ocf-data-sampler 0.0.25__py3-none-any.whl → 0.0.27__py3-none-any.whl

ocf_data_sampler/select/spatial_slice_for_dataset.py

@@ -30,8 +30,8 @@ def slice_datasets_by_space(
             sliced_datasets_dict["nwp"][nwp_key] = select_spatial_slice_pixels(
                 datasets_dict["nwp"][nwp_key],
                 location,
-                height_pixels=nwp_config.nwp_image_size_pixels_height,
-                width_pixels=nwp_config.nwp_image_size_pixels_width,
+                height_pixels=nwp_config.image_size_pixels_height,
+                width_pixels=nwp_config.image_size_pixels_width,
             )
 
     if "sat" in datasets_dict:
@@ -40,8 +40,8 @@ def slice_datasets_by_space(
         sliced_datasets_dict["sat"] = select_spatial_slice_pixels(
             datasets_dict["sat"],
             location,
-            height_pixels=sat_config.satellite_image_size_pixels_height,
-            width_pixels=sat_config.satellite_image_size_pixels_width,
+            height_pixels=sat_config.image_size_pixels_height,
+            width_pixels=sat_config.image_size_pixels_width,
         )
 
     if "gsp" in datasets_dict:

ocf_data_sampler/select/time_slice_for_dataset.py

@@ -4,7 +4,7 @@ import pandas as pd
 from ocf_data_sampler.config import Configuration
 from ocf_data_sampler.select.dropout import draw_dropout_time, apply_dropout_time
 from ocf_data_sampler.select.select_time_slice import select_time_slice_nwp, select_time_slice
-from ocf_data_sampler.time_functions import minutes
+from ocf_data_sampler.utils import minutes
 
 
 def slice_datasets_by_time(
@@ -23,22 +23,22 @@ def slice_datasets_by_time(
     sliced_datasets_dict = {}
 
     if "nwp" in datasets_dict:
-
+        
         sliced_datasets_dict["nwp"] = {}
-
+        
         for nwp_key, da_nwp in datasets_dict["nwp"].items():
-
+                            
             nwp_config = config.input_data.nwp[nwp_key]
 
             sliced_datasets_dict["nwp"][nwp_key] = select_time_slice_nwp(
                 da_nwp,
                 t0,
                 sample_period_duration=minutes(nwp_config.time_resolution_minutes),
-                history_duration=minutes(nwp_config.history_minutes),
-                forecast_duration=minutes(nwp_config.forecast_minutes),
+                interval_start=minutes(nwp_config.interval_start_minutes),
+                interval_end=minutes(nwp_config.interval_end_minutes),
                 dropout_timedeltas=minutes(nwp_config.dropout_timedeltas_minutes),
                 dropout_frac=nwp_config.dropout_fraction,
-                accum_channels=nwp_config.nwp_accum_channels,
+                accum_channels=nwp_config.accum_channels,
             )
 
     if "sat" in datasets_dict:
@@ -49,8 +49,8 @@ def slice_datasets_by_time(
             datasets_dict["sat"],
             t0,
             sample_period_duration=minutes(sat_config.time_resolution_minutes),
-            interval_start=minutes(-sat_config.history_minutes),
-            interval_end=minutes(-sat_config.live_delay_minutes),
+            interval_start=minutes(sat_config.interval_start_minutes),
+            interval_end=minutes(sat_config.interval_end_minutes),
             max_steps_gap=2,
         )
 
@@ -74,15 +74,15 @@ def slice_datasets_by_time(
             datasets_dict["gsp"],
             t0,
             sample_period_duration=minutes(gsp_config.time_resolution_minutes),
-            interval_start=minutes(30),
-            interval_end=minutes(gsp_config.forecast_minutes),
+            interval_start=minutes(gsp_config.time_resolution_minutes),
+            interval_end=minutes(gsp_config.interval_end_minutes),
         )
-
+    
         sliced_datasets_dict["gsp"] = select_time_slice(
             datasets_dict["gsp"],
             t0,
             sample_period_duration=minutes(gsp_config.time_resolution_minutes),
-            interval_start=-minutes(gsp_config.history_minutes),
+            interval_start=minutes(gsp_config.interval_start_minutes),
             interval_end=minutes(0),
         )
 
