Its always showing

Not enough data to calculate anomaly score

I tried different anomaly_sensitivity from 1.5 to 2 Nothing is working out

models:
  - name: metric_cal
    config:
      elementary:
        timestamp_column: 'metric_date'
    columns:
      - name: metric_value
        tests:
          - elementary.column_anomalies:
              column_anomalies:
                - sum
              time_bucket:
                period: month
                count: 1
              days_back: 426
              config:
                severity: ERROR
              anomaly_sensitivity: 2
              where_expression: "product_name = 'Transactions' "

Hey @Ram, Do you have available data for 426 days back ?

Yes

Hey @Ram,

min_training_set_size

is by default 14. As we truncate to full months, 426 days probably result in 13 buckets. you can change the default, see here how: https://docs.elementary-data.com/data-tests/anomaly-detection-configuration/min-training-set-size

@Maayan Salom I tried as you mentioned added

min_training_set_size:13

Still i see Not enough data to calculate anomaly score.

Did you run the test with this config and produced a new report? Also if there is no data the bucket will be missing. I suggest you try it with min training of 3 for example to see it is working

Yes ran the dbt test and then edr report