Merge pull request #21 from senresearch/develop

v0.2.0

.github/workflows/CompatHelper.yml

@@ -0,0 +1,16 @@
+name: CompatHelper
+on:
+  schedule:
+    - cron: 0 0 * * *
+  workflow_dispatch:
+jobs:
+  CompatHelper:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Pkg.add("CompatHelper")
+        run: julia -e 'using Pkg; Pkg.add("CompatHelper")'
+      - name: CompatHelper.main()
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          COMPATHELPER_PRIV: ${{ secrets.COMPATHELPER_PRIV }}  # optional
+        run: julia -e 'using CompatHelper; CompatHelper.main()'

.github/workflows/TagBot.yml

@@ -0,0 +1,15 @@
+name: TagBot
+on:
+  issue_comment:
+    types:
+      - created
+  workflow_dispatch:
+jobs:
+  TagBot:
+    if: github.event_name == 'workflow_dispatch' || github.actor == 'JuliaTagBot'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: JuliaRegistries/TagBot@v1
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          ssh: ${{ secrets.DOCUMENTER_KEY }}

.github/workflows/ci.yml

@@ -0,0 +1,51 @@
+name: CI
+on:
+  pull_request:
+  push:
+    branches: 
+      - main
+      - dev
+      - testing
+jobs:
+  test:
+    name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        version:
+          - '1.6'
+          - '1' # automatically expands to the latest stable 1.x release of Julia
+          - 'nightly'
+        os:
+          - ubuntu-latest
+        arch:
+          - x64
+        include:
+          - os: windows-latest
+            version: '1'
+            arch: x64
+    steps:
+      - uses: actions/checkout@v2
+      - uses: julia-actions/setup-julia@v1
+        with:
+          version: ${{ matrix.version }}
+          arch: ${{ matrix.arch }}
+      - uses: actions/cache@v1
+        env:
+          cache-name: cache-artifacts
+        with:
+          path: ~/.julia/artifacts
+          key: ${{ runner.os }}-test-${{ env.cache-name }}-${{ hashFiles('**/Project.toml') }}
+          restore-keys: |
+            ${{ runner.os }}-test-${{ env.cache-name }}-
+            ${{ runner.os }}-test-
+            ${{ runner.os }}-
+      - uses: julia-actions/julia-buildpkg@v1
+      - uses: julia-actions/julia-runtest@v1
+        env:
+          JULIA_NUM_THREADS: 4
+      - uses: julia-actions/julia-processcoverage@v1
+      - uses: codecov/codecov-action@v1
+        with:
+          file: lcov.info

.github/workflows/documentation.yml

@@ -0,0 +1,33 @@
+# [.github/workflows/Documentation.yml]
+name: Documentation
+
+on:
+  push:
+    branches:
+      - main
+      - dev
+    tags: '*'
+  pull_request:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: julia-actions/setup-julia@latest
+      - uses: julia-actions/julia-buildpkg@v1
+        with:
+          version: '1'
+      - name: Install dependencies
+        run: julia --project=docs/ -e '
+             using Pkg;
+             Pkg.develop(PackageSpec(path=pwd()));
+             Pkg.add("Documenter");
+             Pkg.instantiate()'
+
+      - name: Build and deploy
+        run: julia --project=docs docs/make.jl
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          DOCUMENTER_KEY: ${{ secrets.DOCUMENTER_KEY }}
+          DOCUMENTER_DEBUG: true

.gitignore

@@ -1 +1,6 @@
-*.DS_Store
+/docs/build/
+/docs/site/
+*.DS_Store
+*.jl.*.cov
+*.jl.cov
+*.jl.mem

Project.toml

@@ -1,19 +1,25 @@
 name = "MatrixLM"
 uuid = "37290134-6146-11e9-0c71-a5c489be1f53"
-authors = ["Jane Liang"]
-version = "0.1.3"
+authors = ["Jane Liang, Saunak Sen"]
+version = "0.2.0"
 
 [deps]
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 Distributed = "8ba89e20-285c-5b6f-9357-94700520ee1b"
-GLM = "38e38edf-8417-5370-95a0-9cbb8c7f171a"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 SharedArrays = "1a1011a3-84de-559e-8e89-a11a2f7dc383"
 Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
-Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+StatsModels = "3eaba693-59b7-5ba5-a881-562e759f1c8d"
 
 [compat]
 DataFrames = "0.22, 1"
-GLM = "1.3, 2"
-julia = "1.0.5"
+StatsModels = "0.6 - 0"
+julia = "1"
+
+[extras]
+GLM = "38e38edf-8417-5370-95a0-9cbb8c7f171a"
+Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+
+[targets]
+test = ["GLM", "Test"]

