phrb / experimentaldesign.jl

Design of Experiments in Julia

ExperimentalDesign

Build	Docs	Test Coverage

ExperimentalDesign provides tools for Design of Experiments in Julia, enabling the construction of designs for screening, modeling, exploration, and optimization.

Development on this package is ongoing, so expect things to change. Pull requests are more than welcome!

Check the documentation for the latest features and API, and check the examples directory for Jupyter Notebooks and code.

Current features are:

• Designs that support categorical and continuous factors
• Integration with StatsModels @formula
• Full factorial designs:
  • Explicit: for small designs that fit in memory
  • Iterable: for larger designs, generates experiments on demand
• Two-level fractional factorial designs
• Plackett-Burman designs for screening (check the example)
• Box-Behnken and central composite designs for response surface modeling
• Flexible random designs using the Distributions package
• Latin Hypercube designs using the LatinHypercubeSampling.jl package
• Several variance-optimizing criteria

Intended features include the ones provided by R packages such as DoE.base, FrF2, and AlgDesign.

experimentaldesign.jl's Issues

Latest release throws error on load

It looks like some code for testing was left behind in a file, which is no longer present on master. Maybe it's time to tag a new release?

@v1.5) pkg> add ExperimentalDesign
   Updating registry at `~/.julia/registries/General`
  Resolving package versions...
  Installed ShiftedArrays ────── v1.0.0
  Installed Primes ───────────── v0.5.0
  Installed StatsModels ──────── v0.6.13
  Installed ExperimentalDesign ─ v0.1.0
Updating `~/.julia/environments/v1.5/Project.toml`
  [4babbea4] + ExperimentalDesign v0.1.0
Updating `~/.julia/environments/v1.5/Manifest.toml`
  [4babbea4] + ExperimentalDesign v0.1.0
  [27ebfcd6] + Primes v0.5.0
  [1277b4bf] + ShiftedArrays v1.0.0
  [3eaba693] + StatsModels v0.6.13
[ Info: Precompiling ExperimentalDesign [4babbea4-9e7d-11e9-116f-e1ada04bd296]
ERROR: LoadError: LoadError: MethodError: no method matching term(::String)
Closest candidates are:
  term(::Symbol) at /home/fredrikb/.julia/packages/StatsModels/h6g21/src/terms.jl:598
  term(::Number) at /home/fredrikb/.julia/packages/StatsModels/h6g21/src/terms.jl:597
  term(::StatsModels.AbstractTerm) at /home/fredrikb/.julia/packages/StatsModels/h6g21/src/terms.jl:599
Stacktrace:
 [1] _broadcast_getindex_evalf at ./broadcast.jl:648 [inlined]
 [2] _broadcast_getindex at ./broadcast.jl:621 [inlined]
 [3] getindex at ./broadcast.jl:575 [inlined]
 [4] copy at ./broadcast.jl:876 [inlined]
 [5] materialize at ./broadcast.jl:837 [inlined]
 [6] linear_model(::DataFrames.DataFrame) at /home/fredrikb/.julia/packages/ExperimentalDesign/Cqcyh/src/d_optimal/variance_predictions.jl:14
 [7] optimize_design(; factors::Int64, levels::Int64, experiments::Int64, design::DataFrames.DataFrame, candidate_set::DataFrames.DataFrame, iterations::Int64, refresh_candidate_set::Bool) at /home/fredrikb/.julia/packages/ExperimentalDesign/Cqcyh/src/d_optimal/variance_predictions.jl:122
 [8] measure_optimize_design_refresh(::Bool) at /home/fredrikb/.julia/packages/ExperimentalDesign/Cqcyh/src/d_optimal/variance_predictions.jl:210
 [9] top-level scope at /home/fredrikb/.julia/packages/ExperimentalDesign/Cqcyh/src/d_optimal/variance_predictions.jl:246
 [10] include(::Function, ::Module, ::String) at ./Base.jl:380
 [11] include at ./Base.jl:368 [inlined]
 [12] include(::String) at /home/fredrikb/.julia/packages/ExperimentalDesign/Cqcyh/src/ExperimentalDesign.jl:3
 [13] top-level scope at /home/fredrikb/.julia/packages/ExperimentalDesign/Cqcyh/src/ExperimentalDesign.jl:32
 [14] include(::Function, ::Module, ::String) at ./Base.jl:380
 [15] include(::Module, ::String) at ./Base.jl:368
 [16] top-level scope at none:2
 [17] eval at ./boot.jl:331 [inlined]
 [18] eval(::Expr) at ./client.jl:467
 [19] top-level scope at ./none:3
in expression starting at /home/fredrikb/.julia/packages/ExperimentalDesign/Cqcyh/src/d_optimal/variance_predictions.jl:246
in expression starting at /home/fredrikb/.julia/packages/ExperimentalDesign/Cqcyh/src/ExperimentalDesign.jl:32

load error with @formula

PlackettBurman(@formula(y ~ x1 + x2 + x3 + x4))

LoadError: UndefVarError: @formula not defined
in expression starting at In[24]:1

Stacktrace:
[1] top-level scope
[2] include_string(::Function, ::Module, ::String, ::String) at ./loading.jl:1091
[3] execute_code(::String, ::String) at /Users/blaine/.julia/packages/IJulia/rWZ9e/src/execute_request.jl:27
[4] execute_request(::ZMQ.Socket, ::IJulia.Msg) at /Users/blaine/.julia/packages/IJulia/rWZ9e/src/execute_request.jl:86
[5] #invokelatest#1 at ./essentials.jl:710 [inlined]
[6] invokelatest at ./essentials.jl:709 [inlined]
[7] eventloop(::ZMQ.Socket) at /Users/blaine/.julia/packages/IJulia/rWZ9e/src/eventloop.jl:8
[8] (::IJulia.var"#15#18")() at ./task.jl:356

Using Julia 1.5.2

General registry entry incorrect? Always installs v0.1.0

When attempting to pull this package from the general registry, it always installs v0.1.0. It works fine when installing directly from the ExperimentalDesign repository.

I'm not knowledgeable about how the general registry works, but I took a look at the entry for ExperimentalDesign and compared it to a few others. It's a guess on my part, but Deps.toml doesn't have any information in it for v0.4.0, which probably creates a situation where the package manager thinks v0.4.0 doesn't exist because there are no dependencies.

I've looked a little at the package documentation but can't say I've found anything that might explain if this is the issue or not.

Status of ExperimentalDesign.jl?

I'm looking to use this package to do optimal design of experiments - what's the status of it? I've poked through the docs, but am not 100% sure on how everything all goes together.

Update for StatsModels v0.7

Update for StatsModels v0.7

A- E- G- optimality

Hi!

Is support of A- E- G- optimality in dev plan?

Add description for API and extend documentation

Hi! This is very nice package, but here is few documentation for API and examples. I can try to make some work if possible...

Extreme Vertex Designs

Hi again,

I, with the help of some others, was able to whip up some entry point code for making extreme vertex candidate sets. Maybe we can find a way to work together to flesh out this area of the ecosystem?

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!