Recover metview failure

[PaoloBonettiPolimi]

Overview

I have added the option to read the .csv files of our seven regions and plotting with matplotlib rather than using metview to avoid crashed when it is not possible to load it.

@mmaiergerber let me know if you double check it and you find some issues, it seems to work both with and without metview locally.
@cehbrecht let me know if this works when deployed.

[cehbrecht]

@PaoloBonettiPolimi I have deployed this branch and the processes starts. But it fails with an exception:

Traceback (most recent call last):
  File "/usr/local/anaconda/envs/shearwater/lib/python3.11/site-packages/pywps/app/Process.py", line 260, in _run_process
    self.handler(wps_request, wps_response)  # the user must update the wps_response.
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/anaconda/envs/shearwater/lib/python3.11/site-packages/shearwater/processes/wps_cyclone.py", line 263, in _handler
    prediction = model_trained.predict(test_img_std)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/anaconda/envs/shearwater/lib/python3.11/site-packages/keras/src/utils/traceback_utils.py", line 70, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/usr/local/anaconda/envs/shearwater/lib/python3.11/site-packages/keras/src/engine/data_adapter.py", line 1319, in __init__
    raise ValueError("Expected input data to be non-empty.")
ValueError: Expected input data to be non-empty.

Maybe this is due to the current default input parameters?

[PaoloBonettiPolimi]

@cehbrecht it should be due to the default date, since without metview we only have the csv data from April 2016 to December 2019. I tried changing the year to 2019 and it seems to work on the version you deployed.