How to split data in ML Multimetric job

I was trying to do Multimetric ml job with sample data(kibana_sample_data_flights), to get anomalies for flights from different Origin(Origin, OriginCountry, OriginCityName, OriginAirportID ..) to the destination ( Dest, DestCountry, DestCityName, DestAirportID ) for each Carrier for metric average AvgTicketPrice and event rate.
I know that should use split. But how do I split by Origin, Dest, Carrier for each metric (AvgTicketPrice, eventrate).

I have following doubts

  • How to split Origin(Origin, OriginCountry, OriginCityName, OriginAirportID ..) fields.
  • How to split Dest ( Dest, DestCountry, DestCityName, DestAirportID ).
  • How to split Origin (Origin, OriginCountry, OriginCityName, OriginAirportID ..) to Dest ( Dest, DestCountry, DestCityName, DestAirportID ) by Carrier for metric (mean of AvgTicketPrice).
    "FlightNum": "Y56DWSH",
    "DestCountry": "RU",
    "OriginWeather": "Cloudy",
    "OriginCityName": "Durban",
    "AvgTicketPrice": 404.7860204873357,
    "DistanceMiles": 6736.8698449714075,
    "FlightDelay": false,
    "DestWeather": "Sunny",
    "Dest": "Olenya Air Base",
    "FlightDelayType": "No Delay",
    "OriginCountry": "ZA",
    "dayOfWeek": 0,
    "DistanceKilometers": 10841.941063785665,
    "timestamp": "2018-12-24T18:22:55",
    "DestLocation": {
      "lat": "68.15180206",
      "lon": "33.46390152"
    "DestAirportID": "XLMO",
    "Carrier": "ES-Air",
    "Cancelled": false,
    "FlightTimeMin": 602.3300590992036,
    "Origin": "King Shaka International Airport",
    "OriginLocation": {
      "lat": "-29.61444444",
      "lon": "31.11972222"
    "DestRegion": "RU-MUR",
    "OriginAirportID": "DUR",
    "OriginRegion": "SE-BD",
    "DestCityName": "Olenegorsk",
    "FlightTimeHour": 10.03883431832006,
    "FlightDelayMin": 0

The multi-mettic UI only allows one split at a time. If you want to do more splits you can make separate jobs.

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.