rename to TmleCLI

.github/workflows/CI.yml

@@ -57,9 +57,9 @@ jobs:
       - run: |
           julia --project=docs -e '
             using Documenter: DocMeta, doctest
-            using TMLECLI
-            DocMeta.setdocmeta!(TMLECLI, :DocTestSetup, :(using TMLECLI); recursive=true)
-            doctest(TMLECLI)'
+            using TmleCLI
+            DocMeta.setdocmeta!(TmleCLI, :DocTestSetup, :(using TmleCLI); recursive=true)
+            doctest(TmleCLI)'
       - run: julia --project=docs docs/make.jl
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

Project.toml

@@ -1,4 +1,4 @@
-name = "TMLECLI"
+name = "TmleCLI"
 uuid = "2573d147-4098-46ba-9db2-8608d210ccac"
 authors = ["Olivier Labayle"]
 version = "0.9.0"
@@ -13,7 +13,6 @@ Configurations = "5218b696-f38b-4ac9-8b61-a12ec717816d"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 EvoTrees = "f6006082-12f8-11e9-0c9c-0d5d367ab1e5"
 GLMNet = "8d5ece8b-de18-5317-b113-243142960cc6"
-HDF5 = "f67ccb44-e63f-5c2f-98bd-6dc0ccc4ba2f"
 JLD2 = "033835bb-8acc-5ee8-8aae-3f567f8a3819"
 JSON = "682c06a0-de6a-54ab-a142-c8b1cf79cde6"
 MKL = "33e6dc65-8f57-5167-99aa-e5a354878fb2"
@@ -24,8 +23,6 @@ MLJModelInterface = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
 MLJModels = "d491faf4-2d78-11e9-2867-c94bc002c0b7"
 MLJXGBoostInterface = "54119dfa-1dab-4055-a167-80440f4f7a91"
 Mmap = "a63ad114-7e13-5084-954f-fe012c677804"
-MultipleTesting = "f8716d33-7c4a-5097-896f-ce0ecbd3ef6b"
-Optim = "429524aa-4258-5aef-a3af-852621145aeb"
 PackageCompiler = "9b87118b-4619-50d2-8e1e-99f35a4d4d9d"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 Serialization = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
@@ -52,9 +49,8 @@ MLJLinearModels = "0.10.0"
 MLJModelInterface = "1.8.0"
 MLJModels = "0.16, 0.17"
 MLJXGBoostInterface = "0.3.4"
-MultipleTesting = "0.6.0"
-Optim = "1.7"
 PackageCompiler = "2.1.16"
+TMLE = "0.17"
 Tables = "1.10.1"
 YAML = "0.4.9"
 julia = "1.10, 1"

README.md

@@ -1,8 +1,8 @@
-# TMLECLI
+# TmleCLI
 
-[![Stable](https://img.shields.io/badge/docs-stable-blue.svg)](https://targene.github.io/TMLE-CLI.jl/stable/)
-![GitHub Workflow Status (with branch)](https://img.shields.io/github/actions/workflow/status/TARGENE/TMLE-CLI.jl/CI.yml?branch=main)
-![Codecov](https://img.shields.io/codecov/c/github/TARGENE/TMLE-CLI.jl/main)
-![GitHub release (latest SemVer)](https://img.shields.io/github/v/release/TARGENE/TMLE-CLI.jl)
+[![Stable](https://img.shields.io/badge/docs-stable-blue.svg)](https://targene.github.io/TmleCLI.jl/stable/)
+![GitHub Workflow Status (with branch)](https://img.shields.io/github/actions/workflow/status/TARGENE/TmleCLI.jl/CI.yml?branch=main)
+![Codecov](https://img.shields.io/codecov/c/github/TARGENE/TmleCLI.jl/main)
+![GitHub release (latest SemVer)](https://img.shields.io/github/v/release/TARGENE/TmleCLI.jl)
 
 Command Line Interface for Targeted Minimum-Loss Estimation of causal effects on Tabular datasets.

