ocf-data-sampler 0.5.11__tar.gz → 0.6.2__tar.gz

{ocf_data_sampler-0.5.11 → ocf_data_sampler-0.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocf-data-sampler
-Version: 0.5.11
+Version: 0.6.2
 Author: James Fulton, Peter Dudfield
 Author-email: Open Climate Fix team <info@openclimatefix.org>
 License: MIT License
@@ -28,7 +28,7 @@ License: MIT License
 Project-URL: repository, https://github.com/openclimatefix/ocf-data-sampler
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
-Requires-Python: >=3.11
+Requires-Python: <3.14,>=3.11
 Description-Content-Type: text/markdown
 Requires-Dist: torch
 Requires-Dist: numpy
@@ -50,7 +50,7 @@ Requires-Dist: zarr>=3
 # ocf-data-sampler
  
 <!-- ALL-CONTRIBUTORS-BADGE:START - Do not remove or modify this section -->
-[![All Contributors](https://img.shields.io/badge/all_contributors-14-orange.svg?style=flat-square)](#contributors-)
+[![All Contributors](https://img.shields.io/badge/all_contributors-16-orange.svg?style=flat-square)](#contributors-)
 <!-- ALL-CONTRIBUTORS-BADGE:END -->
 
 [![tags badge](https://img.shields.io/github/v/tag/openclimatefix/ocf-data-sampler?include_prereleases&sort=semver&color=FFAC5F)](https://github.com/openclimatefix/ocf-data-sampler/tags)
@@ -137,6 +137,10 @@ Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/d
       <td align="center" valign="top" width="14.28%"><a href="https://drona-gyawali.github.io/"><img src="https://avatars.githubusercontent.com/u/170401554?v=4?s=100" width="100px;" alt="Dorna Raj Gyawali"/><br /><sub><b>Dorna Raj Gyawali</b></sub></a><br /><a href="https://github.com/openclimatefix/ocf-data-sampler/commits?author=drona-gyawali" title="Code">💻</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/adnanhashmi25"><img src="https://avatars.githubusercontent.com/u/55550094?v=4?s=100" width="100px;" alt="Adnan Hashmi"/><br /><sub><b>Adnan Hashmi</b></sub></a><br /><a href="https://github.com/openclimatefix/ocf-data-sampler/commits?author=adnanhashmi25" title="Code">💻</a></td>
     </tr>
+    <tr>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/utsav-pal"><img src="https://avatars.githubusercontent.com/u/159793156?v=4?s=100" width="100px;" alt="utsav-pal"/><br /><sub><b>utsav-pal</b></sub></a><br /><a href="https://github.com/openclimatefix/ocf-data-sampler/commits?author=utsav-pal" title="Code">💻</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/zaryab-ali"><img src="https://avatars.githubusercontent.com/u/85732412?v=4?s=100" width="100px;" alt="zaryab-ali"/><br /><sub><b>zaryab-ali</b></sub></a><br /><a href="https://github.com/openclimatefix/ocf-data-sampler/commits?author=zaryab-ali" title="Code">💻</a></td>
+    </tr>
   </tbody>
 </table>
 

{ocf_data_sampler-0.5.11 → ocf_data_sampler-0.6.2}/README.md

@@ -1,7 +1,7 @@
 # ocf-data-sampler
  
 <!-- ALL-CONTRIBUTORS-BADGE:START - Do not remove or modify this section -->
-[![All Contributors](https://img.shields.io/badge/all_contributors-14-orange.svg?style=flat-square)](#contributors-)
+[![All Contributors](https://img.shields.io/badge/all_contributors-16-orange.svg?style=flat-square)](#contributors-)
 <!-- ALL-CONTRIBUTORS-BADGE:END -->
 
