/sample/site.py,sha256=0BvDXs0kxTjUq7kWpeoITK_uN4uE0w1IvEFXZUoKOb0,2507
-ocf_data_sampler/sample/uk_regional.py,sha256=D1A6nQB1PYCmxb3FzU9gqbNufQfx__wcprcDm50jCJw,4381
+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=HCx5Wzk8Oh2Z9vV94Jy-ALJsHtGduwvMaQOleQXp5z0,1142
-ocf_data_sampler/select/fill_time_periods.py,sha256=h0XD1Ds_wUUoy-7bILxmN8AIbjlQ6YdXRKuCk_Is5jo,460
-ocf_data_sampler/select/find_contiguous_time_periods.py,sha256=Nvz4gLCbbKzAe3sQXfxgExL9NtZVk1WNORvHs94DQ_k,11130
+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
@@ -48,8 +48,8 @@ ocf_data_sampler/torch_datasets/utils/valid_time_periods.py,sha256=Qo65qUHtle_bW
 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=RlC7YYtBLipUzFS1tQxela1SgHCxSpReUKEJ4429PwQ,7689
-tests/config/test_config.py,sha256=VQjNiucIk5VnPQdGA6Mr-RNd9CwGI06AiikChTHrcnY,3969
+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
@@ -59,24 +59,24 @@ tests/load/test_load_sites.py,sha256=6V-U3_EtBklkV7w-hOoR4nba3dSaZ_cnjuRWFs8kYVU
 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=yf4u7mAU0E3FQ4xAH6YjuHuHBzzFoXjHSFNkOVJUdSM,1455
+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=kiycl7RxAQYMCZJlokmx6Da5h_oBpSs8Is8pmSW4gOU,2413
+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=Gln-Or060cUWvA7Q7c1vsthgCttOAM2z9yBI9zUIrDw,6238
-tests/test_sample/test_uk_regional_sample.py,sha256=gkeQWC2wC757jKJz_QBmDMFQjn3R54q_tEo948yyxCY,4840
+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=F0D-DugFgVtt8G1q7lylmPLrOZj6H6YPNd9s_6Wn_yM,5594
+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-0.1.10.dist-info/LICENSE,sha256=F-Q3UFCR-BECSocV55BFDpn4YKxve9PKrm-lTt6o_Tg,1073
-ocf_data_sampler-0.1.10.dist-info/METADATA,sha256=HDEoz2xG-Qw23Rz2Wcms5_w1p3hbrRK1MBIJjwA6WrA,12174
-ocf_data_sampler-0.1.10.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ocf_data_sampler-0.1.10.dist-info/top_level.txt,sha256=Faob6N6cFdPc5eUpCTYcXgCaNhi4XLLteUL5W5ayYmg,31
-ocf_data_sampler-0.1.10.dist-info/RECORD,,
+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

@@ -30,7 +30,7 @@ def test_incorrect_interval_start_minutes(test_config_filename):
     configuration.input_data.nwp['ukv'].interval_start_minutes = -1111
     with pytest.raises(
         ValueError, 
-        match="interval_start_minutes must be divisible by time_resolution_minutes"
+        match="interval_start_minutes.*must be divisible.*time_resolution_minutes.*"
     ):
         _ = Configuration(**configuration.model_dump())
 
@@ -45,7 +45,7 @@ def test_incorrect_interval_end_minutes(test_config_filename):
     configuration.input_data.nwp['ukv'].interval_end_minutes = 1111
     with pytest.raises(
         ValueError, 
-        match="interval_end_minutes must be divisible by time_resolution_minutes"
+        match="interval_end_minutes.*must be divisible.*time_resolution_minutes.*"
     ):
         _ = Configuration(**configuration.model_dump())
 
@@ -103,7 +103,7 @@ def test_inconsistent_dropout_use(test_config_filename):
 
     configuration = load_yaml_configuration(test_config_filename)
     configuration.input_data.satellite.dropout_fraction= 1.0
-    configuration.input_data.satellite.dropout_timedeltas_minutes = None
+    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())

tests/conftest.py

@@ -130,6 +130,39 @@ def nwp_ukv_zarr_path(session_tmp_path, ds_nwp_ukv):
     yield zarr_path
 