@@ -94,9 +94,10 @@ def slice_datasets_by_time(
         )
 
         sliced_datasets_dict["gsp"] = apply_dropout_time(
-            sliced_datasets_dict["gsp"], gsp_dropout_time
+            sliced_datasets_dict["gsp"], 
+            gsp_dropout_time
         )
-
+    
     if "site" in datasets_dict:
         site_config = config.input_data.site
 
@@ -104,8 +105,8 @@ def slice_datasets_by_time(
             datasets_dict["site"],
             t0,
             sample_period_duration=minutes(site_config.time_resolution_minutes),
-            interval_start=-minutes(site_config.history_minutes),
-            interval_end=minutes(site_config.forecast_minutes),
+            interval_start=minutes(site_config.interval_start_minutes),
+            interval_end=minutes(site_config.interval_end_minutes),
         )
 
         # Randomly sample dropout

ocf_data_sampler/torch_datasets/process_and_combine.py

@@ -15,7 +15,7 @@ from ocf_data_sampler.numpy_batch.gsp import GSPBatchKey
 from ocf_data_sampler.numpy_batch.nwp import NWPBatchKey
 from ocf_data_sampler.select.geospatial import osgb_to_lon_lat
 from ocf_data_sampler.select.location import Location
-from ocf_data_sampler.time_functions import minutes
+from ocf_data_sampler.utils import minutes
 
 
 def process_and_combine_datasets(
@@ -23,7 +23,7 @@ def process_and_combine_datasets(
     config: Configuration,
     t0: pd.Timestamp,
     location: Location,
-    sun_position_key: str = 'gsp'
+    target_key: str = 'gsp'
 ) -> dict:
     """Normalize and convert data to numpy arrays"""
 
@@ -35,7 +35,7 @@ def process_and_combine_datasets(
 
         for nwp_key, da_nwp in dataset_dict["nwp"].items():
             # Standardise
-            provider = config.input_data.nwp[nwp_key].nwp_provider
+            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_batch(da_nwp)
@@ -58,7 +58,8 @@ def process_and_combine_datasets(
 
         numpy_modalities.append(
             convert_gsp_to_numpy_batch(
-                da_gsp, t0_idx=gsp_config.history_minutes // gsp_config.time_resolution_minutes
+                da_gsp, 
+                t0_idx=-gsp_config.interval_start_minutes / gsp_config.time_resolution_minutes
             )
         )
 
@@ -80,34 +81,32 @@ def process_and_combine_datasets(
 
         numpy_modalities.append(
             convert_site_to_numpy_batch(
-                da_sites, t0_idx=site_config.history_minutes / site_config.time_resolution_minutes
+                da_sites, t0_idx=-site_config.interval_start_minutes / site_config.time_resolution_minutes
             )
         )
 
-    if sun_position_key == 'gsp':
+    if target_key == 'gsp':
         # Make sun coords NumpyBatch
         datetimes = pd.date_range(
-            t0 - minutes(gsp_config.history_minutes),
-            t0 + minutes(gsp_config.forecast_minutes),
+            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)
-        key_prefix = "gsp"
 
-    elif sun_position_key == 'site':
+    elif target_key == 'site':
         # Make sun coords NumpyBatch
         datetimes = pd.date_range(
-            t0 - minutes(site_config.history_minutes),
-            t0 + minutes(site_config.forecast_minutes),
+            t0+minutes(site_config.interval_start_minutes),
+            t0+minutes(site_config.interval_end_minutes),
             freq=minutes(site_config.time_resolution_minutes),
         )
 
         lon, lat = location.x, location.y
-        key_prefix = "site"
 
     numpy_modalities.append(
-        make_sun_position_numpy_batch(datetimes, lon, lat, key_prefix=key_prefix)
+        make_sun_position_numpy_batch(datetimes, lon, lat, key_prefix=target_key)
     )
 
