ocf-data-sampler 0.0.1__py3-none-any.whl

ocf_data_sampler-0.0.1.dist-info/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Open Climate Fix
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

ocf_data_sampler-0.0.1.dist-info/METADATA

@@ -0,0 +1,20 @@
+Metadata-Version: 2.1
+Name: ocf_data_sampler
+Version: 0.0.1
+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
+License: MIT
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: xarray
+Requires-Dist: zarr
+Requires-Dist: dask
+Requires-Dist: ocf-blosc2
+Requires-Dist: ocf-datapipes ==3.3.39
+Requires-Dist: pvlib
+
+# OCF Data Sampler
+A repo for sampling from weather data for renewable energy prediction

ocf_data_sampler-0.0.1.dist-info/RECORD

@@ -0,0 +1,7 @@
+tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tests/conftest.py,sha256=OcArgF60paroZQqoP7xExRBF34nEyMuXd7dS7hD6p3w,5393
+ocf_data_sampler-0.0.1.dist-info/LICENSE,sha256=F-Q3UFCR-BECSocV55BFDpn4YKxve9PKrm-lTt6o_Tg,1073
+ocf_data_sampler-0.0.1.dist-info/METADATA,sha256=u1Nhi9GaANW3jMxG1ZBj1oXEkCmTephgJPObqgs35R0,587
+ocf_data_sampler-0.0.1.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+ocf_data_sampler-0.0.1.dist-info/top_level.txt,sha256=EdW7283x-lr_cbuivW8Ij7ANAP-ZJ9sLtILQseEPxXg,6
+ocf_data_sampler-0.0.1.dist-info/RECORD,,

ocf_data_sampler-0.0.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (72.2.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

