21st
May 2017
Alice Jiang
@becausealice2
May 21 2017 02:27 UTC
@conradkay What are you trying to do, and what is the code actually doing?
Segev Malool
@segevmalool
May 21 2017 03:13 UTC
What's the difference between n points in a 1 dimensional space, and 1 point in an n dimensional space?
evaristoc
@evaristoc
May 21 2017 12:47 UTC
@segevmalool try to imagine drawing those points either on a line (1 dim) or a two-coordinate space (2 dim).
satenndrra
@satenndrra
May 21 2017 15:03 UTC
@evaristoc no problem!
satenndrra
@satenndrra
May 21 2017 15:09 UTC
@segevmalool I may be but by examining this situation with n=1, 2 and 3 and extrapolating for higher dimensions... any number of points (>1) in a 1 dimensional space would always form a line (along the 'length' of that dimension), whereas a point in an n dimensional space (including n=1 I guess) would still just be a point. I mean by definition a point has dimensions = 0, hence whether it lies on a line (1 dimensional), a piece of paper (2 dimensional) or within a solid object (3 dimensional), it would still be a point (an entity of n = 0). I guess...
*I may be wrong , but by examining...
Segev Malool
@segevmalool
May 21 2017 16:19 UTC
Here's my answer: Let's say n=10^10. In one context (if these are iid draws from some 1-d distribution) this would be considered good size dataset, and it would be appropriate to model them by drawing each point on a single line, and estimating statistics or density. But what if these points represent pixels in a 10^5 x 10^5 grey image? You could find the average pixel intensity in the image, and think of the image as a distribution of pixel intensities, and scrutinize it to death. "Studying the image." On the other hand, you could chunk up to a more appropriate level of abstraction, and think of the 10^10 pixels as being just a single point in a high dimensional space.
Segev Malool
@segevmalool
May 21 2017 16:25 UTC
Similarly, if I have 20 apples from a single tree, and each has a weight, then these are good candidates for statistical analysis. But if I have 10 apples and 10 oranges (20 fruits), then I'm likely to see a bimodal or noisy weight distribution "caused" by the "improper" aggregation of the apples and oranges.
John Otu
@johnotu
May 21 2017 20:14 UTC
Hi guys, is it still possible to get an API key for the open API?
Alice Jiang
@becausealice2
May 21 2017 20:56 UTC
@johnotu I'm fairly certain the API is still on the backburner and there are no keys just yet.