ocf-data-sampler 0.0.46__py3-none-any.whl → 0.0.48__py3-none-any.whl

ocf_data_sampler/numpy_sample/site.py

@@ -13,7 +13,7 @@ class SiteSampleKey:
     solar_elevation = "site_solar_elevation"
     id = "site_id"
 
-
+# TODO update to include trig datetime + solar coords
 def convert_site_to_numpy_sample(da: xr.DataArray, t0_idx: int | None = None) -> dict:
     """Convert from Xarray to NumpySample"""
 
@@ -22,6 +22,7 @@ def convert_site_to_numpy_sample(da: xr.DataArray, t0_idx: int | None = None) ->
         SiteSampleKey.generation: da.values,
         SiteSampleKey.capacity_kwp: da.isel(time_utc=0)["capacity_kwp"].values,
         SiteSampleKey.time_utc: da["time_utc"].values.astype(float),
+        SiteSampleKey.id: da["site_id"].values,
     }
 
     if t0_idx is not None:

ocf_data_sampler/select/select_time_slice.py

@@ -3,7 +3,6 @@ import pandas as pd
 import numpy as np
 
 
-
 def _sel_fillnan(
         da: xr.DataArray, 
         start_dt: pd.Timestamp, 
@@ -25,17 +24,6 @@ def _sel_default(
     return da.sel(time_utc=slice(start_dt, end_dt))
 
 
-# TODO either implement this or remove it, which would tidy up the code
-def _sel_fillinterp(
-        da: xr.DataArray, 
-        start_dt: pd.Timestamp, 
-        end_dt: pd.Timestamp, 
-        sample_period_duration: pd.Timedelta,
-    ) -> xr.DataArray:
-    """Select a time slice from a DataArray, filling missing times with linear interpolation."""
-    return NotImplemented
-
-
 def select_time_slice(
     ds: xr.DataArray,
     t0: pd.Timestamp,
@@ -43,17 +31,10 @@ def select_time_slice(
     interval_end: pd.Timedelta,
     sample_period_duration: pd.Timedelta,
     fill_selection: bool = False,
-    max_steps_gap: int = 0,
 ):
     """Select a time slice from a Dataset or DataArray."""
-    assert max_steps_gap >= 0, "max_steps_gap must be >= 0 "
     
-    if fill_selection and max_steps_gap == 0:
-        _sel = _sel_fillnan
-    elif fill_selection and max_steps_gap > 0:
-        _sel = _sel_fillinterp
-    else:
-        _sel = _sel_default
+    _sel = _sel_fillnan if fill_selection else _sel_default
 
     t0_datetime_utc = pd.Timestamp(t0)
     start_dt = t0_datetime_utc + interval_start

ocf_data_sampler/select/time_slice_for_dataset.py

@@ -51,7 +51,6 @@ def slice_datasets_by_time(
             sample_period_duration=minutes(sat_config.time_resolution_minutes),
             interval_start=minutes(sat_config.interval_start_minutes),
             interval_end=minutes(sat_config.interval_end_minutes),
-            max_steps_gap=2,
         )
 
         # Randomly sample dropout
@@ -122,4 +121,4 @@ def slice_datasets_by_time(
             site_dropout_time,
         )
 
-    return sliced_datasets_dict
+    return sliced_datasets_dict

ocf_data_sampler/torch_datasets/datasets/site.py

@@ -257,6 +257,8 @@ class SitesDataset(Dataset):
         )
         combined_sample_dataset = xr.merge([combined_sample_dataset, sun_position_features_xr])
 
+        # TODO include t0_index in xr dataset? 
+
         # Fill any nan values
         return combined_sample_dataset.fillna(0.0)
 
@@ -317,6 +319,26 @@ class SitesDataset(Dataset):
 
 # ----- functions to load presaved samples ------
 
+def convert_netcdf_to_numpy_sample(ds: xr.Dataset) -> dict:
+    """Convert a netcdf dataset to a numpy sample"""
+
+    # convert the single dataset to a dict of arrays
+    sample_dict = convert_from_dataset_to_dict_datasets(ds) 
+
+    if "satellite" in sample_dict:
+        # rename satellite to satellite actual # TODO this could be improves
+        sample_dict["sat"] = sample_dict.pop("satellite")
+
+    # process and combine the datasets
+    sample = convert_to_numpy_and_combine(
+        dataset_dict=sample_dict,
+    )
+
+    # TODO think about normalization, maybe its done not in sample creation, maybe its done afterwards,
+    #  to allow it to be flexible
+
+    return sample
+
 def convert_from_dataset_to_dict_datasets(combined_dataset: xr.Dataset) -> dict[str, xr.DataArray]:
     """
     Convert a combined sample dataset to a dict of datasets for each input
@@ -360,26 +382,6 @@ def nest_nwp_source_dict(d: dict, sep: str = "/") -> dict:
         new_dict["nwp"] = nwp_subdict
     return new_dict
 
-def convert_netcdf_to_numpy_sample(ds: xr.Dataset) -> dict:
-    """Convert a netcdf dataset to a numpy sample"""
-
-    # convert the single dataset to a dict of arrays
-    sample_dict = convert_from_dataset_to_dict_datasets(ds) 
-
-    if "satellite" in sample_dict:
-        # rename satellite to satellite actual # TODO this could be improves
-        sample_dict["sat"] = sample_dict.pop("satellite")
-
-    # process and combine the datasets
-    sample = convert_to_numpy_and_combine(
-        dataset_dict=sample_dict,
-    )
-
-    # TODO think about normalization, maybe its done not in sample creation, maybe its done afterwards,
-    #  to allow it to be flexible
-
-    return sample
-
 def convert_to_numpy_and_combine(
     dataset_dict: dict,
 ) -> dict:
@@ -406,7 +408,6 @@ def convert_to_numpy_and_combine(
 
     if "site" in dataset_dict:
         da_sites = dataset_dict["site"]
-        sites_sample = convert_site_to_numpy_sample(da_sites)
 
         numpy_modalities.append(
             convert_site_to_numpy_sample(
@@ -414,8 +415,6 @@ def convert_to_numpy_and_combine(
             )
         )
 
