ocf-data-sampler 0.0.25__tar.gz → 0.0.26__tar.gz

{ocf_data_sampler-0.0.25/ocf_data_sampler.egg-info → ocf_data_sampler-0.0.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ocf_data_sampler
-Version: 0.0.25
+Version: 0.0.26
 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 → ocf_data_sampler-0.0.26}/ocf_data_sampler/config/model.py

@@ -14,7 +14,7 @@ import logging
 from typing import Dict, List, Optional
 from typing_extensions import Self
 
-from pydantic import BaseModel, Field, RootModel, field_validator, ValidationInfo, model_validator
+from pydantic import BaseModel, Field, RootModel, field_validator, model_validator
 from ocf_data_sampler.constants import NWP_PROVIDERS
 
 logger = logging.getLogger(__name__)
@@ -34,27 +34,12 @@ class Base(BaseModel):
 class General(Base):
     """General pydantic model"""
 
-    name: str = Field("example", description="The name of this configuration file.")
+    name: str = Field("example", description="The name of this configuration file")
     description: str = Field(
         "example configuration", description="Description of this configuration file"
     )
 
 
-class DataSourceMixin(Base):
-    """Mixin class, to add forecast and history minutes"""
-
-    forecast_minutes: int = Field(
-        ...,
-        ge=0,
-        description="how many minutes to forecast in the future. ",
-    )
-    history_minutes: int = Field(
-        ...,
-        ge=0,
-        description="how many historic minutes to use. ",
-    )
-
-
 # noinspection PyMethodParameters
 class DropoutMixin(Base):
     """Mixin class, to add dropout minutes"""
@@ -65,7 +50,12 @@ class DropoutMixin(Base):
         "negative or zero.",
     )
 
-    dropout_fraction: float = Field(0, description="Chance of dropout being applied to each sample")
+    dropout_fraction: float = Field(
+        default=0,
+        description="Chance of dropout being applied to each sample",
+        ge=0,
+        le=1,
+    )
 
     @field_validator("dropout_timedeltas_minutes")
     def dropout_timedeltas_minutes_negative(cls, v: List[int]) -> List[int]:
@@ -75,12 +65,6 @@ class DropoutMixin(Base):
                 assert m <= 0, "Dropout timedeltas must be negative"
         return v
 
-    @field_validator("dropout_fraction")
-    def dropout_fraction_valid(cls, v: float) -> float:
-        """Validate 'dropout_fraction'"""
-        assert 0 <= v <= 1, "Dropout fraction must be between 0 and 1"
-        return v
-
     @model_validator(mode="after")
     def dropout_instructions_consistent(self) -> Self:
         if self.dropout_fraction == 0:
@@ -93,69 +77,67 @@ class DropoutMixin(Base):
 
 
 # noinspection PyMethodParameters
-class TimeResolutionMixin(Base):
+class TimeWindowMixin(Base):
     """Time resolution mix in"""
 
     time_resolution_minutes: int = Field(
         ...,
+        gt=0,
         description="The temporal resolution of the data in minutes",
     )
 
-
-class Site(DataSourceMixin, TimeResolutionMixin, DropoutMixin):
-    """Site configuration model"""
-
-    file_path: str = Field(
+    forecast_minutes: int = Field(
         ...,
-        description="The NetCDF files holding the power timeseries.",
+        ge=0,
+        description="how many minutes to forecast in the future",
     )
-    metadata_file_path: str = Field(
+    history_minutes: int = Field(
         ...,
-        description="The CSV files describing power system",
+        ge=0,
+        description="how many historic minutes to use",
     )
 
     @field_validator("forecast_minutes")
-    def forecast_minutes_divide_by_time_resolution(cls, v: int, info: ValidationInfo) -> int:
-        """Check forecast length requested will give stable number of timesteps"""
-        if v % info.data["time_resolution_minutes"] != 0:
+    def forecast_minutes_divide_by_time_resolution(cls, v, values) -> int:
+        if v % values.data["time_resolution_minutes"] != 0:
             message = "Forecast duration must be divisible by time resolution"
             logger.error(message)
             raise Exception(message)
         return v
 