 [![tags badge](https://img.shields.io/github/v/tag/openclimatefix/ocf-data-sampler?include_prereleases&sort=semver&color=FFAC5F)](https://github.com/openclimatefix/ocf-data-sampler/tags)
@@ -88,6 +88,10 @@ Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/d
       <td align="center" valign="top" width="14.28%"><a href="https://drona-gyawali.github.io/"><img src="https://avatars.githubusercontent.com/u/170401554?v=4?s=100" width="100px;" alt="Dorna Raj Gyawali"/><br /><sub><b>Dorna Raj Gyawali</b></sub></a><br /><a href="https://github.com/openclimatefix/ocf-data-sampler/commits?author=drona-gyawali" title="Code">💻</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/adnanhashmi25"><img src="https://avatars.githubusercontent.com/u/55550094?v=4?s=100" width="100px;" alt="Adnan Hashmi"/><br /><sub><b>Adnan Hashmi</b></sub></a><br /><a href="https://github.com/openclimatefix/ocf-data-sampler/commits?author=adnanhashmi25" title="Code">💻</a></td>
     </tr>
+    <tr>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/utsav-pal"><img src="https://avatars.githubusercontent.com/u/159793156?v=4?s=100" width="100px;" alt="utsav-pal"/><br /><sub><b>utsav-pal</b></sub></a><br /><a href="https://github.com/openclimatefix/ocf-data-sampler/commits?author=utsav-pal" title="Code">💻</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/zaryab-ali"><img src="https://avatars.githubusercontent.com/u/85732412?v=4?s=100" width="100px;" alt="zaryab-ali"/><br /><sub><b>zaryab-ali</b></sub></a><br /><a href="https://github.com/openclimatefix/ocf-data-sampler/commits?author=zaryab-ali" title="Code">💻</a></td>
+    </tr>
   </tbody>
 </table>
 

{ocf_data_sampler-0.5.11 → ocf_data_sampler-0.6.2}/ocf_data_sampler/config/model.py

@@ -7,7 +7,7 @@ Prefix with a protocol like s3:// to read from alternative filesystems.
 from collections.abc import Iterator
 from typing import Literal
 
-from pydantic import BaseModel, Field, RootModel, field_validator, model_validator
+from pydantic import BaseModel, ConfigDict, Field, RootModel, field_validator, model_validator
 from typing_extensions import override
 
 NWP_PROVIDERS = [
@@ -23,10 +23,7 @@ NWP_PROVIDERS = [
 class Base(BaseModel):
     """Pydantic Base model where no extras can be added."""
 
-    class Config:
-        """Config class."""
-
-        extra = "forbid"  # forbid use of extra kwargs
+    model_config = ConfigDict(extra="forbid")
 
 
 class General(Base):
@@ -90,12 +87,17 @@ class DropoutMixin(Base):
         "negative or zero.",
     )
 
-    dropout_fraction: float|list[float] = Field(
-        default=0,
+    dropout_fraction: float | list[float] = Field(
+        default=0.0,
         description="Either a float(Chance of dropout being applied to each sample) or a list of "
         "floats (probability that dropout of the corresponding timedelta is applied)",
     )
 
+    dropout_value: float = Field(
+        default=0.0,
+        description="The value to use for dropped out values. "
+        "Idea is to use -1, but to be backwards comptaible we've put the default as 0")
+
     @field_validator("dropout_timedeltas_minutes")
     def dropout_timedeltas_minutes_negative(cls, v: list[int]) -> list[int]:
         """Validate 'dropout_timedeltas_minutes'."""
@@ -106,31 +108,22 @@ class DropoutMixin(Base):
 
 
     @field_validator("dropout_fraction")
-    def dropout_fractions(cls, dropout_frac: float|list[float]) -> float|list[float]:
+    def dropout_fractions(cls, dropout_frac: float | list[float]) -> float | list[float]:
         """Validate 'dropout_frac'."""
-        from math import isclose
-        if isinstance(dropout_frac, float):
-            if not (dropout_frac <= 1):
-                raise ValueError("Input should be less than or equal to 1")
-            elif not (dropout_frac >= 0):
-                raise ValueError("Input should be greater than or equal to 0")
+        if isinstance(dropout_frac, float | int):
+            if not (0<= dropout_frac <= 1):
+                raise ValueError("Dropout fractions must be in range [0, 1]")
 
         elif isinstance(dropout_frac, list):
             if not dropout_frac:
                 raise ValueError("List cannot be empty")
 