-        numpy_modalities.append(sites_sample)
-
     # Combine all the modalities and fill NaNs
     combined_sample = merge_dicts(numpy_modalities)
     combined_sample = fill_nans_in_arrays(combined_sample)

{ocf_data_sampler-0.0.46.dist-info → ocf_data_sampler-0.0.48.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ocf_data_sampler
-Version: 0.0.46
+Version: 0.0.48
 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-0.0.46.dist-info → ocf_data_sampler-0.0.48.dist-info}/RECORD

@@ -24,7 +24,7 @@ ocf_data_sampler/numpy_sample/datetime_features.py,sha256=U-9uRplfZ7VYFA4qBduI8O
 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=PIfmCtPA37dqpC8GArkryVqFrNAwqacj0iW2ikBOdSk,789
+ocf_data_sampler/numpy_sample/site.py,sha256=cOVpFN_EVRD0d4TJtmPdNYcWjiWuWr8eswktC97KR8Q,890
 ocf_data_sampler/numpy_sample/sun_position.py,sha256=UklhucCxCT6GMlAhCWL6c4cfWrdc1cWgegrYaqUoHOY,1611
 ocf_data_sampler/select/__init__.py,sha256=E4AJulEbO2K-o0UlG1fgaEteuf_1ZFjHTvrotXSb4YU,332
 ocf_data_sampler/select/dropout.py,sha256=HCx5Wzk8Oh2Z9vV94Jy-ALJsHtGduwvMaQOleQXp5z0,1142
@@ -33,12 +33,12 @@ ocf_data_sampler/select/find_contiguous_time_periods.py,sha256=q7IaNfX95A3z9XHqb
 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=D5P_cSvnv8Qs49K5au7lPxDr9U_VmDn42s5leMzHt0k,6122
+ocf_data_sampler/select/select_time_slice.py,sha256=gFeuAuV2C7DJMHgiTHqjRUXOdfI-iraVF5NIzWhewFQ,5524
 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/select/time_slice_for_dataset.py,sha256=BFjNwWAzhcb1hpqx7UPi5RF9WWt15owbZp1WB-uGA6Q,4305
 ocf_data_sampler/torch_datasets/datasets/__init__.py,sha256=nJUa2KzVa84ZoM0PT2AbDz26ennmAYc7M7WJVfypPMs,85
 ocf_data_sampler/torch_datasets/datasets/pvnet_uk_regional.py,sha256=xxeX4Js9LQpydehi3BS7k9psqkYGzgJuM17uTYux40M,8742
-ocf_data_sampler/torch_datasets/datasets/site.py,sha256=7gTtXG3DFzs_0XlYK0oleFPT-Gena_NSngcG_FAnY54,15394
+ocf_data_sampler/torch_datasets/datasets/site.py,sha256=75M0oDstOLyLZBySVIS6fLJSbEjfxcWBlgGP_ewui7s,15334
 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
 scripts/refactor_site.py,sha256=asZ27hQ4IyXgCCUaFJqcz1ObBNcV2W3ywqHBpSXA_fc,1728
@@ -66,8 +66,8 @@ tests/torch_datasets/conftest.py,sha256=eRCzHE7cxS4AoskExkCGFDBeqItktAYNAdkfpMoF
 tests/torch_datasets/test_merge_and_fill_utils.py,sha256=ueA0A7gZaWEgNdsU8p3CnKuvSnlleTUjEhSw2HUUROM,1229
 tests/torch_datasets/test_pvnet_uk_regional.py,sha256=FCiFueeFqrsXe7gWguSjBz5ZeUrvyhGbGw81gaVvkHM,5087
 tests/torch_datasets/test_site.py,sha256=0tnjgx6z4VlzjoF_V2p3Y2t2Z1d0o_07Vwb-FH_c3tU,4640
-ocf_data_sampler-0.0.46.dist-info/LICENSE,sha256=F-Q3UFCR-BECSocV55BFDpn4YKxve9PKrm-lTt6o_Tg,1073
-ocf_data_sampler-0.0.46.dist-info/METADATA,sha256=S8ScJ8z3O0O5qhgGZmdI0Ugan2Yz4dH0nGj9R8N1sgs,11788
-ocf_data_sampler-0.0.46.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ocf_data_sampler-0.0.46.dist-info/top_level.txt,sha256=Faob6N6cFdPc5eUpCTYcXgCaNhi4XLLteUL5W5ayYmg,31
-ocf_data_sampler-0.0.46.dist-info/RECORD,,
+ocf_data_sampler-0.0.48.dist-info/LICENSE,sha256=F-Q3UFCR-BECSocV55BFDpn4YKxve9PKrm-lTt6o_Tg,1073
+ocf_data_sampler-0.0.48.dist-info/METADATA,sha256=Wl37iFa0xFXGRsHNEHLn7WYeXbWvbg8SGgLXcksExQA,11788
+ocf_data_sampler-0.0.48.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+ocf_data_sampler-0.0.48.dist-info/top_level.txt,sha256=Faob6N6cFdPc5eUpCTYcXgCaNhi4XLLteUL5W5ayYmg,31
+ocf_data_sampler-0.0.48.dist-info/RECORD,,