-
The documentation of the `weighted.median` states that the resulting value will be
`...a value m such that the total weight of data less than or equal to m is equal to half the total weight.`
Th…
-
Users noticed some strange behavior where lower quantiles would predict constant values while other quantiles would predict time-varying values.
When they manually hacked a work-around, they achie…
-
From https://discourse.julialang.org/t/median-vs-50th-quantile-giving-different-answers/18414/4
```julia
julia> x = [1; 4; 3; 2; 2.5; 7];
julia> w = [0.1;0.3;0.05;0.05;0.2;0.3];
julia> quantil…
-
Hello!
Thank you for this project, it's really complete and modular, which makes it easy to replicate and modify the code. I have a comment regarding the implementation of FQF. As far as I understa…
-
Is it feasible to update quantile sketches (with a focus on KLL) with multiple values at once rather than one at a time, especially if those values are identical?
I've created a PR at https://githu…
-
## Description
@leerho proposed how the topN algorithm can be improved here: https://github.com/apache/incubator-druid/issues/7161#issuecomment-468890906
## Motivation
Avoid potentially signi…
-
Issue #2283 identified fibers 1098, 3994, 4720, 4891 with problematic redshifts, possibly due to bad/unstable TPCORR issues (thanks to @rongpu and @julienguy for debugging those).
1098, 3994, 4720 …
-
For our work we frequently need to compute weighted quantiles. This is especially important when we need to weigh data from recent years more heavily in making predictions.
I've put together a fun…
-
We would like to have a linear opinion pool method. Here's a proposed function signature:
```
#' Compute ensemble model outputs as a linear pool, otherwise known as a
#' distributional mixture, …
-
### Notebook description
Dear @malmans2,
we agreed with ECMWF on preparing a notebook focused on the **hit-rate of seasonal forecasts** using a similar strategy as for the assessment of the bias…