#! pip install climetlab_s2s_ai_challenge --quiet
import climetlab as cml
import xarray as xr
xr.set_options(display_style="text")
import climetlab_s2s_ai_challenge
print(f"Climetlab version : {cml.__version__}")
print(f"Climetlab-s2s-ai-challenge plugin version : {climetlab_s2s_ai_challenge.__version__}")
Climetlab version : 0.9.1 Climetlab-s2s-ai-challenge plugin version : 0.8.1
Let us get the zarr pointer to the cloud data.
hindcast = cml.load_dataset(
"s2s-ai-challenge-training-input", origin="ecmwf", parameter="tp", format="zarr"
).to_xarray()
hindcast.coords
By downloading data from this dataset, you agree to the terms and conditions defined at https://apps.ecmwf.int/datasets/data/s2s/licence/. If you do not agree with such terms, do not download the data.
/Users/aaron.spring/anaconda3/envs/climetlab/lib/python3.7/site-packages/xarray/core/dataset.py:413: UserWarning: Specified Dask chunks (5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 3) would separate on disks chunk shape 10 for dimension forecast_time. This could degrade performance. Consider rechunking after loading instead. _check_chunks_compatibility(var, output_chunks, preferred_chunks) /Users/aaron.spring/anaconda3/envs/climetlab/lib/python3.7/site-packages/xarray/core/dataset.py:413: UserWarning: Specified Dask chunks (120, 120) would separate on disks chunk shape 240 for dimension longitude. This could degrade performance. Consider rechunking after loading instead. _check_chunks_compatibility(var, output_chunks, preferred_chunks)
Coordinates: * forecast_time (forecast_time) datetime64[ns] 2000-01-02 ... 2012-01-16 * latitude (latitude) float64 90.0 88.5 87.0 85.5 ... -87.0 -88.5 -90.0 * lead_time (lead_time) timedelta64[ns] 0 days 1 days ... 45 days 46 days * longitude (longitude) float64 0.0 1.5 3.0 4.5 ... 355.5 357.0 358.5 * realization (realization) int64 0 1 2 3 4 5 6 7 8 9 10 valid_time (forecast_time, lead_time) datetime64[ns] dask.array<chunksize=(53, 47), meta=np.ndarray>
forecast = cml.load_dataset("s2s-ai-challenge-test-input", origin="ecmwf", parameter=["tp"], format="zarr").to_xarray()
forecast
By downloading data from this dataset, you agree to the terms and conditions defined at https://apps.ecmwf.int/datasets/data/s2s/licence/. If you do not agree with such terms, do not download the data.
<xarray.Dataset> Dimensions: (forecast_time: 53, latitude: 121, lead_time: 47, longitude: 240, realization: 51) Coordinates: * forecast_time (forecast_time) datetime64[ns] 2020-01-02 ... 2020-12-31 * latitude (latitude) float64 90.0 88.5 87.0 85.5 ... -87.0 -88.5 -90.0 * lead_time (lead_time) timedelta64[ns] 0 days 1 days ... 45 days 46 days * longitude (longitude) float64 0.0 1.5 3.0 4.5 ... 355.5 357.0 358.5 * realization (realization) int64 0 1 2 3 4 5 6 7 ... 44 45 46 47 48 49 50 valid_time (forecast_time, lead_time) datetime64[ns] dask.array<chunksize=(53, 47), meta=np.ndarray> Data variables: tp (realization, forecast_time, lead_time, latitude, longitude) float32 dask.array<chunksize=(6, 2, 47, 121, 240), meta=np.ndarray> Attributes: Conventions: CF-1.7 GRIB_centre: ecmf GRIB_centreDescription: European Centre for Medium-Range Weather Forecasts GRIB_edition: 2 GRIB_subCentre: 0 history: 2021-05-10T15:46:13 GRIB to CDM+CF via cfgrib-0.... institution: European Centre for Medium-Range Weather Forecasts