I have followed the steps in your github and blog, everything went well except for the size of train and test set. In the fold \train_test_data\application_classification\test.parquet, the total size of data is 2.49 GB while that in \train_test_data\application_classification\train.parquet is only 37.6 MB. Is that OK?
I have followed the steps in your github and blog, everything went well except for the size of train and test set. In the fold \train_test_data\application_classification\test.parquet, the total size of data is 2.49 GB while that in \train_test_data\application_classification\train.parquet is only 37.6 MB. Is that OK?