Closed kanesp closed 2 years ago
The anomaly column is only required for validation purpose. See point 1 in usage.
i find the anomaly column is used in anomaly_detection.test(test_loader, encoder, decoder, critic_x) which is used to detect anomalies. if i want to detect anomalies, my dataset must have the anomaly column. Right?
Description
The dataset for ur code should have a column name as signal containing the signals and a column with name anomaly containing the true labels. But in the paper of TADGAN, e.g.,NAB(Art) dataset is only has two COLUMN ( timestamp and value). how can i use the dataset like NAB?