Sendy Logistics Challenge
$7,000 USD
Predict the estimated time of arrival (ETA) for motorbike deliveries in Nairobi
23 August–25 November 2019 23:59
974 data scientists enrolled, 357 on the leaderboard
Using Uber movement data
published 4 Nov 2019, 14:34

In Uber Time, can anyone share how to obtain Sourceid and dstid from Longitude and Latitude?


u can use Point and Polygon from shapely : from shapely.geometry import Point, Polygon

create your point and polygon :

p = Point(24.952242, 60.1696017) poly = Polygon( [(24.950899, 60.169158), (24.953492, 60.169158), (24.953510, 60.170104), (24.950958, 60.169990)])

after that you can check if your polygon contains your point :


or if your point is in polygon :


There is a json file called sublocations in the uber data defining the boundaries of each 'district' in Nairobi. You have to use a geocoding library to map your points ( you have to do some searching inside the polygones ) to those districts.

The ID's obtained are sourceid for a pickup point, dstid for a destination point.

Thanks Yos.This makes sense. I will try it.

Thanks Blenz. I have downloaded the sublocations file. Will try now.

Has adding the Uber movement data improve the results for anyone?

Uber data did'nt give me much improvement

@seddik11, how many seconds improvement did you get on the leaderboard?