deps/build_sysimage.jl

@@ -1,6 +1,6 @@
 using PackageCompiler
 PackageCompiler.create_sysimage(
-    ["TMLECLI"], 
+    ["TmleCLI"], 
     cpu_target="generic",
     sysimage_path="TMLESysimage.so", 
     precompile_execution_file="deps/execute.jl", 

deps/execute.jl

@@ -1,7 +1,7 @@
-using TMLECLI
+using TmleCLI
 
 @info "Running precompilation script."
 # Run workload
-TEST_DIR = joinpath(pkgdir(TMLECLI), "test")
+TEST_DIR = joinpath(pkgdir(TmleCLI), "test")
 push!(LOAD_PATH, TEST_DIR)
 include(joinpath(TEST_DIR, "runtests.jl"))

docker/Dockerfile

@@ -14,9 +14,9 @@ RUN bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)"
 
 # Import the project
 
-COPY . /TMLECLI.jl 
+COPY . /TmleCLI.jl 
 
-WORKDIR /TMLECLI.jl
+WORKDIR /TmleCLI.jl
 
 # Precompile the project
 RUN julia --project -e'using Pkg; Pkg.instantiate(); Pkg.resolve(); Pkg.precompile()'

docs/make.jl

@@ -1,18 +1,18 @@
 using Documenter
-using TMLECLI
+using TmleCLI
 
-DocMeta.setdocmeta!(TMLECLI, :DocTestSetup, :(using TMLECLI); recursive=true)
+DocMeta.setdocmeta!(TmleCLI, :DocTestSetup, :(using TmleCLI); recursive=true)
 
 makedocs(
     authors="Olivier Labayle",
-    repo="https://github.com/TARGENE/TMLE-CLI.jl/blob/{commit}{path}#{line}",
-    sitename = "TMLE-CLI.jl",
+    repo="https://github.com/TARGENE/TmleCLI.jl/blob/{commit}{path}#{line}",
+    sitename = "TmleCLI.jl",
     format = Documenter.HTML(;
         prettyurls=get(ENV, "CI", "false") == "true",
-        canonical="https://TARGENE.github.io/TMLE-CLI.jl",
+        canonical="https://TARGENE.github.io/TmleCLI.jl",
         assets=String["assets/logo.ico"],
     ),
-    modules = [TMLECLI],
+    modules = [TmleCLI],
     pages=[
         "Home" => "index.md",
         "Command Line Interface" => ["cli.md", "tmle_estimation.md", "sieve_variance.md", "make_summary.md"],
@@ -25,7 +25,7 @@ makedocs(
 
 @info "Deploying docs..."
 deploydocs(;
-    repo="github.com/TARGENE/TMLE-CLI.jl",
+    repo="github.com/TARGENE/TmleCLI.jl",
     devbranch="main",
     push_preview=true
 )

docs/src/index.md

@@ -1,4 +1,4 @@
-# TMLE-CLI.jl
+# TmleCLI.jl
 
 The goal of this package, is to provide a standalone executable to run large scale Targeted Minimum Loss-based Estimation ([TMLE](https://link.springer.com/book/10.1007/978-1-4419-9782-1)) on tabular datasets. To learn more about TMLE, please visit [TMLE.jl](https://targene.github.io/TMLE.jl/stable/), the companion package.
 

docs/src/models.md

@@ -1,7 +1,7 @@
 # Models
 
 ```@meta
-CurrentModule = TMLECLI
+CurrentModule = TmleCLI
 ```
 
 Because [TMLE.jl](https://targene.github.io/TMLE.jl/stable/) is based on top of [MLJ](https://alan-turing-institute.github.io/MLJ.jl/dev/), we can support any model respecting the MLJ interface. At the moment, we readily support all models from the following packages:
@@ -12,13 +12,13 @@ Because [TMLE.jl](https://targene.github.io/TMLE.jl/stable/) is based on top of
 - [GLMNet](https://github.com/JuliaStats/GLMNet.jl): A Julia wrapper of the [glmnet](https://glmnet.stanford.edu/articles/glmnet.html) package. See the [GLMNet](@ref) section.
 - [MLJModels](https://github.com/JuliaAI/MLJModels.jl): General utilities such as the `OneHotEncoder` or `InteractionTransformer`.
 
