Co-written by fellow data scientist & kitesurfing enthusiast Michal Stypa.

While thinking about the next kiteboarding session, we asked ourselves if there is anything we as data scientists can do to get the most out of our beloved sport? We were looking for tangible insights, something that would give us an advantage in planning when and where to head out for the next session.

For those not quite familiar with the sport, kiteboarding requires fair amounts of steady, on-shore wind. It is a simple but crucial condition. No wind, no kite. There are of course other factors influencing the “kiteability” of a day but lack of wind/off-shore winds are the only two real show-stoppers.

This being by far the biggest issue of any kiteboader, is why we decided to focus our efforts on wind analysis, taking a closer look on the historical data from our home region — Skåne, Sweden.

How many kiteable days are there per year?

To answer this question, we will dive into some wind data and use data analysis to figure out when the best time is to kitesurf. But first, an introduction to the data:

Spots

• Landskrona — Lundåkra
• Lomma — Habo Ljung
• Falsterbo — Ljunghusen/Parkvägen

Data & tools

We gathered and augmented the data using python originating from multiple sources, most notably Dark Sky API , sunrise-sunset.org/api, and findwind.se. The data ranges from 2008 to 2017 with an hourly granularity giving us 87672 data points per spot. Here is a sample of how each hour is represented in the data.

{
  "precipProbabilityError": 0.2,
  "precipAccumulation": 0.03,
  "icon": "clear-night",
  "precipType": "snow",
  "precipIntensityError": 1.3818,
  "humidity": 0.92,
  "cloudCover": 0.14,
  "summary": "Clear",
  "apparentTemperature": -7.06,
  "pressure": 1012.87,
  "windSpeed": 1.54,
  "temperature": -4.58,
  "time": 978303600,
  "windBearing": 257,
  "precipIntensity": 0.0229,
  "uvIndex": 0,
  "dewPoint": -5.61,
  "precipProbability": 0.73
}

We used pandas for cleaning/processing/analysis and the stunning charts you see in this post are made with react-vx. They’re interactive in our original blog post.

#data-analysis #kitesurfing #programming #visualization #python