     # Combine all the modalities and fill NaNs

ocf_data_sampler/torch_datasets/pvnet_uk_regional.py

@@ -9,7 +9,7 @@ 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.time_functions import minutes
+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
 

ocf_data_sampler/torch_datasets/site.py

@@ -14,7 +14,7 @@ from ocf_data_sampler.select import (
     intersection_of_multiple_dataframes_of_periods,
     slice_datasets_by_time, slice_datasets_by_space
 )
-from ocf_data_sampler.time_functions import minutes
+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
 
@@ -22,8 +22,8 @@ xr.set_options(keep_attrs=True)
 
 
 def find_valid_t0_and_site_ids(
-        datasets_dict: dict,
-        config: Configuration,
+    datasets_dict: dict,
+    config: Configuration,
 ) -> pd.DataFrame:
     """Find the t0 times where all of the requested input data is available
 
@@ -57,8 +57,8 @@ def find_valid_t0_and_site_ids(
         time_periods = find_contiguous_t0_periods(
             pd.DatetimeIndex(site["time_utc"]),
             sample_period_duration=minutes(site_config.time_resolution_minutes),
-            history_duration=minutes(site_config.history_minutes),
-            forecast_duration=minutes(site_config.forecast_minutes),
+            interval_start=minutes(site_config.interval_start_minutes),
+            interval_end=minutes(site_config.interval_end_minutes),
         )
         valid_time_periods_per_site = intersection_of_multiple_dataframes_of_periods(
             [valid_time_periods, time_periods]
@@ -100,10 +100,10 @@ def get_locations(site_xr: xr.Dataset):
 
 class SitesDataset(Dataset):
     def __init__(
-            self,
-            config_filename: str,
-            start_time: str | None = None,
-            end_time: str | None = None,
+        self,
+        config_filename: str,
+        start_time: str | None = None,
+        end_time: str | None = None,
     ):
         """A torch Dataset for creating PVNet Site samples
 
@@ -154,7 +154,7 @@ class SitesDataset(Dataset):
         sample_dict = slice_datasets_by_time(sample_dict, t0, self.config)
         sample_dict = compute(sample_dict)
 
-        sample = process_and_combine_datasets(sample_dict, self.config, t0, location, sun_position_key='site')
+        sample = process_and_combine_datasets(sample_dict, self.config, t0, location, target_key='site')
 
         return sample
 

ocf_data_sampler/torch_datasets/valid_time_periods.py

@@ -2,9 +2,13 @@ import numpy as np
 import pandas as pd
 
 from ocf_data_sampler.config import Configuration
-from ocf_data_sampler.select.find_contiguous_time_periods import find_contiguous_t0_periods_nwp, \
-    find_contiguous_t0_periods, intersection_of_multiple_dataframes_of_periods
-from ocf_data_sampler.time_functions import minutes
+from ocf_data_sampler.select.find_contiguous_time_periods import (
+    find_contiguous_t0_periods_nwp,
+    find_contiguous_t0_periods, 
+    intersection_of_multiple_dataframes_of_periods,
+)
+from ocf_data_sampler.utils import minutes
+
 
 
 def find_valid_time_periods(
@@ -38,7 +42,7 @@ def find_valid_time_periods(
                 max_staleness = minutes(nwp_config.max_staleness_minutes)
 
             # The last step of the forecast is lost if we have to diff channels
-            if len(nwp_config.nwp_accum_channels) > 0:
+            if len(nwp_config.accum_channels) > 0:
                 end_buffer = minutes(nwp_config.time_resolution_minutes)
             else:
                 end_buffer = minutes(0)
@@ -46,7 +50,7 @@ def find_valid_time_periods(
             # This is the max staleness we can use considering the max step of the input data
             max_possible_staleness = (
                 pd.Timedelta(da["step"].max().item())
-                - minutes(nwp_config.forecast_minutes)
+                - minutes(nwp_config.interval_end_minutes)
                 - end_buffer
             )
 