-            if not all(isinstance(i, float) for i in dropout_frac):
-                raise ValueError("All elements in the list must be floats")
-
             if not all(0 <= i <= 1 for i in dropout_frac):
-                raise ValueError("Each float in the list must be between 0 and 1")
-
-            if not isclose(sum(dropout_frac), 1.0, rel_tol=1e-9):
-                raise ValueError("Sum of all floats in the list must be 1.0")
+                raise ValueError("All dropout fractions must be in range [0, 1]")
 
+            if not (0 <= sum(dropout_frac) <= 1):
+                raise ValueError("The sum of dropout fractions must be in range [0, 1]")
 
-        else:
-            raise TypeError("Must be either a float or a list of floats")
         return dropout_frac
 
 
@@ -172,23 +165,6 @@ class NormalisationConstantsMixin(Base):
     """Normalisation constants for multiple channels."""
     normalisation_constants: dict[str, NormalisationValues]
 
-    @property
-    def channel_means(self) -> dict[str, float]:
-        """Return the channel means."""
-        return {
-            channel: norm_values.mean
-            for channel, norm_values in self.normalisation_constants.items()
-        }
-
-
-    @property
-    def channel_stds(self) -> dict[str, float]:
-        """Return the channel standard deviations."""
-        return {
-            channel: norm_values.std
-            for channel, norm_values in self.normalisation_constants.items()
-        }
-
 
 class Satellite(TimeWindowMixin, DropoutMixin, SpatialWindowMixin, NormalisationConstantsMixin):
     """Satellite configuration model."""
@@ -363,9 +339,19 @@ class InputData(Base):
     site: Site | None = None
     solar_position: SolarPosition | None = None
 
+    @model_validator(mode="after")
+    def check_site_or_gsp(self) -> "InputData":
+        """Ensure that either `site` or `gsp` is provided in the input data."""
+        if self.site is None and self.gsp is None:
+            raise ValueError(
+                "You must provide either `site` or `gsp` in the `input_data`",
+            )
+
+        return self
+
 
 class Configuration(Base):
     """Configuration model for the dataset."""
 
     general: General = General()
-    input_data: InputData = InputData()
+    input_data: InputData = Field(default_factory=InputData)

{ocf_data_sampler-0.5.11 → ocf_data_sampler-0.6.2}/ocf_data_sampler/load/gsp.py

@@ -32,7 +32,7 @@ def open_gsp(
     boundaries_version: str = "20220314",
     public: bool = False,
 ) -> xr.DataArray:
-    """Open the GSP data and validates its data types.
+    """Open and eagerly load the GSP data and validates its data types.
 
     Args:
         zarr_path: Path to the GSP zarr data
@@ -93,4 +93,6 @@ def open_gsp(
             dtype = gsp_da.coords[coord].dtype
             raise TypeError(f"{coord} should be {expected_dtype.__name__}, not {dtype}")
 
-    return gsp_da
+    # Below we load the data eagerly into memory - this makes the dataset faster to sample from, but
+    # at the cost of a little extra memory usage
+    return gsp_da.compute()

{ocf_data_sampler-0.5.11 → ocf_data_sampler-0.6.2}/ocf_data_sampler/load/nwp/nwp.py

@@ -29,7 +29,6 @@ def _validate_nwp_data(data_array: xr.DataArray, provider: str) -> None:
     common_expected_dtypes = {
         "init_time_utc": np.datetime64,
         "step": np.timedelta64,
-        "channel": (np.str_, np.object_),
     }
 
     geographic_spatial_dtypes = {

{ocf_data_sampler-0.5.11 → ocf_data_sampler-0.6.2}/ocf_data_sampler/load/nwp/providers/utils.py