     @field_validator("history_minutes")
-    def history_minutes_divide_by_time_resolution(cls, v: int, info: ValidationInfo) -> int:
-        """Check history length requested will give stable number of timesteps"""
-        if v % info.data["time_resolution_minutes"] != 0:
+    def history_minutes_divide_by_time_resolution(cls, v, values) -> int:
+        if v % values.data["time_resolution_minutes"] != 0:
             message = "History duration must be divisible by time resolution"
             logger.error(message)
             raise Exception(message)
         return v
 
-    # TODO validate the netcdf for sites
-    # TODO validate the csv for metadata
 
-class Satellite(DataSourceMixin, TimeResolutionMixin, DropoutMixin):
-    """Satellite configuration model"""
+class SpatialWindowMixin(Base):
+    """Mixin class, to add path and image size"""
 
-    # Todo: remove 'satellite' from names
-    satellite_zarr_path: str | tuple[str] | list[str] = Field(
+    image_size_pixels_height: int = Field(
         ...,
-        description="The path or list of paths which hold the satellite zarr",
+        description="The number of pixels of the height of the region of interest",
     )
-    satellite_channels: list[str] = Field(
-        ..., description="the satellite channels that are used"
-    )
-    satellite_image_size_pixels_height: int = Field(
+
+    image_size_pixels_width: int = Field(
         ...,
-        description="The number of pixels of the height of the region of interest"
-        " for non-HRV satellite channels.",
+        description="The number of pixels of the width of the region of interest",
     )
 
-    satellite_image_size_pixels_width: int = Field(
+
+class Satellite(TimeWindowMixin, DropoutMixin, SpatialWindowMixin):
+    """Satellite configuration model"""
+    
+    zarr_path: str | tuple[str] | list[str] = Field(
         ...,
-        description="The number of pixels of the width of the region "
-        "of interest for non-HRV satellite channels.",
+        description="The path or list of paths which hold the data zarr",
+    )
+
+    channels: list[str] = Field(
+        ..., description="the satellite channels that are used"
     )
 
     live_delay_minutes: int = Field(
@@ -164,21 +146,21 @@ class Satellite(DataSourceMixin, TimeResolutionMixin, DropoutMixin):
 
 
 # noinspection PyMethodParameters
-class NWP(DataSourceMixin, TimeResolutionMixin, DropoutMixin):
+class NWP(TimeWindowMixin, DropoutMixin, SpatialWindowMixin):
     """NWP configuration model"""
-
-    nwp_zarr_path: str | tuple[str] | list[str] = Field(
+    
+    zarr_path: str | tuple[str] | list[str] = Field(
         ...,
-        description="The path which holds the NWP zarr",
+        description="The path or list of paths which hold the data zarr",
     )
-    nwp_channels: list[str] = Field(
+    
+    channels: list[str] = Field(
         ..., description="the channels used in the nwp data"
     )
-    nwp_accum_channels: list[str] = Field([], description="the nwp channels which need to be diffed")
-    nwp_image_size_pixels_height: int = Field(..., description="The size of NWP spacial crop in pixels")
-    nwp_image_size_pixels_width: int = Field(..., description="The size of NWP spacial crop in pixels")
 
-    nwp_provider: str = Field(..., description="The provider of the NWP data")
+    provider: str = Field(..., description="The provider of the NWP data")
+
+    accum_channels: list[str] = Field([], description="the nwp channels which need to be diffed")
 
     max_staleness_minutes: Optional[int] = Field(
         None,
@@ -187,33 +169,15 @@ class NWP(DataSourceMixin, TimeResolutionMixin, DropoutMixin):
         " the maximum forecast horizon of the NWP and the requested forecast length.",
     )
 
-
-    @field_validator("nwp_provider")
-    def validate_nwp_provider(cls, v: str) -> str:
-        """Validate 'nwp_provider'"""
+    @field_validator("provider")
+    def validate_provider(cls, v: str) -> str:
+        """Validate 'provider'"""
         if v.lower() not in NWP_PROVIDERS:
             message = f"NWP provider {v} is not in {NWP_PROVIDERS}"
             logger.warning(message)
             raise Exception(message)
         return v
 
