
タイトル：
Aude Explores Coordinated Migration  Data Analysis with R

概説：

We want you to develop a mindset of being both curious and skeptical, when

you work with data. To help you get into this mindset, I want to share

another conversation that I had with Aude. In this next video, I want you

to listen to Aude's work and look

out for how she demonstrated this exact mindset.

>> So we gathered all the home towns and current cities from the

users and I was looking at conditional probabilities given

a hometown. What is the probability that you currently live

in each different cities? Like, for example given that your

hometown is New York, what is the probability that you

live in Chicago or that you live in, that you

still live in New York or that you live in

San Francisco or Paris and so on. And what I

was expecting is that, at least, the most likely city,

where you would live right now would be the city where

your home town is. If you grew up in

Chicago, the most likely place that you're going to

be now is still Chicago. You could be moving

as well but the most likely place would remain your

hometown. But I saw a fair number of cases

where the most likely current city was different from

the home town and, and that was, was a

fairly high probability. I was really surprised. I was wondering

if I had, had a prime in my computations, If there was some issues upstream of

what I was doing. So I decided to put all the cities on a map. All the pairs of

hometowns and current cities for which the most

likely current city was different from the hometown. And

what we saw on this map was really fascinating

because it was really not what we we're expecting.

It was not a bug in the code. We were really seeing patterns arise. Here we only

plotted pairs of hometown and current city, so

there's no movement between the pairs but what we

see is that a lot of these cities for which the most likely

current city is different from the hometown arise in western Africa or in

India or in like Turkey, which we were not

necessarily expecting at the beginning. And there were a

lot of small cities all moving to the same current

city and so we decided to dig a bit

more into it. One thing that happens is that sometimes

the distribution of the current city is very flat.

Given that you grew up in, let's say Paris, maybe

you're still living in Paris but maybe you live in

like one of the thousand cities in the suburbs and

so the distribution is really flat and so we

have to decide what was considered as a coordinates

demarcation. We decided yeah, the probability to move to

that city is high enough that we're considering that.

And the other thing we have to think about is that if you look at the map at

the world scale or if you zoom to a

very specific area, you don't want to see the same things.

So,we also want it to have interactivity in the visualization. And so we

decided to use D3, which is a Javascriptbased visualization framework, which

enables you to have a lot of interactivity with with your data

and enabled us to do a lot of that exploration and so on.