@@ -75,7 +75,7 @@ def _tensostore_open_zarr_paths(zarr_path: str | list[str], time_dim: str) -> xr
         zarr_path = sorted(glob(zarr_path))
 
     if isinstance(zarr_path, list | tuple):
-        ds = open_zarrs(zarr_path, concat_dim=time_dim).sortby(time_dim)
+        ds = open_zarrs(zarr_path, concat_dim=time_dim, data_source="nwp").sortby(time_dim)
     else:
         ds = open_zarr(zarr_path)
     return ds

{ocf_data_sampler-0.5.11 → ocf_data_sampler-0.6.2}/ocf_data_sampler/load/open_xarray_tensorstore.py

@@ -14,6 +14,7 @@ References:
     [2] https://www.apache.org/licenses/LICENSE-2.0
 """
 
+import logging
 import os.path
 import re
 
@@ -26,6 +27,7 @@ from xarray_tensorstore import (
     _TensorStoreAdapter,
 )
 
+logger = logging.getLogger(__name__)
 
 def _zarr_spec_from_path(path: str, zarr_format: int) -> ...:
     if re.match(r"\w+\://", path):  # path is a URI
@@ -127,6 +129,7 @@ def open_zarrs(
     concat_dim: str,
     context: ts.Context | None = None,
     mask_and_scale: bool = True,
+    data_source: str = "unknown",
 ) -> xr.Dataset:
     """Open multiple zarrs with TensorStore.
 
@@ -135,6 +138,7 @@ def open_zarrs(
         concat_dim: Dimension along which to concatenate the data variables.
         context: TensorStore context.
         mask_and_scale: Whether to mask and scale the data.
+        data_source: Which data source is being opened. Used for warning context.
 
     Returns:
         Concatenated Dataset with all data variables opened via TensorStore.
@@ -143,13 +147,28 @@ def open_zarrs(
         context = ts.Context()
 
     ds_list = [xr.open_zarr(p, mask_and_scale=mask_and_scale, decode_timedelta=True) for p in paths]
-    ds = xr.concat(
-        ds_list,
-        dim=concat_dim,
-        data_vars="minimal",
-        compat="equals",
-        combine_attrs="drop_conflicts",
-    )
+    try:
+        ds = xr.concat(
+            ds_list,
+            dim=concat_dim,
+            data_vars="minimal",
+            compat="equals",
+            combine_attrs="drop_conflicts",
+            join="exact",
+        )
+    except ValueError:
+        logger.warning(f"Coordinate mismatch found in {data_source} input data. "
+                       f"The coordinates will be overwritten! "
+                       f"This might be fine for satellite data. "
+                       f"Proceed with caution.")
+        ds = xr.concat(
+            ds_list,
+            dim=concat_dim,
+            data_vars="minimal",
+            compat="equals",
+            combine_attrs="drop_conflicts",
+            join="override",
+        )
 
     if mask_and_scale:
         _raise_if_mask_and_scale_used_for_data_vars(ds)

{ocf_data_sampler-0.5.11 → ocf_data_sampler-0.6.2}/ocf_data_sampler/load/satellite.py