-    # Todo: put into time mixin when moving intervals there
-    @field_validator("forecast_minutes")
-    def forecast_minutes_divide_by_time_resolution(cls, v: int, info: ValidationInfo) -> int:
-        if v % info.data["time_resolution_minutes"] != 0:
-            message = "Forecast duration must be divisible by time resolution"
-            logger.error(message)
-            raise Exception(message)
-        return v
-
-    @field_validator("history_minutes")
-    def history_minutes_divide_by_time_resolution(cls, v: int, info: ValidationInfo) -> int:
-        if v % info.data["time_resolution_minutes"] != 0:
-            message = "History duration must be divisible by time resolution"
-            logger.error(message)
-            raise Exception(message)
-        return v
-
 
 class MultiNWP(RootModel):
     """Configuration for multiple NWPs"""
@@ -241,27 +205,26 @@ class MultiNWP(RootModel):
         return self.root.items()
 
 
-# noinspection PyMethodParameters
-class GSP(DataSourceMixin, TimeResolutionMixin, DropoutMixin):
+class GSP(TimeWindowMixin, DropoutMixin):
     """GSP configuration model"""
 
-    gsp_zarr_path: str = Field(..., description="The path which holds the GSP zarr")
+    zarr_path: str = Field(..., description="The path which holds the GSP zarr")
 
-    @field_validator("forecast_minutes")
-    def forecast_minutes_divide_by_time_resolution(cls, v: int, info: ValidationInfo) -> int:
-        if v % info.data["time_resolution_minutes"] != 0:
-            message = "Forecast duration must be divisible by time resolution"
-            logger.error(message)
-            raise Exception(message)
-        return v
 
-    @field_validator("history_minutes")
-    def history_minutes_divide_by_time_resolution(cls, v: int, info: ValidationInfo) -> int:
-        if v % info.data["time_resolution_minutes"] != 0:
-            message = "History duration must be divisible by time resolution"
-            logger.error(message)
-            raise Exception(message)
-        return v
+class Site(TimeWindowMixin, DropoutMixin):
+    """Site configuration model"""
+
+    file_path: str = Field(
+        ...,
+        description="The NetCDF files holding the power timeseries.",
+    )
+    metadata_file_path: str = Field(
+        ...,
+        description="The CSV files describing power system",
+    )
+
+    # TODO validate the netcdf for sites
+    # TODO validate the csv for metadata
 
 
 # noinspection PyPep8Naming
@@ -280,4 +243,4 @@ class Configuration(Base):
     """Configuration model for the dataset"""
 
     general: General = General()
-    input_data: InputData = InputData()
+    input_data: InputData = InputData()

{ocf_data_sampler-0.0.25 → ocf_data_sampler-0.0.26}/ocf_data_sampler/load/load_dataset.py

@@ -20,8 +20,8 @@ def get_dataset_dict(config: Configuration) -> dict[str, dict[xr.DataArray]]:
     datasets_dict = {}
 
     # Load GSP data unless the path is None
-    if in_config.gsp and in_config.gsp.gsp_zarr_path:
-        da_gsp = open_gsp(zarr_path=in_config.gsp.gsp_zarr_path).compute()
+    if in_config.gsp and in_config.gsp.zarr_path:
+        da_gsp = open_gsp(zarr_path=in_config.gsp.zarr_path).compute()
 
         # Remove national GSP
         datasets_dict["gsp"] = da_gsp.sel(gsp_id=slice(1, None))
@@ -32,9 +32,9 @@ def get_dataset_dict(config: Configuration) -> dict[str, dict[xr.DataArray]]:
         datasets_dict["nwp"] = {}
         for nwp_source, nwp_config in in_config.nwp.items():
 
-            da_nwp = open_nwp(nwp_config.nwp_zarr_path, provider=nwp_config.nwp_provider)
+            da_nwp = open_nwp(nwp_config.zarr_path, provider=nwp_config.provider)
 
-            da_nwp = da_nwp.sel(channel=list(nwp_config.nwp_channels))
+            da_nwp = da_nwp.sel(channel=list(nwp_config.channels))
 
             datasets_dict["nwp"][nwp_source] = da_nwp
 
@@ -42,9 +42,9 @@ def get_dataset_dict(config: Configuration) -> dict[str, dict[xr.DataArray]]:
     if in_config.satellite:
         sat_config = config.input_data.satellite
 