@@ -56,12 +60,16 @@ def find_valid_time_periods(
             else:
                 # Make sure the max acceptable staleness isn't longer than the max possible
                 assert max_staleness <= max_possible_staleness
+                
+            # Find the first forecast step
+            first_forecast_step = pd.Timedelta(da["step"].min().item())
 
             time_periods = find_contiguous_t0_periods_nwp(
-                datetimes=pd.DatetimeIndex(da["init_time_utc"]),
-                history_duration=minutes(nwp_config.history_minutes),
+                init_times=pd.DatetimeIndex(da["init_time_utc"]),
+                interval_start=minutes(nwp_config.interval_start_minutes),
                 max_staleness=max_staleness,
                 max_dropout=max_dropout,
+                first_forecast_step = first_forecast_step,
             )
 
             contiguous_time_periods[f'nwp_{nwp_key}'] = time_periods
@@ -72,8 +80,8 @@ def find_valid_time_periods(
         time_periods = find_contiguous_t0_periods(
             pd.DatetimeIndex(datasets_dict["sat"]["time_utc"]),
             sample_period_duration=minutes(sat_config.time_resolution_minutes),
-            history_duration=minutes(sat_config.history_minutes),
-            forecast_duration=minutes(sat_config.forecast_minutes),
+            interval_start=minutes(sat_config.interval_start_minutes),
+            interval_end=minutes(sat_config.interval_end_minutes),
         )
 
         contiguous_time_periods['sat'] = time_periods
@@ -84,8 +92,8 @@ def find_valid_time_periods(
         time_periods = find_contiguous_t0_periods(
             pd.DatetimeIndex(datasets_dict["gsp"]["time_utc"]),
             sample_period_duration=minutes(gsp_config.time_resolution_minutes),
-            history_duration=minutes(gsp_config.history_minutes),
-            forecast_duration=minutes(gsp_config.forecast_minutes),
+            interval_start=minutes(gsp_config.interval_start_minutes),
+            interval_end=minutes(gsp_config.interval_end_minutes),
         )
 
         contiguous_time_periods['gsp'] = time_periods
@@ -105,4 +113,4 @@ def find_valid_time_periods(
     if len(valid_time_periods) == 0:
         raise ValueError(f"No valid time periods found, {contiguous_time_periods=}")
 
-    return valid_time_periods
+    return valid_time_periods

ocf_data_sampler/{time_functions.py → utils.py}

@@ -7,5 +7,4 @@ def minutes(minutes: int | list[float]) -> pd.Timedelta | pd.TimedeltaIndex:
     Args:
         minutes: the number of minutes, single value or list
     """
-    minutes_delta = pd.to_timedelta(minutes, unit="m")
-    return minutes_delta
+    return pd.to_timedelta(minutes, unit="m")

{ocf_data_sampler-0.0.25.dist-info → ocf_data_sampler-0.0.27.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ocf_data_sampler
-Version: 0.0.25
+Version: 0.0.27
 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-0.0.25.dist-info → ocf_data_sampler-0.0.27.dist-info}/RECORD