 
+@pytest.fixture()
+def ds_nwp_ukv_time_sliced():
+
+    t0 = pd.to_datetime("2024-01-02 00:00")
+
+    x = np.arange(-100, 100, 10)
+    y = np.arange(-100, 100, 10)
+    steps = pd.timedelta_range("0h", "8h", freq="1h")
+    target_times = t0 + steps
+
+    channels = ["t", "dswrf"]
+    init_times = pd.to_datetime([t0]*len(steps))
+    
+    # Create dummy time-sliced NWP data
+    da_nwp = xr.DataArray(
+        np.random.normal(size=(len(target_times), len(channels), len(x), len(y))),
+        coords=dict(
+            target_time_utc=(["target_time_utc"], target_times),
+            channel=(["channel"], channels),
+            x_osgb=(["x_osgb"], x),
+            y_osgb=(["y_osgb"], y),
+        )
+    )
+
+    # Add extra non-coordinate dimensions
+    da_nwp = da_nwp.assign_coords(
+        init_time_utc=("target_time_utc", init_times),
+        step=("target_time_utc", steps),
+    )
+
+    return da_nwp
+
+
 @pytest.fixture(scope="session")
 def ds_nwp_ecmwf():
     init_times = pd.date_range(start="2023-01-01 00:00", freq="6h", periods=24 * 7)

tests/numpy_sample/test_nwp.py

@@ -1,52 +1,13 @@
-import numpy as np
-import pandas as pd
-import xarray as xr
-
-import pytest
-
 from ocf_data_sampler.numpy_sample import convert_nwp_to_numpy_sample, NWPSampleKey
 
-@pytest.fixture(scope="module")
-def da_nwp_like():
-    """Create dummy data which looks like time-sliced NWP data"""
-
-    t0 = pd.to_datetime("2024-01-02 00:00")
-
-    x = np.arange(-100, 100, 10)
-    y = np.arange(-100, 100, 10)
-    steps = pd.timedelta_range("0h", "8h", freq="1h")
-    target_times = t0 + steps
-
-    channels = ["t", "dswrf"]
-    init_times = pd.to_datetime([t0]*len(steps))
-    
-    # Create dummy time-sliced NWP data
-    da_nwp = xr.DataArray(
-        np.random.normal(size=(len(target_times), len(channels), len(x), len(y))),
-        coords=dict(
-            target_times_utc=(["target_times_utc"], target_times),
-            channel=(["channel"], channels),
-            x_osgb=(["x_osgb"], x),
-            y_osgb=(["y_osgb"], y),
-        )
-    )
-
-    # Add extra non-coordinate dimensions
-    da_nwp = da_nwp.assign_coords(
-        init_time_utc=("target_times_utc", init_times),
-        step=("target_times_utc", steps),
-    )
-
-    return da_nwp
-
 
-def test_convert_nwp_to_numpy_sample(da_nwp_like):
+def test_convert_nwp_to_numpy_sample(ds_nwp_ukv_time_sliced):
 
     # Call the function
-    numpy_sample = convert_nwp_to_numpy_sample(da_nwp_like)
+    numpy_sample = convert_nwp_to_numpy_sample(ds_nwp_ukv_time_sliced)
 
     # Assert the output type
     assert isinstance(numpy_sample, dict)
 
     # Assert the shape of the numpy sample
-    assert (numpy_sample[NWPSampleKey.nwp] == da_nwp_like.values).all()
+    assert (numpy_sample[NWPSampleKey.nwp] == ds_nwp_ukv_time_sliced.values).all()

tests/select/test_dropout.py

@@ -14,10 +14,8 @@ def da_sample():
     datetimes = pd.date_range("2024-01-01 12:00", "2024-01-01 13:00", freq="5min")
 
     da_sat = xr.DataArray(
-        np.random.normal(size=(len(datetimes),)),
-        coords=dict(
-            time_utc=(["time_utc"], datetimes),
-        )
+        np.random.normal(size=(len(datetimes))),
+        coords=dict(time_utc=datetimes)
     )
     return da_sat
 