@@ -19,7 +19,7 @@ def open_sat_data(zarr_path: str | list[str]) -> xr.DataArray:
     """
     # Open the data
     if isinstance(zarr_path, list | tuple):
-        ds = open_zarrs(zarr_path, concat_dim="time")
+        ds = open_zarrs(zarr_path, concat_dim="time", data_source="satellite")
     else:
         ds = open_zarr(zarr_path)
 

ocf_data_sampler-0.6.2/ocf_data_sampler/load/site.py

@@ -0,0 +1,73 @@
+"""Funcitons for loading site data."""
+
+import numpy as np
+import pandas as pd
+import xarray as xr
+
+
+def open_site(generation_file_path: str, metadata_file_path: str) -> xr.DataArray:
+    """Open a site's generation data and metadata.
+
+    Args:
+        generation_file_path: Path to the site generation netcdf data
+        metadata_file_path: Path to the site csv metadata
+
+    Returns:
+        xr.DataArray: The opened site generation data
+    """
+    generation_ds = xr.open_dataset(generation_file_path)
+    metadata_df = pd.read_csv(metadata_file_path, index_col="site_id")
+
+    if not metadata_df.index.is_unique:
+        raise ValueError("site_id is not unique in metadata")
+
+    # Ensure metadata aligns with the site_id dimension in generation_ds
+    metadata_df = metadata_df.reindex(generation_ds.site_id.values)
+
+    # Assign coordinates to the Dataset using the aligned metadata
+    # Check if variable capacity was passed with the generation data
+    # If not assign static capacity from metadata
+    if hasattr(generation_ds,"capacity_kwp"):
+        generation_ds = generation_ds.assign_coords(
+            latitude=(metadata_df.latitude.to_xarray()),
+            longitude=(metadata_df.longitude.to_xarray()),
+            capacity_kwp=generation_ds.capacity_kwp,
+        )
+    else:
+        generation_ds = generation_ds.assign_coords(
+            latitude=(metadata_df.latitude.to_xarray()),
+            longitude=(metadata_df.longitude.to_xarray()),
+            capacity_kwp=(metadata_df.capacity_kwp.to_xarray()),
+        )
+
+    # Sanity checks, to prevent inf or negative values
+    # Note NaNs are allowed in generation_kw as can have non overlapping time periods for sites
+    if np.isinf(generation_ds.generation_kw.values).all():
+        raise ValueError("generation_kw contains infinite (+/- inf) values")
+    if not (generation_ds.capacity_kwp.values > 0).all():
+        raise ValueError("capacity_kwp contains non-positive values")
+
+    site_da = generation_ds.generation_kw
+
+    # Validate data types directly in loading function
+    if not np.issubdtype(site_da.dtype, np.floating):
+        raise TypeError(f"Generation data should be float, not {site_da.dtype}")
+
+
+    coord_dtypes = {
+    "time_utc": (np.datetime64,),
+    "site_id": (np.integer,),
+    "capacity_kwp": (np.integer, np.floating),
+    "latitude": (np.floating,),
+    "longitude": (np.floating,),
+}
+    for coord, expected_dtypes in coord_dtypes.items():
+        if not any(np.issubdtype(site_da.coords[coord].dtype, dt) for dt in expected_dtypes):
+            dtype = site_da.coords[coord].dtype
+            allowed = ", ".join(dt.__name__ for dt in expected_dtypes)
+            raise TypeError(f"{coord} should be one of ({allowed}), not {dtype}")
+
+    # Load the data eagerly into memory by calling compute
+    # this makes the dataset faster to sample from, but
+    # at the cost of a little extra memory usage
+    return site_da.compute()

{ocf_data_sampler-0.5.11 → ocf_data_sampler-0.6.2}/ocf_data_sampler/numpy_sample/nwp.py

@@ -28,7 +28,7 @@ def convert_nwp_to_numpy_sample(da: xr.DataArray, t0_idx: int | None = None) ->
         NWPSampleKey.channel_names: da.channel.values,
         NWPSampleKey.init_time_utc: da.init_time_utc.values.astype(float),
         NWPSampleKey.step: (da.step.values / 3600).astype(int),
-        NWPSampleKey.target_time_utc: da.target_time_utc.values.astype(float),
+        NWPSampleKey.target_time_utc: (da.init_time_utc.values + da.step.values).astype(float),
     }
 
     if t0_idx is not None:

