Apologies for the delayed response.
For features:
When you execute batteryml run configs/baselines/sklearn/variance_model/matr_1.yaml ./workspace/test --train --eval, the data will be cached in the BatteryML/cache folder. The cached files will have names in the format battery_cache_xx.pkl.
To load the data from these cached pickle files, you can use the following keys:
data['dataset']: This contains the features.
data['raw_data']: This contains the processed raw data.
The naming of the cache files is based on a hash of the config settings in the config.yaml file. We use the hash_string function in BatteryML/batteryml/pipeline.py for this.
For predictions:
As for the predictions, they are stored in BatteryML/workspaces/<your model>/<dataset>/predictions_seed_n_xx.pkl. Here, and should be replaced with the name of your model and dataset, respectively.
I hope this clarifies your question. Let me know if you have any further queries.
Apologies for the delayed response. For features: When you execute
batteryml run configs/baselines/sklearn/variance_model/matr_1.yaml ./workspace/test --train --eval, the data will be cached in theBatteryML/cachefolder. The cached files will have names in the formatbattery_cache_xx.pkl.To load the data from these cached pickle files, you can use the following keys:
data['dataset']: This contains the features.data['raw_data']: This contains the processed raw data.The naming of the cache files is based on a hash of the config settings in the
config.yamlfile. We use the hash_string function inBatteryML/batteryml/pipeline.pyfor this.For predictions: As for the predictions, they are stored in and should be replaced with the name of your model and dataset, respectively.
BatteryML/workspaces/<your model>/<dataset>/predictions_seed_n_xx.pkl. Here,I hope this clarifies your question. Let me know if you have any further queries.