-Further support for more packages can be added on request, please fill an [issue](https://github.com/TARGENE/TMLE-CLI.jl/issues).
+Further support for more packages can be added on request, please fill an [issue](https://github.com/TARGENE/TmleCLI.jl/issues).
 
 Also, because the estimator file used by the TMLE CLI is a pure Julia file, it is possible to use it in order to install additional package that can be used to define additional models.
 
-Finally, we also provide some additional models described in [Additional models provided by TMLE-CLI.jl](@ref).
+Finally, we also provide some additional models described in [Additional models provided by TmleCLI.jl](@ref).
 
-## Additional models provided by TMLE-CLI.jl
+## Additional models provided by TmleCLI.jl
 
 ### GLMNet
 

docs/src/resampling.md

@@ -1,7 +1,7 @@
 # Resampling Strategies
 
 ```@meta
-CurrentModule = TMLECLI
+CurrentModule = TmleCLI
 ```
 
 We also provide additional resampling strategies compliant with the `MLJ.ResamplingStrategy` interface.

docs/src/tmle_estimation.md

@@ -124,7 +124,7 @@ Linear models typically do not involve any interaction terms. Here, to add extra
 
 ### Estimators Via A Julia File
 
-Building an estimator via a configuration string is quite flexible and should cover most use cases. However, in some cases you may want to have full control over the estimation procedure. This is possible by instead providing a Julia configuration file describing the estimators to be used. The file should define an `ESTIMATORS` NamedTuple describing the estimators to be used, and some examples can be found [here](https://github.com/TARGENE/TMLE-CLI.jl/tree/treatment_values/estimators-configs).
+Building an estimator via a configuration string is quite flexible and should cover most use cases. However, in some cases you may want to have full control over the estimation procedure. This is possible by instead providing a Julia configuration file describing the estimators to be used. The file should define an `ESTIMATORS` NamedTuple describing the estimators to be used, and some examples can be found [here](https://github.com/TARGENE/TmleCLI.jl/tree/treatment_values/estimators-configs).
 
 For further information, we recommend you have a look at both:
 
@@ -155,7 +155,7 @@ In what follows, `Y` is an outcome of interest, `W` a set of confounding variabl
 
 For all the following experiments:
 
-- The Julia script can be found at [experiments/runtime.jl](https://github.com/TARGENE/TMLE-CLI.jl/tree/main/experiments/runtime.jl).
+- The Julia script can be found at [experiments/runtime.jl](https://github.com/TARGENE/TmleCLI.jl/tree/main/experiments/runtime.jl).
 - The various estimators used below are further described in the[estimators-configs](https://github.com/TARGENE/TMLE.jl/tree/main/estimators-configs) folder.
 
 ### Multiple treatment contrasts

experiments/runtime.jl

@@ -1,5 +1,5 @@
 using ArgParse
-using TMLECLI
+using TmleCLI
 
 const ESTIMATORS = [
     "glm",
@@ -60,7 +60,7 @@ function main(parsed_args)
             "chunksize" => 100,
             "verbosity" => parsed_args["verbosity"],
         )
-        nparams = length(TMLECLI.parameters_from_yaml(paramfile))
+        nparams = length(TmleCLI.parameters_from_yaml(paramfile))
 
         # Time it: this will include precompilation time
         t_start = time()

src/TMLECLI.jl

@@ -1,4 +1,4 @@
-module TMLECLI
+module TmleCLI
 
 if occursin("Intel", Sys.cpu_info()[1].model)
     using MKL
@@ -20,7 +20,6 @@ using GLMNet
 using MLJModels
 using Mmap
 using Serialization
-using MultipleTesting
 using Combinatorics
 using Tables
 using Random

src/models/biallelic_snp_encoder.jl

@@ -59,7 +59,7 @@ function MLJModelInterface.transform(model::BiAllelicSNPEncoder, fitresult, X)
             ref_allele = fitresult[colname]
             newcoltype = Missing <: eltype(column) ? Union{Missing, Int} : Int
             newcolumn = Vector{newcoltype}(undef, size(column, 1))
-            TMLECLI.count_nref!(newcolumn, column, ref_allele)
+            TmleCLI.count_nref!(newcolumn, column, ref_allele)
         else
             newcolumn = column
         end

