Hi everyone, I’ve set up a test in DBT:

- name: features_usage_per_day
    description: "aggregate feature usage per day"
    tests:
      - elementary.all_columns_anomalies:
          meta:
            description: "Check for anomalies in all usage-numeric columns"
          exclude_regexp: "^(usage_date)$"
          training_period:
            period: day
            count: 168
          anomaly_sensitivity: 4
          timestamp_column: usage_date
          seasonality: day_of_week
          detection_period:
            period: day
            count: 3
          time_bucket:
            period: day
            count: 1
          column_anomalies:
            - average
          tags: ['daily_anomalies']

The data spans 505 days (with

usage_date

covering the last 505 days). When I run the test, I’m getting this error: “Not enough data to calculate anomaly scores on.” How is this possible when the training period is set to 168 days and the table contains 505 days? Any ideas? TY 🙂