@@ -1,14 +1,14 @@
 ocf_data_sampler/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 ocf_data_sampler/constants.py,sha256=tUwHrsGShqIn5Izze4i32_xB6X0v67rvQwIYB-P5PJQ,3355
-ocf_data_sampler/time_functions.py,sha256=R6ZlVEe6h4UlJeUW7paZYAMWveOv9MTjMsoISCwnsiE,284
+ocf_data_sampler/utils.py,sha256=rKA0BHAyAG4f90zEcgxp25EEYrXS-aOVNzttZ6Mzv2k,250
 ocf_data_sampler/config/__init__.py,sha256=YXnAkgHViHB26hSsjiv32b6EbpG-A1kKTkARJf0_RkY,212
 ocf_data_sampler/config/load.py,sha256=4f7vPHAIAmd-55tPxoIzn7F_TI_ue4NxkDcLPoVWl0g,943
-ocf_data_sampler/config/model.py,sha256=5GO8SF_4iOZhCAyIJyENSl0dnDRIWrURgqwslrVWke8,9462
+ocf_data_sampler/config/model.py,sha256=sXmh7IadwXDT-7lxEl5_b3vjovZgZYR77EXy4GHaf4w,7276
 ocf_data_sampler/config/save.py,sha256=wKdctbv0dxIIiQtcRHLRxpWQVhEFQ_FCWg-oNaRLIps,1093
 ocf_data_sampler/data/uk_gsp_locations.csv,sha256=RSh7DRh55E3n8lVAaWXGTaXXHevZZtI58td4d4DhGos,10415772
 ocf_data_sampler/load/__init__.py,sha256=MjgfxilTzyz1RYFoBEeAXmE9hyjknLvdmlHPmlAoiQY,44
 ocf_data_sampler/load/gsp.py,sha256=Gcr1JVUOPKhFRDCSHtfPDjxx0BtyyEhXrZvGEKLPJ5I,759
-ocf_data_sampler/load/load_dataset.py,sha256=R4RAIVLVx6CHA6Qs61kD9sx834I_GMGAn6G7ZgwFMUA,1627
+ocf_data_sampler/load/load_dataset.py,sha256=Ua3RaUg4PIYJkD9BKqTfN8IWUbezbhThJGgEkd9PcaE,1587
 ocf_data_sampler/load/satellite.py,sha256=3KlA1fx4SwxdzM-jC1WRaONXO0D6m0WxORnEnwUnZrA,2967
 ocf_data_sampler/load/site.py,sha256=ROif2XXIIgBz-JOOiHymTq1CMXswJ3AzENU9DJmYpcU,782
 ocf_data_sampler/load/utils.py,sha256=EQGvVWlGMoSOdbDYuMfVAa0v6wmAOPmHIAemdrTB5v4,1406
@@ -27,22 +27,22 @@ ocf_data_sampler/numpy_batch/sun_position.py,sha256=zw2bjtcjsm_tvKk0r_MZmgfYUJLH
 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=iTtMjIPFYG5xtUYYedAFBLjTWWUa7t7WQ0-yksWf0-E,440
-ocf_data_sampler/select/find_contiguous_time_periods.py,sha256=6ioB8LeFpFNBMgKDxrgG3zqzNjkBF_jlV9yye2ZYT2E,11925
+ocf_data_sampler/select/find_contiguous_time_periods.py,sha256=q7IaNfX95A3z9XHqbhgtkZ4Js1gn5K9Qyp6DVLbsL-Q,11093
 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=41cch1fQr59fZgv7UHsNGc3OvoynrixT3bmr3_1d7cU,6628
-ocf_data_sampler/select/spatial_slice_for_dataset.py,sha256=Nrc3j8DR5MM4BPPp9IQwaIMpoyOkc6AADMnfOjg-170,1791
-ocf_data_sampler/select/time_slice_for_dataset.py,sha256=A9fxvurbM0JSRkrjyg5Lr70_Mj6t5OO7HFqHUZel9q4,4220
+ocf_data_sampler/select/select_time_slice.py,sha256=D5P_cSvnv8Qs49K5au7lPxDr9U_VmDn42s5leMzHt0k,6122
+ocf_data_sampler/select/spatial_slice_for_dataset.py,sha256=3tRrMBXr7s4CnClbVSIq7hpls3H4Y3qYTDwswcxCCCE,1763
+ocf_data_sampler/select/time_slice_for_dataset.py,sha256=LMw8KnOCKnPjD0m4UubAWERpaiQtzRKkI2cSh5a0A-M,4335
 ocf_data_sampler/torch_datasets/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-ocf_data_sampler/torch_datasets/process_and_combine.py,sha256=Lovc2UM3-HgUy2BoQEIr0gQTz3USW6ACRWo-iTgxjHs,4993
-ocf_data_sampler/torch_datasets/pvnet_uk_regional.py,sha256=TpHALGU7hpo3iLbvD0nkoY6zu94Vq99W1V1qSGEcIW8,5552
-ocf_data_sampler/torch_datasets/site.py,sha256=1k0fWXYwAAIWG5DX_j3tgNfY8gglfPGLNzNlZd8EnJs,6631