-        da_sat = open_sat_data(sat_config.satellite_zarr_path)
+        da_sat = open_sat_data(sat_config.zarr_path)
 
-        da_sat = da_sat.sel(channel=list(sat_config.satellite_channels))
+        da_sat = da_sat.sel(channel=list(sat_config.channels))
 
         datasets_dict["sat"] = da_sat
 

{ocf_data_sampler-0.0.25 → ocf_data_sampler-0.0.26}/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-0.0.25 → ocf_data_sampler-0.0.26}/ocf_data_sampler/select/time_slice_for_dataset.py

@@ -38,7 +38,7 @@ def slice_datasets_by_time(
                 forecast_duration=minutes(nwp_config.forecast_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:

{ocf_data_sampler-0.0.25 → ocf_data_sampler-0.0.26}/ocf_data_sampler/torch_datasets/process_and_combine.py

@@ -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)

{ocf_data_sampler-0.0.25 → ocf_data_sampler-0.0.26}/ocf_data_sampler/torch_datasets/valid_time_periods.py

@@ -38,7 +38,7 @@ 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)

{ocf_data_sampler-0.0.25 → ocf_data_sampler-0.0.26/ocf_data_sampler.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ocf_data_sampler
-Version: 0.0.25
+Version: 0.0.26
 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 → ocf_data_sampler-0.0.26}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ocf_data_sampler"
-version = "0.0.25"
+version = "0.0.26"
 license = { file = "LICENSE" }
 readme = "README.md"
 description = "Sample from weather data for renewable energy prediction"

{ocf_data_sampler-0.0.25 → ocf_data_sampler-0.0.26}/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
     """
@@ -99,10 +99,11 @@ 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 +120,7 @@ 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 +129,12 @@ 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())
 
 

{ocf_data_sampler-0.0.25 → ocf_data_sampler-0.0.26}/tests/torch_datasets/test_pvnet_uk_regional.py

@@ -11,9 +11,9 @@ def pvnet_config_filename(tmp_path, config_filename, nwp_ukv_zarr_path, uk_gsp_z
 
     # adjust config to point to the zarr file
     config = load_yaml_configuration(config_filename)
-    config.input_data.nwp['ukv'].nwp_zarr_path = nwp_ukv_zarr_path
-    config.input_data.satellite.satellite_zarr_path = sat_zarr_path
-    config.input_data.gsp.gsp_zarr_path = uk_gsp_zarr_path
+    config.input_data.nwp['ukv'].zarr_path = nwp_ukv_zarr_path
+    config.input_data.satellite.zarr_path = sat_zarr_path
+    config.input_data.gsp.zarr_path = uk_gsp_zarr_path
 
     filename = f"{tmp_path}/configuration.yaml"
     save_yaml_configuration(config, filename)
@@ -60,7 +60,7 @@ def test_pvnet_no_gsp(pvnet_config_filename):
     # load config
     config = load_yaml_configuration(pvnet_config_filename)
     # remove gsp
-    config.input_data.gsp.gsp_zarr_path = ''
+    config.input_data.gsp.zarr_path = ''
 
     # save temp config file
     with tempfile.NamedTemporaryFile() as temp_config_file:

{ocf_data_sampler-0.0.25 → ocf_data_sampler-0.0.26}/tests/torch_datasets/test_site.py

@@ -13,8 +13,8 @@ def site_config_filename(tmp_path, config_filename, nwp_ukv_zarr_path, sat_zarr_
 
     # adjust config to point to the zarr file
     config = load_yaml_configuration(config_filename)
-    config.input_data.nwp["ukv"].nwp_zarr_path = nwp_ukv_zarr_path
-    config.input_data.satellite.satellite_zarr_path = sat_zarr_path
+    config.input_data.nwp["ukv"].zarr_path = nwp_ukv_zarr_path
+    config.input_data.satellite.zarr_path = sat_zarr_path
     config.input_data.site = data_sites
     config.input_data.gsp = None