Apply Model Page (17/11/2017)

[FireFlyTy]

Light Version of Train Page - see apply model section

CONTROLS:

• Model Tuning section

---

DYNAMIC THESHOLDS

• Low-type Anomalies (if Low or Both anomalies type)
  • Correction [-1, 1] (inherited from Train)
  • Scale [0.25, 4] (inherited from Train)
• High-type Anomalies (if High or Both anomalies type)
  • Correction [-1, 1] (inherited from Train)
  • Scale [0.25, 4] (inherited from Train)

ACTIONS

1. Apply Model caused by Test button:
   • RES = dynamicThreshold.apply( ts.agg = list( data.agg = <aggregated time series - test>, ts_type=<aggregation type - days, hours, etc>, ts_val=<aggregation step>, ts_func = <aggregation function>), model = MODEL, type_th = 'Both', correction =list("Low" = c(coef = <Low-type Anomalies: Correction TEST>, scale = <Low-type Anomalies: Scale TEST>), "High" = c(coef = < High-type Anomalies: Correction TEST>, scale = <High-type Anomalies: Scale TEST>)))
2. Show Results with interpretation
   Model Manual Tuning - caused by TEST Correction and Scale sliders: see Apply Model section

---

PROPHET

Model Tuning section

• Low-type Anomalies (if Low or Both anomalies type)
  • Scale [-100, 100] (default - inherited from Train)
• High-type Anomalies (if High or Both anomalies type)
  • Scale [-100, 100] (default - inherited from Train)

ACTIONS
Test execution - caused by Test button:

1. Apply Model:
   • RES <- model_prophet_new_interval(MODEL$data_test, percent_up=<Scale UP Train>, percent_low=<Scale LOW Train>, method='Both')
2. Tuning model
   • RES_tune <- model_prophet_new_interval(RES, percent_up=<Scale UP>, percent_low=<Scale LOW>, method='Both')
3. Show Results with interpretation:
   • plot_time_series(RES, treshhold_type = 'both') or
     plot_time_series(RES_tune, treshhold_type = 'both')
   • ANAYSIS.STAT = anomalies.stat(ad_results = RES, data, ts_type=< aggregation type - days, hours, etc >, ts_val=< aggregation step >)
   • anomalies.detail(aANAYSIS.STAT$ad_res[index,], data, ts_func = < aggregation function >)