-ocf_data_sampler/torch_datasets/valid_time_periods.py,sha256=dNJkBH5wdsFUjoFSmthU3yTqar6OPE77WsRQUebm-PY,4163
+ocf_data_sampler/torch_datasets/process_and_combine.py,sha256=4k6f6PlMqrg3luMwGw3764iOyfuUNUePKyoikYGaRMI,4953
+ocf_data_sampler/torch_datasets/pvnet_uk_regional.py,sha256=QRFqbdfNchVWj4y70n-rJdFvFGvQj-WpZLdFqWjnOTw,5543
+ocf_data_sampler/torch_datasets/site.py,sha256=lo2ULurfWNu9vzBC6H4pdKMMpUMIT8_FWC1l_1mgIOM,6596
+ocf_data_sampler/torch_datasets/valid_time_periods.py,sha256=Qo65qUHtle_bW5tLTYr7empHTRv-lpjvfx_6GNJj3Xg,4371
 scripts/refactor_site.py,sha256=asZ27hQ4IyXgCCUaFJqcz1ObBNcV2W3ywqHBpSXA_fc,1728
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/conftest.py,sha256=ZRktySCynj3NBbFRR4EFNLRLFMErkQsC-qQlmQzhbRg,7360
-tests/config/test_config.py,sha256=G_PD_pXib0zdRBPUIn0jjwJ9VyoKaO_TanLN1Mh5Ca4,5055
+tests/conftest.py,sha256=N-_XgXpWeTRhkwP_NVh2mBORt2LKkM4mbkm-O62RN5I,7363
+tests/config/test_config.py,sha256=eaye_F7-el4tTP4n2vRME8qlV0b2jaKUX4HhgOUpa7E,5203
 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=STX5AqqmOAgUgE9R1xyq_sM3P1b8NKdGjO-hDhayfxM,524
@@ -53,14 +53,14 @@ tests/numpy_batch/test_satellite.py,sha256=8a4ZwMLpsOmYKmwI1oW_su_hwkCNYMEJAEfa0
 tests/numpy_batch/test_sun_position.py,sha256=FYQ7KtlN0V5LlEjgI-cKjTMtGHUCxiMvxkRYTdMAgEE,2485
 tests/select/test_dropout.py,sha256=kiycl7RxAQYMCZJlokmx6Da5h_oBpSs8Is8pmSW4gOU,2413
 tests/select/test_fill_time_periods.py,sha256=o59f2YRe5b0vJrG3B0aYZkYeHnpNk4s6EJxdXZluNQg,907
-tests/select/test_find_contiguous_time_periods.py,sha256=G6tJRJd0DMfH9EdfzlKWsmfTbtMwOf3w-2filjJzuIQ,5998
+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=XC1J3DBBDnt81jcba5u-Hnd0yKv8GIQErLm-OECV6rs,10147
-tests/torch_datasets/test_pvnet_uk_regional.py,sha256=u3taw6p3oozM0_7cEEhCYbImAQPRldRhpruqSyV08Vg,2675
-tests/torch_datasets/test_site.py,sha256=5hdUP64neCDWEo2NMSd-MhbpuQjQvD6NOvhZ1DlMmo8,2733
-ocf_data_sampler-0.0.25.dist-info/LICENSE,sha256=F-Q3UFCR-BECSocV55BFDpn4YKxve9PKrm-lTt6o_Tg,1073
-ocf_data_sampler-0.0.25.dist-info/METADATA,sha256=p3SKEM4gRy0Z4LTcRWlgTrpjQ-QV89ar69tM9EwhudU,5269
-ocf_data_sampler-0.0.25.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-ocf_data_sampler-0.0.25.dist-info/top_level.txt,sha256=Faob6N6cFdPc5eUpCTYcXgCaNhi4XLLteUL5W5ayYmg,31
-ocf_data_sampler-0.0.25.dist-info/RECORD,,
+tests/select/test_select_time_slice.py,sha256=QOhoR3qsr7RBGze4yohcViZ-ad1zYQzIKzxlnf0ymnU,9603
+tests/torch_datasets/test_pvnet_uk_regional.py,sha256=8gxjJO8FhY-ImX6eGnihDFsa8fhU2Zb4bVJaToJwuwo,2653
+tests/torch_datasets/test_site.py,sha256=yTv6tAT6lha5yLYJiC8DNms1dct8o_ObPV97dHZyT7I,2719
+ocf_data_sampler-0.0.27.dist-info/LICENSE,sha256=F-Q3UFCR-BECSocV55BFDpn4YKxve9PKrm-lTt6o_Tg,1073
+ocf_data_sampler-0.0.27.dist-info/METADATA,sha256=bMOcVYluH-m7tyVm2J0Vz2T3ZLqNtEoX0HUwUvZMfEw,5269
+ocf_data_sampler-0.0.27.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
+ocf_data_sampler-0.0.27.dist-info/top_level.txt,sha256=Faob6N6cFdPc5eUpCTYcXgCaNhi4XLLteUL5W5ayYmg,31
+ocf_data_sampler-0.0.27.dist-info/RECORD,,