src/runner.jl

@@ -125,7 +125,7 @@ function (runner::Runner)(partition)
             continue
         end
         # Make sure data types are appropriate for the estimand
-        TMLECLI.coerce_types!(runner.dataset, Ψ)
+        TmleCLI.coerce_types!(runner.dataset, Ψ)
         # Maybe update cache with new η_spec
         estimators_results = []
         for estimator in runner.estimators

test/cache_managers.jl

@@ -1,21 +1,21 @@
 module TestRunner
 
-using TMLECLI
+using TmleCLI
 using Test
 using TMLE
 
 @testset "Test NoCacheManager" begin
-    cache_manager = TMLECLI.NoCacheManager()
+    cache_manager = TmleCLI.NoCacheManager()
     cache_manager.cache["Toto"] = 1
     cache_manager.cache["Tata"] = 2
-    TMLECLI.release!(cache_manager, nothing)
+    TmleCLI.release!(cache_manager, nothing)
     @test cache_manager.cache == Dict()
     # Check this does not throw
-    TMLECLI.release!(cache_manager, nothing)
+    TmleCLI.release!(cache_manager, nothing)
 end
 
 @testset "Test MaxSizeCacheManager" begin
-    cache_manager = TMLECLI.MaxSizeCacheManager(3)
+    cache_manager = TmleCLI.MaxSizeCacheManager(3)
     Y_T₁T₂ = TMLE.ConditionalDistribution(:Y, (:T₁, :T₂, :W))
     cache_manager.cache[Y_T₁T₂] = 1
     T₁_W = TMLE.ConditionalDistribution(:T₁, (:W,))
@@ -29,7 +29,7 @@ end
     cache_manager.cache[η] = 1
     cache_manager.cache[:last_fluctuation] = 1
     length(cache_manager.cache) == 5
-    TMLECLI.release!(cache_manager, nothing)
+    TmleCLI.release!(cache_manager, nothing)
     # CMRelevantFactors and fluctuation dropped
     @test cache_manager.cache == Dict(
         TMLE.ConditionalDistribution(:Y, (:T₁, :T₂, :W)) => 1,
@@ -62,7 +62,7 @@ end
         )
     ]
     η_counts = TMLE.nuisance_function_counts(estimands)
-    cache_manager = TMLECLI.ReleaseUnusableCacheManager(η_counts)
+    cache_manager = TmleCLI.ReleaseUnusableCacheManager(η_counts)
     # Estimation of the first estimand will fill the cache with the following
     Y_T₁T₂ = TMLE.ConditionalDistribution(:Y, (:T₁, :T₂, :W))
     cache_manager.cache[Y_T₁T₂] = 1
@@ -78,7 +78,7 @@ end
     cache_manager.cache[:last_fluctuation] = 1
     @test length(cache_manager.cache) == 5
     # After estimation of the first estimand, the fluctuation and composite factor are released
-    TMLECLI.release!(cache_manager, estimands[1])
+    TmleCLI.release!(cache_manager, estimands[1])
     @test cache_manager.cache == Dict(
         TMLE.ConditionalDistribution(:Y, (:T₁, :T₂, :W)) => 1,
         TMLE.ConditionalDistribution(:T₂, (:W,))         => 1,
@@ -89,7 +89,7 @@ end
     cache_manager.cache[η] = 1
     cache_manager.cache[:last_fluctuation] = 1
     # Y_T₁T₂ and T₂_W are no longer needed
-    TMLECLI.release!(cache_manager, estimands[2])
+    TmleCLI.release!(cache_manager, estimands[2])
     @test cache_manager.cache == Dict(TMLE.ConditionalDistribution(:T₁, (:W,)) => 1)
 
