Error after resume training from previous non finished training

[Dadja111]

Error for 1_Default_LightGBM_SampleWeigthing_Update_1

'AutoML_1/X.data'
Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/supervised/base_automl.py", line 1178, in _fit
trained = self.train_model(params)
File "/usr/local/lib/python3.10/site-packages/supervised/base_automl.py", line 384, in train_model
mf.train(results_path, model_subpath)
File "/usr/local/lib/python3.10/site-packages/supervised/model_framework.py", line 171, in train
train_data, validation_data = self.validation.get_split(k_fold, repeat)
File "/usr/local/lib/python3.10/site-packages/supervised/validation/validation_step.py", line 28, in get_split
return self.validator.get_split(k, repeat)
File "/usr/local/lib/python3.10/site-packages/supervised/validation/validator_kfold.py", line 120, in get_split
X = load_data(self._X_path)
File "/usr/local/lib/python3.10/site-packages/supervised/utils/utils.py", line 25, in load_data
return store.get(file_path)
File "/usr/local/lib/python3.10/site-packages/supervised/utils/utils.py", line 11, in get
return copy.deepcopy(Store.data[key])
KeyError: 'AutoML_1/X.data'

Indeed I observed from extraction below from your code (https://github.com/mljar/mljar-supervised/blob/master/supervised/utils/utils.py#L4C1-L29C39):

class Store:
data = {}

def set(self, key, value):
    Store.data[key] = value

def get(self, key):
    return copy.deepcopy(Store.data[key])

def dump_data(file_path, df):
store = Store()
store.set(file_path, df)
# try:
# df.to_parquet(file_path, index=False)
# except Exception as e:
# df.to_csv(file_path, index=False)

def load_data(file_path):
store = Store()
return store.get(file_path)
# try:
# return pd.read_parquet(file_path)
# except Exception as e:
# return pd.read_csv(file_path)

Calling load_data function will always result from error. The Store class instance does not containing any data after initialization. So looking for some key in store will always result in error.

I was not able to continue training due to a such error. Every new model fitting result in the same error.
I also get "'module' object is not callable" several time.