Sendy Logistics Challenge
$7,000 USD
Predict the estimated time of arrival (ETA) for motorbike deliveries in Nairobi
1552 data scientists enrolled, 431 on the leaderboard
LogisticsPredictionStructuredLocation
Kenya
23 August 2019—26 November 2019
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?

Hello,

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 :

poly.contains(p)

or if your point is in polygon :

p.within(poly)

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

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 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?