@@ -29,7 +27,7 @@ def test_draw_dropout_time():
     dropout_time = draw_dropout_time(t0, dropout_timedeltas, dropout_frac=1)
 
     assert isinstance(dropout_time, pd.Timestamp)
-    assert dropout_time-t0 in dropout_timedeltas
+    assert (dropout_time-t0) in dropout_timedeltas
 
 
 def test_draw_dropout_time_partial():
@@ -48,21 +46,17 @@ def test_draw_dropout_time_partial():
     dropouts == {None} | set(t0 + dt for dt in dropout_timedeltas)
 
 
-def test_draw_dropout_time_none():
+def test_draw_dropout_time_null():
     t0 = pd.Timestamp("2021-01-01 04:00:00")
 
-    # No dropout timedeltas
-    dropout_time = draw_dropout_time(t0, dropout_timedeltas=None, dropout_frac=1)
-    assert dropout_time is None
-
     # Dropout fraction is 0
     dropout_timedeltas = [pd.Timedelta(-30, "min")]
     dropout_time = draw_dropout_time(t0, dropout_timedeltas=dropout_timedeltas, dropout_frac=0)
-    assert dropout_time is None
+    assert dropout_time==t0
 
     # No dropout timedeltas and dropout fraction is 0
-    dropout_time = draw_dropout_time(t0, dropout_timedeltas=None, dropout_frac=0)
-    assert dropout_time is None
+    dropout_time = draw_dropout_time(t0, dropout_timedeltas=[], dropout_frac=0)
+    assert dropout_time==t0
 
 
 @pytest.mark.parametrize("t0_str", ["12:00", "12:30", "13:00"])

tests/test_sample/test_site_sample.py

@@ -74,17 +74,9 @@ def sample_data():
     )
 
 
-def test_site_sample_init():
-    """ Test initialisation """
-    sample = SiteSample()
-    assert isinstance(sample._data, dict)
-    assert len(sample._data) == 0
-
-
 def test_site_sample_with_data(sample_data):
     """ Testing of defined sample with actual data """
-    sample = SiteSample()
-    sample._data = sample_data
+    sample = SiteSample(sample_data)
     
     # Assert data structure
     assert isinstance(sample._data, Dataset)
@@ -109,8 +101,7 @@ def test_site_sample_with_data(sample_data):
 
 def test_save_load(tmp_path, sample_data):
     """ Save and load functionality """
-    sample = SiteSample()
-    sample._data = sample_data    
+    sample = SiteSample(sample_data)
     filepath = tmp_path / "test_sample.nc"
     sample.save(filepath)
     
@@ -127,36 +118,16 @@ def test_save_load(tmp_path, sample_data):
     xr.testing.assert_identical(sample._data, loaded._data)
 
 
-def test_invalid_save_format(sample_data):
-    """ Saving with invalid format """
-    sample = SiteSample()
-    sample._data = sample_data
-    with pytest.raises(ValueError, match="Only .nc format is supported"):
-        sample.save("invalid.txt")
-
-
-def test_invalid_load_format():
-    """ Loading with invalid format """
-    with pytest.raises(ValueError, match="Only .nc format is supported"):
-        SiteSample.load("invalid.txt")
-
-
 def test_invalid_data_type():
     """ Handling of invalid data types """
-    sample = SiteSample()
-    sample._data = {"invalid": "data"}
     
     with pytest.raises(TypeError, match="Data must be xarray Dataset"):
-        sample.to_numpy()
-    
-    with pytest.raises(TypeError, match="Data must be xarray Dataset for saving"):
-        sample.save("test.nc")
+        _ = SiteSample({"invalid": "data"})
 
 
 def test_to_numpy(sample_data):
     """ To numpy conversion """
-    sample = SiteSample()
-    sample._data = sample_data
+    sample = SiteSample(sample_data)
     numpy_data = sample.to_numpy()
     
     # Assert structure
@@ -180,8 +151,7 @@ def test_to_numpy(sample_data):
 
 def test_data_consistency(sample_data):
     """ Consistency of data across operations """
-    sample = SiteSample()
-    sample._data = sample_data    
+    sample = SiteSample(sample_data)
     numpy_data = sample.to_numpy()
     
     # Assert components remain consistent after conversion above