{ocf_data_sampler-0.0.25.dist-info → ocf_data_sampler-0.0.27.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.3.0)
+Generator: setuptools (75.5.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

tests/config/test_config.py

@@ -10,13 +10,13 @@ from ocf_data_sampler.config import (
 )
 
 
-def test_default():
+def test_default_configuration():
     """Test default pydantic class"""
 
     _ = Configuration()
 
 
-def test_yaml_load_test_config(test_config_filename):
+def test_load_yaml_configuration(test_config_filename):
     """
     Test that yaml loading works for 'test_config.yaml'
     and fails for an empty .yaml file
@@ -56,7 +56,7 @@ def test_yaml_save(test_config_filename):
         assert test_config == tmp_config
 
 
-def test_extra_field():
+def test_extra_field_error():
     """
     Check an extra parameters in config causes error
     """
@@ -68,27 +68,33 @@ def test_extra_field():
         _ = Configuration(**configuration_dict)
 
 
-def test_incorrect_forecast_minutes(test_config_filename):
+def test_incorrect_interval_start_minutes(test_config_filename):
     """
-    Check a forecast length not divisible by time resolution causes error
+    Check a history length not divisible by time resolution causes error
     """
 
     configuration = load_yaml_configuration(test_config_filename)
 
-    configuration.input_data.nwp['ukv'].forecast_minutes = 1111
-    with pytest.raises(Exception, match="duration must be divisible by time resolution"):
+    configuration.input_data.nwp['ukv'].interval_start_minutes = -1111
+    with pytest.raises(
+        ValueError, 
+        match="interval_start_minutes must be divisible by time_resolution_minutes"
+    ):
         _ = Configuration(**configuration.model_dump())
 
 
-def test_incorrect_history_minutes(test_config_filename):
+def test_incorrect_interval_end_minutes(test_config_filename):
     """
-    Check a history length not divisible by time resolution causes error
+    Check a forecast length not divisible by time resolution causes error
     """
 
     configuration = load_yaml_configuration(test_config_filename)
 