ocf_data_sampler-0.0.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+tests

tests/conftest.py

@@ -0,0 +1,202 @@
+import os
+
+import numpy as np
+import pandas as pd
+import pytest
+import xarray as xr
+import tempfile
+
+
+
+@pytest.fixture(scope="session")
+def config_filename():
+    return f"{os.path.dirname(os.path.abspath(__file__))}/test_data/pvnet_test_config.yaml"
+
+
+@pytest.fixture(scope="session")
+def sat_zarr_path():
+
+    # Load dataset which only contains coordinates, but no data
+    ds = xr.open_zarr(
+        f"{os.path.dirname(os.path.abspath(__file__))}/test_data/non_hrv_shell.zarr.zip"
+    ).compute()
+
+    # Add time coord
+    ds = ds.assign_coords(time=pd.date_range("2023-01-01 00:00", "2023-01-02 23:55", freq="5min"))
+
+    # Add data to dataset
+    ds["data"] = xr.DataArray(
+        np.zeros([len(ds[c]) for c in ds.coords], dtype=np.float32),
+        coords=ds.coords,
+    )
+
+    # Transpose to variables, time, y, x (just in case)
+    ds = ds.transpose("variable", "time", "y_geostationary", "x_geostationary")
+
+    # add 100,000 to x_geostationary, this to make sure the fix index is within the satellite image
+    ds["x_geostationary"] = ds["x_geostationary"] - 200_000
+
+    # Add some NaNs
+    ds["data"].values[:, :, 0, 0] = np.nan
+
+    # make sure channel values are strings
+    ds["variable"] = ds["variable"].astype(str)
+
+    # add data attrs area
+    ds["data"].attrs["area"] = (
+        """msg_seviri_rss_3km:
+        description: MSG SEVIRI Rapid Scanning Service area definition with 3 km resolution
+        projection:
+            proj: geos
+            lon_0: 9.5
+            h: 35785831
+            x_0: 0
+            y_0: 0
+            a: 6378169
+            rf: 295.488065897014
+            no_defs: null
+            type: crs
+        shape:
+            height: 298
+            width: 615
+        area_extent:
+            lower_left_xy: [28503.830075263977, 5090183.970808983]
+            upper_right_xy: [-1816744.1169023514, 4196063.827395439]
+            units: m
+        """
+    )
+
+    # Specifiy chunking
+    ds = ds.chunk({"time": 10, "variable": -1, "y_geostationary": -1, "x_geostationary": -1})
+
+    # Save temporarily as a zarr
+    with tempfile.TemporaryDirectory() as tmpdir:
+        zarr_path = f"{tmpdir}/test_sat.zarr"
+        ds.to_zarr(zarr_path)
+
+        yield zarr_path
+
+
+@pytest.fixture(scope="session")
+def ds_nwp_ukv():
+    init_times = pd.date_range(start="2023-01-01 00:00", freq="180min", periods=24 * 7)
+    steps = pd.timedelta_range("0h", "10h", freq="1h")
+
+    x = np.linspace(-239_000, 857_000, 50)
+    y = np.linspace(-183_000, 1225_000, 100)
+    variables = ["si10", "dswrf", "t", "prate"]
+
+    coords = (
+        ("init_time", init_times),
+        ("variable", variables),
+        ("step", steps),
+        ("x", x),
+        ("y", y),
+    )
+
+    nwp_array_shape = tuple(len(coord_values) for _, coord_values in coords)
+
+    nwp_data = xr.DataArray(
+        np.random.uniform(0, 200, size=nwp_array_shape).astype(np.float32),
+        coords=coords,
+    )
+    return nwp_data.to_dataset(name="UKV")
+
+
+@pytest.fixture(scope="session")
+def nwp_ukv_zarr_path(ds_nwp_ukv):
+    ds = ds_nwp_ukv.chunk(
+        {
+            "init_time": 1, 
+            "step": -1, 
+            "variable": -1,
+            "x": 50, 
+            "y": 50,
+        }
+    )
+    with tempfile.TemporaryDirectory() as tmpdir:
+        filename = tmpdir + "/ukv_nwp.zarr"
+        ds.to_zarr(filename)
+        yield filename
+
+
+@pytest.fixture(scope="session")
+def ds_nwp_ecmwf():
+    init_times = pd.date_range(start="2023-01-01 00:00", freq="6h", periods=24 * 7)
+    steps = pd.timedelta_range("0h", "14h", freq="1h")
+
+    lons = np.arange(-12, 3)
+    lats = np.arange(48, 60)
+    variables = ["t2m","dswrf", "mcc"]
+
+    coords = (
+        ("init_time", init_times),
+        ("variable", variables),
+        ("step", steps),
+        ("longitude", lons),
+        ("latitude", lats),
+    )
+
+    nwp_array_shape = tuple(len(coord_values) for _, coord_values in coords)
+
+    nwp_data = xr.DataArray(
+        np.random.uniform(0, 200, size=nwp_array_shape).astype(np.float32),
+        coords=coords,
+    )
+    return nwp_data.to_dataset(name="ECMWF_UK")
+
+
+@pytest.fixture(scope="session")
+def nwp_ecmwf_zarr_path(ds_nwp_ecmwf):
+    ds = ds_nwp_ecmwf.chunk(
+        {
+            "init_time": 1, 
+            "step": -1, 
+            "variable": -1,
+            "longitude": 50, 
+            "latitude": 50,
+        }
+    )
+    with tempfile.TemporaryDirectory() as tmpdir:
+        filename = tmpdir + "/ukv_ecmwf.zarr"
+        ds.to_zarr(filename)
+        yield filename
+
+
+@pytest.fixture(scope="session")
+def ds_uk_gsp():
+    times = pd.date_range("2023-01-01 00:00", "2023-01-02 00:00", freq="30min")
+    gsp_ids = np.arange(0, 318)
+    capacity = np.ones((len(times), len(gsp_ids)))
+    generation = np.random.uniform(0, 200, size=(len(times), len(gsp_ids))).astype(np.float32)
+
+    coords = (
+        ("datetime_gmt", times),
+        ("gsp_id", gsp_ids),
+    )
+
+    da_cap = xr.DataArray(
+        capacity,
+        coords=coords,
+    )
+
+    da_gen = xr.DataArray(
+        generation,
+        coords=coords,
+    )
+
+    return xr.Dataset({
+        "capacity_mwp": da_cap, 
+        "installedcapacity_mwp": da_cap, 
+        "generation_mw":da_gen
+    })
+
+
+@pytest.fixture(scope="session")
+def uk_gsp_zarr_path(ds_uk_gsp):
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        filename = tmpdir + "/uk_gsp.zarr"
+        ds_uk_gsp.to_zarr(filename)
+        yield filename
+