An Anomaly With NetCDF Bundling

[AFg6K7h4fhy2]

This issue describes a previously undetected error that arrives with the author's updating of __init__.py.

Presently, the following exists (the author believes correctly) in pyproject.toml:

packages = [{include = "forecasttools"}]
include = [
    { path = "forecasttools/location_table.parquet", format = "sdist" },
    { path = "forecasttools/location_table.parquet", format = "wheel" },
    { path = "forecasttools/example_flusight_submission.parquet", format = "sdist" },
    { path = "forecasttools/example_flusight_submission.parquet", format = "wheel" },
    { path = "forecasttools/example_flu_forecast_wo_dates.nc", format = "sdist" },
    { path = "forecasttools/example_flu_forecast_wo_dates.nc", format = "wheel" },
    { path = "forecasttools/example_flu_forecast_w_dates.nc", format = "sdist" },
    { path = "forecasttools/example_flu_forecast_w_dates.nc", format = "wheel" },
    { path = "forecasttools/nhsn_hosp_COVID.parquet", format = "sdist" },
    { path = "forecasttools/nhsn_hosp_COVID.parquet", format = "wheel" },
    { path = "forecasttools/nhsn_hosp_flu.parquet", format = "sdist" },
    { path = "forecasttools/nhsn_hosp_flu.parquet", format = "wheel" },
]

However the following:

# location table (from Census data)
with importlib.resources.files(__package__).joinpath(
    "location_table.parquet"
).open("rb") as f:
    location_table = pl.read_parquet(f)

# load example flusight submission
with importlib.resources.files(__package__).joinpath(
    "example_flusight_submission.parquet"
).open("rb") as f:
    example_flusight_submission = pl.read_parquet(f)

# load example fitting data for COVID (NHSN, as of 2024-09-26)
with importlib.resources.files(__package__).joinpath(
    "nhsn_hosp_COVID.parquet"
).open("rb") as f:
    nhsn_hosp_COVID = pl.read_parquet(f)

# load example fitting data for influenza (NHSN, as of 2024-09-26)
with importlib.resources.files(__package__).joinpath(
    "nhsn_hosp_flu.parquet"
).open("rb") as f:
    nhsn_hosp_flu = pl.read_parquet(f)

# load light idata NHSN influenza forecast wo dates (NHSN, as of 2024-09-26)
with importlib.resources.files(__package__).joinpath(
    "example_flu_forecast_wo_dates.nc"
).open("rb") as f:
    nhsn_flu_forecast_wo_dates = az.from_netcdf(f)

# load light idata NHSN influenza forecast w dates (NHSN, as of 2024-09-26)
with importlib.resources.files(__package__).joinpath(
    "example_flu_forecast_w_dates.nc"
).open("rb") as f:
    nhsn_flu_forecast_w_dates = az.from_netcdf(f)

when converted BACK to this:

# location table (from Census data)
with importlib.resources.path(
    __package__, "location_table.parquet"
) as data_path:
    location_table = pl.read_parquet(data_path)

# load example flusight submission
with importlib.resources.path(
    __package__, "example_flusight_submission.parquet"
) as data_path:
    dtypes_d = {"location": pl.Utf8}
    example_flusight_submission = pl.read_parquet(data_path)

# load example fitting data for COVID (NHSN, as of 2024-09-26)
with importlib.resources.path(
    __package__, "nhsn_hosp_COVID.parquet"
) as data_path:
    nhsn_hosp_COVID = pl.read_parquet(data_path)

# load example fitting data for influenza (NHSN, as of 2024-09-26)
with importlib.resources.path(
    __package__, "nhsn_hosp_flu.parquet"
) as data_path:
    nhsn_hosp_flu = pl.read_parquet(data_path)

# load light idata NHSN influenza forecast (NHSN, as of 2024-09-26)
with importlib.resources.path(
    __package__, "example_flu_forecast_wo_dates.nc"
) as data_path:
    nhsn_flu_forecast_wo_dates = az.from_netcdf(data_path)


with importlib.resources.path(
    __package__, "example_flu_forecast_w_dates.nc"
) as data_path:
    nhsn_flu_forecast_w_dates = az.from_netcdf(data_path)

solved the following error:

File ~/Library/Caches/pypoetry/virtualenvs/forecasttools-06IzlalN-py3.12/lib/python3.12/site-packages/xarray/backends/file_manager.py:211, in CachingFileManager._acquire_with_cache_info(self, needs_lock)
    210 try:
--> 211     file = self._cache[self._key]
    212 except KeyError:

File ~/Library/Caches/pypoetry/virtualenvs/forecasttools-06IzlalN-py3.12/lib/python3.12/site-packages/xarray/backends/lru_cache.py:56, in LRUCache.__getitem__(self, key)
     55 with self._lock:
---> 56     value = self._cache[key]
     57     self._cache.move_to_end(key)

KeyError: [<class 'h5netcdf.core.File'>, (<_io.BufferedReader name='/Users/trevormartin/Documents/GitHub/CDC-CFA-Invested/forecasttools-py/forecasttools/example_flu_forecast_w_dates.nc'>,), 'r', (('decode_vlen_strings', True), ('driver', None), ('invalid_netcdf', None)), '72e69dc5-b04e-41e9-bab1-159720327227']

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
Cell In[2], line 12
      6 # xr.set_options(display_expand_data=False, display_expand_attrs=False)
      7 
      8 # load example forecast(s)
      9 idata = forecasttools.nhsn_flu_forecast_w_dates
---> 12 forecast_df = forecasttools.idata_forecast_w_dates_to_df(
     13     idata_w_dates=idata,
     14     location="TX",
...
File h5py/h5fd.pyx:154, in h5py.h5fd.H5FD_fileobj_get_eof()

File h5py/h5fd.pyx:154, in h5py.h5fd.H5FD_fileobj_get_eof()

ValueError: seek of closed file

The contents of __init__.py ought to be investigated further.

[AFg6K7h4fhy2]

It is worth noting here that the above error was originally detected during the development of the demonstration for NNH that occurred in this PR: #40.