by Adarsh Janakiraman, Data Science Intern at The Data Lab
The Internet has often been attributed the title of humanity’s greatest unifier, bringing people from across the globe, a little closer to each other. A gift to humanity though it might be, it has dulled our senses to anything that doesn’t move at the speed of light. So we come to our story, the data of air travel. We often forget, that the real world equivalent of this digital bonhomie brought on by the Internet, is air travel.
Thousands of flights zig-zagging through the stratosphere, bringing businessmen, tourists, and families to their destinations in previously unthinkable time. But the inevitable bane of delays, infinite security checks, bad food, cramped seats and the crying baby, do sour our experience, making us under appreciate, what is, one of humanity’s greatest achievements. Well, we are here to explore that world of air travel, to get an insight into an otherwise largely ignored world.
For this exploratory analysis, we are using the dataset provided by Planefinder. This dataset contains the positional record (latitude, longitude, altitude) of every flight in service on a certain date in 2014, taken every 2 minutes. A potential goldmine of information, we chose to focus on a few aspects of this data. The code for the analysis is available on Github.
London has an outsized influence inside the UK
Constraining our analysis to the UK only, we looked at the proportion of flights taking off from each of the major airports in the UK. What we found is that more half of them take off from London airports, mostly Heathrow and Gatwick. Manchester comes next, followed by Edinburgh, Luton and Bristol. The out-sized influence of London on the UK’s business scene is clear.
Taking off from Heathrow is the worst (followed by Birmingham!)
One thing we all hate, when it comes to air travel is, delays. We have all had that horror story involving checking into a flight before being told about the delay. But how about those delays that occur once we have taken our seats and been advised to strap in, but are not moving an inch! That is the delay we are looking at next: The delay between the flight recorders starting and the flight actually taking off. The histogram below shows the shape of the distribution of the delay. It peaks around the 10 min mark.
We can break this down by airport to see which airports in the UK cause the highest delays.
We can break this down by airline!
One reason Heathrow shows the worst take off delay time is because it is also the busiest. This makes intuitive sense to us: as the number of flights taking off from an airport increases, the busier it gets and the longer the subsequent delays. To accommodate for the vast scale difference between number of flights taking of from Heathrow as compared to the others, we have transformed our computation down to the Log scale. Birmingham airport stands out as an outlier on this plot. It doesn’t have the number of flights taking off from the airport to justify the take off delay time experienced.
UK’s most popular destination: the EU (not so the other way round)
With the Brexit referendum coming up soon, everyone is busy analysing the ties between the EU and the UK from different angles. Purely in terms of the number of flights in and out of the UK, the EU countries dominate the air traffic in this country. The number of flights going from the UK to the EU outstrip the number of flights going from the UK to the rest of the world! The same is not the case the other way round. The EU countries traffic with the UK is smaller than its traffic with the rest of the world. This is not surprising given that the UK is only a single country. The network graph below shows the strength of the relationship between the three nodes of our network.
The underlying numbers give an idea on the parity in the UK air travel market which is heavily reliant on the EU business.
From Region (chr) |
To Region (chr) |
total.count (int) |
|
1 | EU | EU | 7192 |
2 | EU | UK | 1383 |
3 | EU | World | 2416 |
4 | UK | EU | 1380 |
5 | UK | UK | 300 |
6 | UK | World | 530 |
7 | World | EU | 2336 |
8 | World | UK | 532 |
9 | World | World | 19344 |
And can you guess which country in the EU is the UK’s favorite destination? If you are thinking of the sun, sand and sangria, then you are right! It is Spain! The number of daily flights to Spain is equivalent to the next three destination countries combined!
So what have we learnt?
- Air traffic out of London accounts for more than half the air traffic from the entire UK
- Heathrow has the worst average take-off delay time of all UK airports. It is also the busiest in terms of number of flights taking off. Birmingham airport does not have the number of flights taking off from it to justify the extended delay.
- The EU is the UK’s biggest destination. There are about 2.5 times the number of flights going to the EU as compared to the rest of the world from the UK
- Spain is the UK’s most popular EU destination country
There are plenty of other nuggets that we can mine from this treasure trove of information. If anyone wants to participate in the analysis, you are welcome to fork the repository on Github.