Size of the circles in the Kibana Tile map visualization - elasticsearch

In Kibana we have a visualization called Tile map which has has several options to customize, such as map type.
My question is about one of this types: Shaded Circle Markers which is basically about changing colors based on value.
Documentation says:
Displays the markers with different shades based on the metric aggregation’s value.
and that's correct, but I don't understand why some bubbles are bigger than others.
I assume that this may be due to the distortion caused by Mercator projection, which which is well presented by Tissot's indicatrix, but I didn't find any source which confirming my hypothesis.
Could you confirm my suspicion or explain in other way this behavior?

I've got an answer from Elastic Team Member who confirmed my suspiction. This distortion is caused by Mercator projection.
Link to Elastic Search forum: https://discuss.elastic.co/t/size-of-the-circles-in-kibana-tile-map-visualization/108395

Related

How to add multiple geojsons to a geochoropleth in dc.js?

I'm trying to create a geochoropleth that maps subregions, but also includes outlines of larger regions. (You can think of it like mapping counties, but then wanting to include thicker outlines of states). Not all subregions are part of larger regions that need to be outlined. (Most aren't.) You can see an example of what I'm trying to replicate here:
What's the best way to add this regional outline to my map? I've tried keeping the regions and subregions as two separate files, with two overlaygeojsons calls in my geochoropleth call (with added d3 styling to change the fill and stroke to just be an outline). But when I do - the projection of the regional outline layer is strangely offset from the lower one.
I've also considered having both sets of boundaries in just the one geojson. However, I wasn't sure how to work with this.
While it would be nice to be able to mouseover the boundaries of the larger regions and get a tooltip before crossing over into the individual subregions and getting their tooltips, this isn't a must. I could live with just outlines around the regions. Please advise on the best way to do this. Happy to provide more detail, and thanks so much!
EDIT: I discovered that I had a misplaced transform tag which is what offset the second layer. Fixed now!

Kibana graph for anomaly detection

With some data loaded into ES using LS, is there a way to mention in Kibana a threshold and display an indicator it breaches the threshold. For example number of transaction in an hour across the system lets set to 200. When gets refreshed the dashboard, it should indicate in red or something when it goes beyond 200 in a time line graph or some visualization.
So If we see for whole day some hours will be red or spikes and most will be green or lower lines. This will be useful for us to display capability of anamoly detection. We are still working to understand Prelert but this kind of detection in Kibana will help us to see in graphs.
Regards,
Raj
There's no such direct threshold mechanism which you could apply on the Kibana Visualizations as the issue's still open.
But then a workaround for this could be to go with a scripted field in Kibana so that you could add up a constant value and use it as a margin in your visualization. Note that The scripted field may work for line visualizations, but it isn't compatible with an area visualization using sub-aggregations.
OR you could use a filter and stacked lines with having one color for above threshold and another color for the ones which under the threshold.
You could still follow up on this ticket and this SO could be handy. Hope it helps!

how do you set projections for city level geographies

I've asked similar questions before and I'm still struggling.
I want to create geo based info graphics at the level of a city.
I need to be able to take some latitude/longitude values and project them such that they are centered and appropriately zoomed.
It would help me a great deal to see an example that plots a small number of points.
37.781040, -122.497681
37.720504, -122.495622
37.723220, -122.395028
This is roughly an L shape and all three points should be in San Francisco.
It could be as simple as 3 black dots on a white background. I hope to learn:
which projection?
how do you adjust the projection so that an area the size of San Francisco is on the canvas?
how do you translate those coordinates and position them on that canvas?
Could someone create such an example?
Thanks.
-Kelly
I created a simple example that works.
https://gist.github.com/kellyfelkins/9741723
I think I was making multiple mistakes that made it really difficult to correct.
In case others have troubles too, here are some things to watch out for:
The projection method expects an array. For a while I was passing it 2 arguments, but it needs a single argument that is an array.
The projection expects the values in longitude, latitude order.
-Kelly

d3 map shows empty with seemingly valid topojson data

I followed this example : http://bost.ocks.org/mike/map/
to display this topojson file :
https://github.com/max-l/topojson-experiments/blob/master/qc-map.json
the map is always empty, I tried setting the proper center
d3.geo.albers().center(-71,45) and many other things without success.
I noticed that Github is able to render it (with leaflet)
https://github.com/max-l/topojson-experiments/blob/master/qc-map.json
which makes me assume it is valid topojson..
I'd guess its a projection issue. The co-ordinates in the topojson and your center look like they are WSG84 or Mercator co-ordinates (the America's are expressed as negative longitudes) and they are similar to the coordinates in this question. WSG84 is generally a safe guess for projections particularity for things like Google Maps, although Albers is commonly used for North America.
I've made a gist using Mercator which displays the map and you can see the block here.

Visualization of river- animation via code

I am trying to visualize a river flow- basically, should be able to visualize river current direction and speed based on an user-defined external parameter. This is required to demonstrate vectors in two dimensions- given education needs, animation quality can be minimal- 'tolerable enough'.
I tried a simplistic approach by a blue background with lines indicating currents- comes out very weak and below my low standards!!
Can someone point out a good example/ approach for achieving the same? Thanks.
You can create an image filter that looks like water. Look at Jerry's image filters. Specifically look at the the caustic filter. You could animate it moving from one end of the river to the other end. You can also experiment with varying the time parameter. Since it's open source, you can translate it to other languages.
Here are some links to 3d visualizations.

Resources