-    configuration.input_data.nwp['ukv'].history_minutes = 1111
-    with pytest.raises(Exception, match="duration must be divisible by time resolution"):
+    configuration.input_data.nwp['ukv'].interval_end_minutes = 1111
+    with pytest.raises(
+        ValueError, 
+        match="interval_end_minutes must be divisible by time_resolution_minutes"
+    ):
         _ = Configuration(**configuration.model_dump())
 
 
@@ -99,10 +105,11 @@ def test_incorrect_nwp_provider(test_config_filename):
 
     configuration = load_yaml_configuration(test_config_filename)
 
-    configuration.input_data.nwp['ukv'].nwp_provider = "unexpected_provider"
+    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
@@ -119,6 +126,7 @@ def test_incorrect_dropout(test_config_filename):
     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
@@ -127,11 +135,12 @@ def test_incorrect_dropout_fraction(test_config_filename):
     configuration = load_yaml_configuration(test_config_filename)
 
     configuration.input_data.nwp['ukv'].dropout_fraction= 1.1
-    with pytest.raises(Exception, match="Dropout fraction must be between 0 and 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(Exception, match="Dropout fraction must be between 0 and 1"):
+    with pytest.raises(ValidationError, match="Input should be greater than or equal to 0"):
         _ = Configuration(**configuration.model_dump())
 
 

tests/conftest.py

@@ -250,11 +250,13 @@ def data_sites() -> Site:
         generation.to_netcdf(filename)
         meta_df.to_csv(filename_csv)
 
-        site = Site(file_path=filename,
-                    metadata_file_path=filename_csv,
-                    time_resolution_minutes=30,
-                    forecast_minutes=60,
-                    history_minutes=30)
+        site = Site(
+            file_path=filename,
+            metadata_file_path=filename_csv,
+            interval_start_minutes=-30,
+            interval_end_minutes=60,
+            time_resolution_minutes=30,
+        )
 
         yield site
 

tests/select/test_find_contiguous_time_periods.py

@@ -11,8 +11,8 @@ def test_find_contiguous_t0_periods():
 
     # Create 5-minutely data timestamps
     freq = pd.Timedelta(5, "min")
-    history_duration = pd.Timedelta(60, "min")
-    forecast_duration = pd.Timedelta(15, "min")
+    interval_start = pd.Timedelta(-60, "min")
+    interval_end = pd.Timedelta(15, "min")
 
     datetimes = (
         pd.date_range("2023-01-01 12:00", "2023-01-01 17:00", freq=freq)
@@ -21,8 +21,8 @@ def test_find_contiguous_t0_periods():
 
     periods = find_contiguous_t0_periods(
         datetimes=datetimes,
-        history_duration=history_duration,
-        forecast_duration=forecast_duration,
+        interval_start=interval_start,
+        interval_end=interval_end,
         sample_period_duration=freq,
     )
 
@@ -135,7 +135,7 @@ def test_find_contiguous_t0_periods_nwp():
     # Create 3-hourly init times with a few time stamps missing
     freq = pd.Timedelta(3, "h")
 
-    datetimes = (
+    init_times = (
         pd.date_range("2023-01-01 03:00", "2023-01-02 21:00", freq=freq)
         .delete([1, 4, 5, 6, 7, 9, 10])
     )
@@ -146,13 +146,13 @@ def test_find_contiguous_t0_periods_nwp():
     max_dropouts_hr = [0, 0, 0, 0, 3]
 
     for i in range(len(expected_results)):
-        history_duration = pd.Timedelta(history_durations_hr[i], "h")
+        interval_start = pd.Timedelta(-history_durations_hr[i], "h")
         max_staleness = pd.Timedelta(max_stalenesses_hr[i], "h")
         max_dropout = pd.Timedelta(max_dropouts_hr[i], "h")
 
         time_periods = find_contiguous_t0_periods_nwp(
-            datetimes=datetimes,
-            history_duration=history_duration,
+            init_times=init_times,
+            interval_start=interval_start,
             max_staleness=max_staleness,
             max_dropout=max_dropout,
         )