     # Estimation of the third estimand will fill the cache with the following
@@ -102,10 +102,10 @@ end
     cache_manager.cache[η] = 1
     cache_manager.cache[:last_fluctuation] = 1
     # Y_T₁ and T₁_W are no longer needed
-    TMLECLI.release!(cache_manager, estimands[3])
+    TmleCLI.release!(cache_manager, estimands[3])
     @test cache_manager.cache == Dict()
     # Check this does not throw
-    TMLECLI.release!(cache_manager, estimands[1])
+    TmleCLI.release!(cache_manager, estimands[1])
 end
 
 end

test/models/adaptive_interaction_transformer.jl

@@ -1,7 +1,7 @@
 module TestRestrictedInteractionTransformer
 
 using Test
-using TMLECLI
+using TmleCLI
 using Random
 using MLJBase
 using Tables
@@ -44,7 +44,7 @@ using Tables
     ]
     @test expected_interactions == interactions
     Xt = MLJBase.transform(mach, X)
-    feature_names = TMLECLI.feature_names(interactions)
+    feature_names = TmleCLI.feature_names(interactions)
     @test Tables.columnnames(Xt) == tuple(Tables.columnnames(X)..., feature_names...)
     @test Xt[Symbol("rs1234_&_sex_&_PC_2")] == X[:rs1234].*X[:sex].*X[:PC_2]
 
@@ -72,7 +72,7 @@ using Tables
     ]
     @test expected_interactions == interactions
     Xt = MLJBase.transform(mach, X)
-    feature_names = TMLECLI.feature_names(interactions)
+    feature_names = TmleCLI.feature_names(interactions)
     @test Tables.columnnames(Xt) == tuple(Tables.columnnames(X)..., feature_names...)
 
     # Test with both primary_variables and primary_variables_patterns
@@ -110,7 +110,7 @@ using Tables
     ]
     @test expected_interactions == interactions
     Xt = MLJBase.transform(mach, X)
-    feature_names = TMLECLI.feature_names(interactions)
+    feature_names = TmleCLI.feature_names(interactions)
     @test Tables.columnnames(Xt) == tuple(Tables.columnnames(X)..., feature_names...)
 
     # Invalid column
@@ -120,7 +120,7 @@ using Tables
         primary_variables=[:A, :B],
     )
     mach = machine(model, X, scitype_check_level=0)
-    @test_throws TMLECLI.InvalidColumnError("A") fit!(mach, verbosity=0)
+    @test_throws TmleCLI.InvalidColumnError("A") fit!(mach, verbosity=0)
 end
 
 end

test/models/biallelic_snp_encoder.jl

@@ -1,7 +1,7 @@
 module TestBiAllelelicSNPEncoder
 
 using Test
-using TMLECLI
+using TmleCLI
 using CategoricalArrays
 using MLJBase
 
@@ -28,21 +28,21 @@ using MLJBase
         othercol = [1, 2, 3, 4]
     )
     mach = machine(BiAllelicSNPEncoder(patterns=[r"^rs"]), X)
-    @test_throws TMLECLI.NonBiAllelicGenotypeError(:rs1234, "CCC") fit!(mach, verbosity=0)
+    @test_throws TmleCLI.NonBiAllelicGenotypeError(:rs1234, "CCC") fit!(mach, verbosity=0)
 
     X = (
         rs1234 = categorical(["AC", "CC", "CCT", missing]),
         othercol = [1, 2, 3, 4]
     )
     mach = machine(BiAllelicSNPEncoder(patterns=[r"^rs"]), X)
-    @test_throws TMLECLI.NonBiallelicSNPError(:rs1234) fit!(mach, verbosity=0)
+    @test_throws TmleCLI.NonBiallelicSNPError(:rs1234) fit!(mach, verbosity=0)
 
     X = (
         rs1234 = ["AC", "CC", "CCT", missing],
         othercol = [1, 2, 3, 4]
     )
     mach = machine(BiAllelicSNPEncoder(patterns=[r"^rs"]), X)
-    @test_throws TMLECLI.NonCategoricalVectorError(:rs1234) fit!(mach, verbosity=0)
+    @test_throws TmleCLI.NonCategoricalVectorError(:rs1234) fit!(mach, verbosity=0)
 
 
 end