ocf_data_sampler-0.6.2/ocf_data_sampler/select/diff_channels.py

@@ -0,0 +1,25 @@
+"""Takes the diff along the step axis for a given set of channels."""
+
+import numpy as np
+import xarray as xr
+
+
+def diff_channels(da: xr.DataArray, accum_channels: list[str]) -> xr.DataArray:
+    """Perform in-place diff of the given channels of the DataArray in the steps dimension.
+
+    Args:
+        da: The DataArray to slice from
+        accum_channels: Channels which are accumulated and need to be differenced
+    """
+    if da.dims[:2] != ("step", "channel"):
+        raise ValueError("This function assumes the first two dimensions are step then channel")
+
+    all_channels = da.channel.values
+    accum_channel_inds = [i for i, c in enumerate(all_channels) if c in accum_channels]
+
+    # Make a copy of the values to avoid changing the underlying numpy array
+    vals = da.values.copy()
+    vals[:-1, accum_channel_inds] = np.diff(vals[:, accum_channel_inds], axis=0)
+    da.values = vals
+
+    return da.isel(step=slice(0, -1))

ocf_data_sampler-0.6.2/ocf_data_sampler/select/dropout.py

@@ -0,0 +1,59 @@
+"""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 apply_history_dropout(
+    t0: pd.Timestamp,
+    dropout_timedeltas: list[pd.Timedelta],
+    dropout_frac: float | list[float],
+    da: xr.DataArray,
+) -> xr.DataArray:
+    """Apply randomly sampled dropout to the historical part of some sequence data.
+
+    Dropped out data is replaced with NaNs
+
+    Args:
+        t0: The forecast init-time.
+        dropout_timedeltas: List of timedeltas relative to t0 to pick from
+        dropout_frac: The probabilit(ies) that each dropout timedelta will be applied. This should
+            be between 0 and 1 inclusive.
+        da: Xarray DataArray with 'time_utc' coordinate
+    """
+    if len(dropout_timedeltas)==0:
+        return da
+
+    if isinstance(dropout_frac, float | int):
+
+        if not (0<=dropout_frac<=1):
+            raise ValueError("`dropout_frac` must be in range [0, 1]")
+
+        # Create list with equal chance for all dropout timedeltas
+        n = len(dropout_timedeltas)
+        dropout_frac = [dropout_frac/n for _ in range(n)]
+    else:
+        if not 0<=sum(dropout_frac)<=1:
+            raise ValueError("The sum of `dropout_frac` must be in range [0, 1]")
+        if len(dropout_timedeltas)!=len(dropout_frac):
+            raise ValueError("`dropout_timedeltas` and `dropout_frac` must have the same length")
+
+        dropout_frac = [*dropout_frac] # Make copy of the list so we can append to it
+
+    dropout_timedeltas = [*dropout_timedeltas] # Make copy of the list so we can append to it
+
+    # Add chance of no dropout
+    dropout_frac.append(1-sum(dropout_frac))
+    dropout_timedeltas.append(None)
+
+    timedelta_choice = np.random.choice(dropout_timedeltas, p=dropout_frac)
+
+    if timedelta_choice is None:
+        return da
+    else:
+        return da.where((da.time_utc <= timedelta_choice + t0) | (da.time_utc> t0))

{ocf_data_sampler-0.5.11 → ocf_data_sampler-0.6.2}/ocf_data_sampler/select/location.py

