francescoalemanno / bayeshistogram.jl Goto Github PK
View Code? Open in Web Editor NEWpure Julia package for optimal histogram binning, based on piecewise constant model.
License: MIT License
bayeshistogram.jl's People
Stargazers
Watchers
bayeshistogram.jl's Issues
Provide errors
Planned for next release
supoprt `weight`?
Still reading the paper and I'm wondering how does weights work with this algorithm, for two reasons:
- The data in HEP has weights (so I assume the paper address it some how)
- I want to use this algorithm for re-binning rather than just binning on raw data
elaborate the point 2 a bit, often the raw data is >> RAM, the best I can do is to first make a really fine-binning histogram, then re-bin it
TagBot trigger issue
This issue is used to trigger TagBot; feel free to unsubscribe.
If you haven't already, you should update your TagBot.yml to include issue comment triggers.
Please see this post on Discourse for instructions and more details.
If you'd like for me to do this for you, comment TagBot fix on this issue.
I'll open a PR within a few hours, please be patient!
indexing off by 1
julia> BayesHistogram.bayesian_blocks(rand(1000); weights=randn(1000)).edges
ERROR: BoundsError: attempt to access 1001-element Vector{Float64} at index [[0, 1001]]
Stacktrace:
[1] throw_boundserror(A::Vector{Float64}, I::Tuple{Vector{Int64}})
@ Base ./abstractarray.jl:703
[2] checkbounds
@ ./abstractarray.jl:668 [inlined]
[3] _getindex
@ ./multidimensional.jl:874 [inlined]
[4] getindex
@ ./abstractarray.jl:1241 [inlined]
[5] bayesian_blocks(t::Vector{Float64}; weights::Vector{Float64}, prior::Pearson{Float64}, resolution::Float64, min_counts::Int64)
@ BayesHistogram ~/.julia/packages/BayesHistogram/V6yoj/src/BayesHistogram.jl:144
[6] top-level scope
@ REPL[20]:1Disagreement with respect to scikit-hep implementation
julia> using NPZ
julia> npzread("./data_gen.npz")
Dict{String, Vector{Float64}} with 2 entries:
"weights" => [1.03524, 1.59065, 1.92159, 1.7245, 1.25175, 1.1111, 1.0…
"data" => [-1.13384, 0.384319, 1.49655, -0.355382, -0.787534, -0.4…
julia> datas = npzread("./data_gen.npz");
julia> answers = npzread("./answers_bayesian_blocks.npz");
julia> bayesian_blocks(datas["data"]).edges
8-element Vector{Float64}:
-3.154662950679158
-2.126058692427544
-1.5407490071030014
-0.7146943329219142
0.6404466881064395
1.3817680464742417
2.1781371551736664
3.265843988558946
julia> answers["be1"]
9-element Vector{Float64}:
-3.154662950679158
-2.366746726914241
-1.8916975822891833
-1.2379204553303205
-0.7146943329219142
0.6404466881064395
1.3817680464742417
2.2181565018686125
3.265843988558946to make the data
import numpy as np
np.random.seed(111)
data1 = np.random.normal(size=1000)
data2 = np.random.normal(2, 1, size=1000)
weights = np.random.uniform(1, 2, size=1000)
np.savez("data_gen.npz", data=data1, weights=weights)here's the output:
data_gen.npz.txt
answers_bayesian_blocks.npz
Prior is specific to astrophysics
need handle integers
In [22]: modeling.bayesian_blocks(np.ceil(np.random.randn(1000) * 100))
Out[22]:
array([-284. , -211. , -131.5, -90.5, 67.5, 131.5, 176.5, 259.5,
326. ])(I will make a PR)
register
@JuliaRegistrator register
allow custom weights squared
since for already binned data:
sum(w.^2) != sum(w2)
we should allow passing a weights2 argument.
@Moelf : wanna have a stab at it?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.