Context

Using this data you can find what caused the delay for flight whether it's Security delay, NAS delay or Carrier delay, etc.

Content

What's inside is more than just rows and columns. Make it easy for others to get started by describing how you acquired the data and what time period it represents, too.

Data Dictionary

1. DayOfWeek → 1 (Monday) - 7 (Sunday)
2. Date → Scheduled date
3. DepTime → Actual departure time (local, hhmm)
4. ArrTime → Actual arrival time (local, hhmm)
5. CRSArrTime → Scheduled arrival time (local, hhmm)
6. UniqueCarrier → Unique carrier code
7. Airline → Airline company
8. FlightNum → flight number
9. TailNum → plane tail number
10. ActualElapsedTime → Actual time an airplane spends in the air(in minutes) with TaxiIn/Out
11. CRSElapsedTime → CRS Elapsed Time of Flight (estimated elapse time), in minutes
12. AirTime → Flight Time (in minutes)
13. ArrDelay → Difference in minutes between scheduled and actual arrival time
14. Origin → Origin IATA(International Air Transport Association) airport code
15. Org_Airport → Origin Airport Name
16. Dest → Destination IATA code
17. Dest_Airport → Destination Airport Name
18. Distance → Distance between airports (miles)
19. TaxiIn → Wheels down and arrival at the destination airport gate, in minutes
20. TaxiOut → The time elapsed between departure from the origin airport gate and wheels off, in minutes
21. Cancelled → Was the flight canceled?
22. CancellationCode → Reason for cancellation
23. Diverted → 1 = yes, 0 = no
24. CarrierDelay → Flight delay due to carrier(e.g. maintenance or crew problems, aircraft cleaning, fueling, etc), 0 = No, yes = (in minutes)
25. WeatherDelay → Flight delay due to weather, 0 = No, yes = (in minutes)
26. NASDelay → Flight delay by NSA(National Aviation System), 0 = No, yes = (in minutes)
27. SecurityDelay → Flight delay by this reason, 0 = No, yes = (in minutes)
28. LateAircraftDelay → Flight delay by this reason, 0 = No, yes = (in minutes)

Acknowledgements

Inspired from others DataSet in the same domain. So, tried to create one balanced dataset ready to use for beginners. This is a public dataset so it's not Licensed by anyone.