@@ -37,9 +37,9 @@ class Location:
             return self._projections[coord_system]
         else:
             raise ValueError(
-                "Requested the coodinate in {coord_system}. This has not yet been added. "
+                f"Requested the coodinate in {coord_system}. This has not yet been added. "
                 "The current available coordinate systems are "
-                f"{list(self.self._projections.keys())}",
+                f"{list(self._projections.keys())}",
             )
 
     def add_coord_system(self, x: float, y: float, coord_system: int) -> None:

ocf_data_sampler-0.6.2/ocf_data_sampler/select/select_spatial_slice.py

@@ -0,0 +1,110 @@
+"""Select spatial slices."""
+
+import numpy as np
+import xarray as xr
+
+from ocf_data_sampler.select.geospatial import find_coord_system
+from ocf_data_sampler.select.location import Location
+
+
+def _get_pixel_index_location(da: xr.DataArray, location: Location) -> tuple[int, int]:
+    """Find pixel index location closest to given Location.
+
+    Args:
+        da: The xarray DataArray.
+        location: The Location object representing the point of interest.
+
+    Returns:
+        The pixel indices.
+
+    Raises:
+        ValueError: If the location is outside the bounds of the DataArray.
+    """
+    target_coords, x_dim, y_dim = find_coord_system(da)
+
+    x, y = location.in_coord_system(target_coords)
+
+    x_vals = da[x_dim].values
+    y_vals = da[y_dim].values
+
+    # Check that requested point lies within the data
+    if not (x_vals[0] < x < x_vals[-1]):
+        raise ValueError(
+            f"{x} is not in the interval {x_vals[0]}: {x_vals[-1]}",
+        )
+    if not (y_vals[0] < y < y_vals[-1]):
+        raise ValueError(
+            f"{y} is not in the interval {y_vals[0]}: {y_vals[-1]}",
+        )
+
+    closest_x = np.argmin(np.abs(x_vals - x))
+    closest_y = np.argmin(np.abs(y_vals - y))
+
+    return closest_x, closest_y
+
+
+def select_spatial_slice_pixels(
+    da: xr.DataArray,
+    location: Location,
+    width_pixels: int,
+    height_pixels: int,
+) -> xr.DataArray:
+    """Select spatial slice based off pixels from location point of interest.
+
+    Args:
+        da: xarray DataArray to slice from
+        location: Location of interest that will be the center of the returned slice
+        height_pixels: Height of the slice in pixels
+        width_pixels: Width of the slice in pixels
+
+    Returns:
+        The selected DataArray slice.
+
+    Raises:
+        ValueError: If the dimensions are not even or the slice is not allowed
+                    when padding is required.
+    """
+    if (width_pixels % 2) != 0:
+        raise ValueError("Width must be an even number")
+    if (height_pixels % 2) != 0:
+        raise ValueError("Height must be an even number")
+
+    _, x_dim, y_dim = find_coord_system(da)
+    center_idx_x, center_idx_y = _get_pixel_index_location(da, location)
+
+    half_width = width_pixels // 2
+    half_height = height_pixels // 2
+
+    left_idx = int(center_idx_x - half_width)
+    right_idx = int(center_idx_x + half_width)
+    bottom_idx = int(center_idx_y - half_height)
+    top_idx = int(center_idx_y + half_height)
+
+    data_width_pixels = len(da[x_dim])
+    data_height_pixels = len(da[y_dim])
+
+    # Padding checks
+    slice_unavailable = (
+        left_idx < 0
+        or right_idx > data_width_pixels
+        or bottom_idx < 0
+        or top_idx > data_height_pixels
+    )
+
+    if slice_unavailable:
+        issues = []
+        if left_idx < 0:
+            issues.append(f"left_idx ({left_idx}) < 0")
+        if right_idx > data_width_pixels:
+            issues.append(f"right_idx ({right_idx}) > data_width_pixels ({data_width_pixels})")
+        if bottom_idx < 0:
+            issues.append(f"bottom_idx ({bottom_idx}) < 0")
+        if top_idx > data_height_pixels:
+            issues.append(f"top_idx ({top_idx}) > data_height_pixels ({data_height_pixels})")
+        issue_details = "\n - ".join(issues)
+        raise ValueError(f"Window for location {location} not available: \n - {issue_details}")
+
+    # Standard selection - without padding
+    da = da.isel({x_dim: slice(left_idx, right_idx), y_dim: slice(bottom_idx, top_idx)})
+
+    return da