Hi guys, I come to present a little project that I have done.
As a data geek computer scientist, I saw the opportunity to learn from my data and make predictions on the GPX files given by the organizations before the races.
That’s why I’ve made a tool that collects all the Strava data you have, trains a ML model, for now with 94% accuracy, and tells you how long it would take you to finish a given track in GPX. The result it throws up is a map with the GPX plotted, with the sections for each slope, and the times in which you would do each quarter of the section.
It’s a “simple” model that has ended up being quite useful to know in how much time I’ll do a new route for example, or a local competition I don’t know. It takes into account values such as time of day, season of the year, ATL, CTL, distance, ascent in meters, percentage of slope sections, etc.
I’m working on a more interactive version, for now it works only by script. For now it is only available to run locally.
I leave the repository for those who understand programming, and some of the results it launches.
I have to say that these coefficients are with respect to my training and my data, there will be something that does not make sense.
I want to implement more features, like plotting the elevation profile, the percentages of each slope category (in this case downhill, green, yellow, …, black, Wahoo scale), etc.
Feel free to leave any ideas or opinions