Popular comments by everyoneishigh

Monthly Challenge – Sofia Air – Solution – Kiwi Team

Fantastic work ! I got a lot of insight about the data which I never had before !

I was thinking of fixing the error values in temperature and all by taking the forward and previous value of the error value and taking those two’s mean instead of the whole column. For example at 1pm the temperature is 17 and 2pm is 53 and 3pm is 19, so I’ll set a threshold of max temperature which will catch 53 as an anomaly and then then replace 53 by 18 which is the average of 17 and 19. Also the mentioned operation will be done after grouping the geohashes.

It is just a suggestion and I am just a beginner so this suggestion may not be helpful :p

Good luck !