dded note for next steps

0c1bc74b · Carsten Hinz · 3ee81cb4 · 0c1bc74b
Commit 0c1bc74b authored 10 months ago by Carsten Hinz
--- a/tests/produce_data_manyStations.ipynb
+++ b/tests/produce_data_manyStations.ipynb
@@ -30,7 +30,7 @@
    "    RegularGrid( lat_resolution=1.9, lon_resolution=2.5, ),\n",
    "    TimeSample( start=dt(2000,1,1), end=dt(2019,12,31), sampling=\"daily\"),#possibly adopt range:-)\n",
    "    [\"mole_fraction_of_ozone_in_air\"],#variable name\n",
-    "    [ \"dma8epax\" ]\n",
+    "    [ \"dma8epax\" ]# change to dma8epa_strict\n",
    ")\n",
    "\n",
    "configs = {\n",

 %% Cell type:code id: tags:

 ``` python
 from datetime import datetime as dt
 from collections import namedtuple
 from pathlib import Path

 from toargridding.toar_rest_client import AnalysisServiceDownload
 from toargridding.grids import RegularGrid
 from toargridding.gridding import get_gridded_toar_data
 from toargridding.metadata import TimeSample
 ```

 %% Cell type:code id: tags:

 ``` python
 #creation of request.

 Config = namedtuple("Config", ["grid", "time", "variables", "stats"])

 valid_data = Config(
    RegularGrid( lat_resolution=1.9, lon_resolution=2.5, ),
    TimeSample( start=dt(2000,1,1), end=dt(2019,12,31), sampling="daily"),#possibly adopt range:-)
    ["mole_fraction_of_ozone_in_air"],#variable name
-    [ "dma8epax" ]
+    [ "dma8epax" ]# change to dma8epa_strict
 )

 configs = {
    "test_ta"  : valid_data
 }

 #testing access:
 #config = configs["test_ta"]
 #config.grid
 ```

 %% Cell type:code id: tags:

 ``` python
 #CAVE: the request takes over 30min per requested year. Therefore this cell needs to be executed at different times to check, if the results are ready for download.
 #the processing is done on the server of the TOAR database.
 #a restart of the cell continues the request to the REST API if the requested data are ready for download
 # The download can also take a few minutes

 stats_endpoint = "https://toar-data.fz-juelich.de/api/v2/analysis/statistics/"
 cache_basepath = Path("cache")
 result_basepath = Path("results")
 cache_basepath.mkdir(exist_ok=True)
 result_basepath.mkdir(exist_ok=True)
 analysis_service = AnalysisServiceDownload(stats_endpoint=stats_endpoint, cache_dir=cache_basepath, sample_dir=result_basepath, use_downloaded=True)

 for person, config in configs.items():
    datasets, metadatas = get_gridded_toar_data(
        analysis_service=analysis_service,
        grid=config.grid,
        time=config.time,
        variables=config.variables,
        stats=config.stats,
    )

    for dataset, metadata in zip(datasets, metadatas):
        dataset.to_netcdf(result_basepath / f"{metadata.get_id()}.nc")
        print(metadata.get_id())
 ```