README.md

@@ -1,12 +1,19 @@
 # MatrixLM
 
-[![Build Status](https://travis-ci.com/senresearch/MatrixLM.jl.svg?branch=master)](https://travis-ci.com/senresearch/MatrixLM.jl)
+[![CI](https://github.com/senresearch/MatrixLM.jl/actions/workflows/ci.yml/badge.svg?branch=testing)](https://github.com/senresearch/MatrixLM.jl/actions/workflows/ci.yml)
+[![codecov](https://codecov.io/gh/senresearch/MatrixLM.jl/branch/testing/graph/badge.svg?token=uHM6utUQoi)](https://codecov.io/gh/senresearch/MatrixLM.jl)
+[![MIT license](https://img.shields.io/badge/license-MIT-green.svg)](https://github.com/chenhz1223/MatrixLM.jl/blob/main/LICENSE.md)
+[![Documentation](https://img.shields.io/badge/docs-dev-blue.svg)](https://senresearch.github.io/MatrixLM.jl/dev/)
+[![Pkg Status](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active)
+
+## Description
+
+This package can estimates matrix linear models. The core functions to obtain closed-form least squares estimates for matrix linear models. Variance shrinkage is adapted from [Ledoit & Wolf (2003)](https://www.sciencedirect.com/science/article/pii/S0927539803000070).
 
-Core functions to obtain closed-form least squares estimates for matrix linear models. Variance shrinkage is adapted from Ledoit & Wolf (2003)<sup>[1](#myfootnote1)</sup>.
 
 An extension of `MatrixLM` for applications in high-throughput genetic screens is the [`GeneticScreens`](https://github.com/senresearch/GeneticScreens.jl) package. See the associated paper, ["Matrix linear models for high-throughput chemical genetic screens"](http://dx.doi.org/10.1534/genetics.119.302299), and its [reproducible code](https://github.com/senresearch/mlm_gs_supplement) for more details. 
 
-[`MatrixLMnet`](https://github.com/senresearch/MatrixLMnet.jl) is a related package that implements algorithms for  L<sub>1</sub>-penalized estimates for matrix linear models. See the associated paper, ["Sparse matrix linear models for structured high-throughput data"](https://arxiv.org/abs/1712.05767), and its [reproducible code](https://github.com/senresearch/mlm_l1_supplement) for more details. 
+[`MatrixLMnet`](https://github.com/senresearch/MatrixLMnet.jl) is a related package that implements algorithms for  L1-penalized estimates for matrix linear models. See the associated paper, ["Sparse matrix linear models for structured high-throughput data"](https://arxiv.org/abs/1712.05767), and its [reproducible code](https://github.com/senresearch/mlm_l1_supplement) for more details. 
 
 ## Installation 
 
@@ -20,78 +27,43 @@ Pkg.add("MatrixLM")
 For the most recent version, use:
 ```
 using Pkg
-Pkg.add(url = "https://github.com/senresearch/MatrixLM.jl", rev="master")
+Pkg.add(url = "https://github.com/senresearch/MatrixLM.jl", rev="main")
 ```
-
-## Usage 
+Alternatively, you can also install `MatrixLM` from the julia REPL. Press `]` to enter pkg mode again, and enter the following:
 
 ```
-using MatrixLM
+add MatrixLM
 ```
 
-First, construct a `RawData` object consisting of the response variable `Y` and row/column predictors `X` and `Z`. All three matrices must be passed in as 2-dimensional arrays. Note that the `contr` function can be used to set up treatment and/or sum contrasts for categorical variables stored in a DataFrame. By default, `contr` generates treatment contrasts for all specified categorical variables (`"treat"`). Other options include `"sum"` for sum contrasts, `"noint"` for treatment contrasts with no intercept, and `"sumnoint"` for sum contrasts with no intercept. 
+## Contributing
 
-```
-using DataFrames
-using Random
-
-# Dimensions of matrices 
-n = 100
-m = 250
-# Number of column covariates
-q = 20
-
-# Randomly generate an X matrix of row covariates with 2 categorical variables
-# and 4 continuous variables
-Random.seed!(1)
-X_df = hcat(DataFrame(catvar1=rand(1:5, n), catvar2=rand(["A", "B", "C"], n)), 
-            DataFrame(rand(n,4)))
-# Use the contr function to get contrasts for the two categorical variables 
-# (treatment contrasts for catvar1 and sum contrasts for catvar2).
-# contr returns a DataFrame, so X needs to be converted into a 2d array.
-X = convert(Array{Float64,2}, contr(X_df, [:catvar1, :catvar2], 
-                                    ["treat", "sum"]))
-# Number of row covariates
-p = size(X)[2]
-
-# Randomly generate some data for column covariates Z and response variable Y
-Z = rand(m,q)
-B = rand(-5:5,p,q)
-E = randn(n,m)
-Y = X*B*transpose(Z)+E
-
-# Construct a RawData object
-dat = RawData(Response(Y), Predictors(X, Z))
-```
+We appreciate contributions from users including reporting bugs, fixing
+issues, improving performance and adding new features.
 
-Least-squares estimates for matrix linear models can be obtained by running `mlm`. An object of type `Mlm` will be returned, with variables for the coefficient estimates (`B`), the coefficient variance estimates (`varB`), and the estimated variance of the errors (`sigma`). By default, `mlm` estimates both row and column main effects (X and Z intercepts), but this behavior can be suppressed by setting `hasXIntercept=false` and/or `hasZIntercept=false`. Column weights for `Y` and the target type for variance shrinkage<sup>[1](#myfootnote1)</sup> can be optionally supplied to `weights` and `targetType`, respectively. 
 
-```
-est = mlm(dat)
-```
+## Questions
 
-The coefficient estimates can be accessed using `coef(est)`. Predicted values and residuals can be obtained by calling `predict` and `resid`. By default, both of these functions use the same data used to fit the model. However, a new `Predictors` object can be passed into `predict` as the `newPredictors` argument and a new `RawData` object can be passed into `resid` as the `newData` argument. For convenience, `fitted(est)` will return the fitted values by calling `predict` with the default arguments. 
+If you have questions about contributing or using `MatrixLM` package, please communicate author form github.
 
-```
-preds = predict(est)
-resids = resid(est)
-```
-
-The t-statistics for an `Mlm` object (defined as `est.B ./ sqrt.(est.varB)`) can be obtained by running `t_stat`. By default, `t_stat` does not return the corresponding t-statistics for any main effects that were estimated by `mlm`, but they will be returned if `isMainEff=true`. 
+## Citing `MatrixLM`
 
-```
-tStats = t_stat(est)
-```
+If you use `MatrixLM` in a scientific publication, please consider citing following paper:
 
-Permutation p-values for the t-statistics can be computed by the `mlm_perms` function. `mlm_perms` calls the more general function `perm_pvals` and will run the permutations in parallel when possible. The illustrative example below only runs 5 permutations, but a different number can be specified as the second argument. By default, the function used to permute `Y` is `shuffle_rows`, which shuffles the rows for `Y`. Alternative functions for permuting `Y`, such as `shuffle_cols`, can be passed into the argument `permFun`. `mlm_perms` calls `mlm` and `t_stat` , so the user is free to specify keyword arguments for `mlm` or `t_stat`; by default, `mlm_perms` will call both functions using their default behavior. 
+Jane W Liang, Robert J Nichols, Śaunak Sen, Matrix Linear Models for High-Throughput Chemical Genetic Screens, Genetics, Volume 212, Issue 4, 1 August 2019, Pages 1063–1073, https://doi.org/10.1534/genetics.119.302299
 
 ```
-nPerms = 5
-tStats, pVals = mlm_perms(dat, nPerms)
+@article{10.1534/genetics.119.302299,
+    author = {Liang, Jane W and Nichols, Robert J and Sen, Śaunak},
+    title = "{Matrix Linear Models for High-Throughput Chemical Genetic Screens}",
+    journal = {Genetics},
+    volume = {212},
+    number = {4},
+    pages = {1063-1073},
+    year = {2019},
+    month = {06},
+    issn = {1943-2631},
+    doi = {10.1534/genetics.119.302299},
+    url = {https://doi.org/10.1534/genetics.119.302299},
+    eprint = {https://academic.oup.com/genetics/article-pdf/212/4/1063/42105135/genetics1063.pdf},
+}
 ```
-
-Additional details can be found in the documentation for specific functions. 
-
----
-
-<a name="myfootnote1">1</a>. Ledoit, O., & Wolf, M. (2003). Improved estimation of the covariance matrix of stock returns with an application to portfolio selection. Journal of empirical finance, 10(5), 603-621. 

docs/Project.toml

@@ -0,0 +1,5 @@
+[deps]
+Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
+
+[compat]
+Documenter = "0.27"