dependency update and the overall reanimation

Author: rssdev10

.github/workflows/CompatHelper.yml

@@ -3,14 +3,48 @@ on:
   schedule:
     - cron: 23 23 * * *
   workflow_dispatch:
+permissions:
+  contents: write
+  pull-requests: write
 jobs:
   CompatHelper:
     runs-on: ubuntu-latest
     steps:
-      - name: Pkg.add("CompatHelper")
-        run: julia -e 'using Pkg; Pkg.add("CompatHelper")'
-      - name: CompatHelper.main()
+      - name: Check if Julia is already available in the PATH
+        id: julia_in_path
+        run: which julia
+        continue-on-error: true
+      - name: Install Julia, but only if it is not already available in the PATH
+        uses: julia-actions/setup-julia@v2
+        with:
+          version: '1'
+          arch: ${{ runner.arch }}
+        if: steps.julia_in_path.outcome != 'success'
+      - name: "Add the General registry via Git"
+        run: |
+          import Pkg
+          ENV["JULIA_PKG_SERVER"] = ""
+          Pkg.Registry.add("General")
+        shell: julia --color=yes {0}
+      - name: "Install CompatHelper"
+        run: |
+          import Pkg
+          name = "CompatHelper"
+          uuid = "aa819f21-2bde-4658-8897-bab36330d9b7"
+          version = "3"
+          Pkg.add(; name, uuid, version)
+        shell: julia --color=yes {0}
+      - name: "Run CompatHelper"
+        run: |
+          import CompatHelper
+          CompatHelper.main()
+        shell: julia --color=yes {0}
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          # This repo uses Documenter, so we can reuse our [Documenter SSH key](https://documenter.juliadocs.org/stable/man/hosting/walkthrough/).
+          # If we didn't have one of those setup, we could configure a dedicated ssh deploy key `COMPATHELPER_PRIV` following https://juliaregistries.github.io/CompatHelper.jl/dev/#Creating-SSH-Key.
+          # Either way, we need an SSH key if we want the PRs that CompatHelper creates to be able to trigger CI workflows themselves.
+          # That is because GITHUB_TOKEN's can't trigger other workflows (see https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#using-the-github_token-in-a-workflow).
+          # Check if you have a deploy key setup using these docs: https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/reviewing-your-deploy-keys.
           COMPATHELPER_PRIV: ${{ secrets.DOCUMENTER_KEY }}
-        run: julia -e 'using CompatHelper; CompatHelper.main()'
+          # COMPATHELPER_PRIV: ${{ secrets.COMPATHELPER_PRIV }}

.github/workflows/TagBot.yml

@@ -4,6 +4,22 @@ on:
     types:
       - created
   workflow_dispatch:
+    inputs:
+      lookback:
+        default: 3
+permissions:
+  actions: read
+  checks: read
+  contents: write
+  deployments: read
+  issues: read
+  discussions: read
+  packages: read
+  pages: read
+  pull-requests: read
+  repository-projects: read
+  security-events: read
+  statuses: read
 jobs:
   TagBot:
     if: github.event_name == 'workflow_dispatch' || github.actor == 'JuliaTagBot'
@@ -12,3 +28,5 @@ jobs:
       - uses: JuliaRegistries/TagBot@v1
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
+          # Edit the following line to reflect the actual name of the GitHub Secret containing your private key
+          ssh: ${{ secrets.DOCUMENTER_KEY }}

.github/workflows/ci.yml

@@ -13,7 +13,8 @@ jobs:
     strategy:
       matrix:
         version:
-          - '1.6'
+          - '1.10'
+          - '1'
           - 'nightly'
         os:
           - ubuntu-latest
@@ -28,33 +29,67 @@ jobs:
           # MacOS not available on x86
           - {os: 'macOS-latest', arch: 'x86'}
           # Don't test on all versions
-          - {os: 'macOS-latest', version: '1.6'}
+          - {os: 'macOS-latest', version: '1.10'}
           - {os: 'macOS-latest', version: 'nightly'}
-          - {os: 'windows-latest', version: '1.6'}
+          - {os: 'windows-latest', version: '1.10'}
           - {os: 'windows-latest', version: 'nightly'}
           - {os: 'windows-latest', arch: 'x86'}
-          - {arch: 'x86', version: '1.6'}
+          - {arch: 'x86', version: '1.10'}
           - {arch: 'x86', version: 'nightly'}
     steps:
-      - uses: actions/checkout@v1
+      - uses: actions/checkout@v4
       - uses: julia-actions/setup-julia@latest
         with:
           version: ${{ matrix.version }}
           arch: ${{ matrix.arch }}
-      - uses: julia-actions/julia-buildpkg@latest
-      - uses: julia-actions/julia-runtest@latest
+      - uses: julia-actions/cache@v2
+      - name: Install dependencies
+        run: |
+          if [[ "${{ matrix.version }}" == "1" || "${{ matrix.version }}" == "nightly" ]]; then
+            # Julia 1.11+ - Install dependencies without any precompilation
+            julia --project=. -e 'using Pkg; Pkg.instantiate(; allow_autoprecomp=false)'
+          else
+            # Julia 1.10 and earlier work normally
+            julia --project=. -e 'using Pkg; Pkg.instantiate()'
+          fi
+        env:
+          JULIA_CUDA_USE_BINARYBUILDER: false
+          JULIA_PKG_PRECOMPILE_AUTO: 0
+        shell: bash
+      - name: Explicit precompilation
+        run: |
+          if [[ "${{ matrix.version }}" == "1" || "${{ matrix.version }}" == "nightly" ]]; then
+            # Julia 1.11+ - Minimal precompilation to avoid world age and segfault issues
+            echo "Skipping precompilation for Julia 1.11+ to avoid world age issues"
+          else
+            # Julia 1.10 - Precompile everything normally
+            julia --project=. -e 'using Pkg; Pkg.precompile()'
+          fi
+        env:
+          JULIA_CUDA_USE_BINARYBUILDER: false
+        shell: bash
+      - name: Run tests
+        run: |
+          if [[ "${{ matrix.version }}" == "1" || "${{ matrix.version }}" == "nightly" ]]; then
+            # Julia 1.11+ - Use minimal compilation and precompilation to avoid world age issues
+            julia --compiled-modules=no --pkgimages=no --color=yes --project=. -e 'using Pkg; Pkg.test()'
+          else
+            # Julia 1.10 and earlier can use normal compiled modules
+            julia --color=yes --project=. -e 'using Pkg; Pkg.test()'
+          fi
         env:
           DATADEPS_ALWAYS_ACCEPT: true
-        with:
-          coverage: false
+          JULIA_CUDA_USE_BINARYBUILDER: false
+          JULIA_PKG_PRECOMPILE_AUTO: 0
+        shell: bash
   docs:
     name: Documentation
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v1
+      - uses: actions/checkout@v4
       - uses: julia-actions/setup-julia@latest
         with:
-          version: '1.6'
+          version: '1.11'
       - run: julia --project=docs -e '
           using Pkg;
           Pkg.develop(PackageSpec(; path=pwd()));

Project.toml

@@ -2,7 +2,7 @@ name = "TextModels"
 uuid = "77b9cbda-2a23-51df-82a3-24144d1cd378"
 license = "MIT"
 desc = "Practical Neural Network based models for Natural Language Processing"
-version = "0.1.1"
+version = "0.2.0"
 
 [deps]
 BSON = "fbb218c0-5317-5bc6-957e-2ee96dd4b1f0"
@@ -12,6 +12,7 @@ DataDeps = "124859b0-ceae-595e-8997-d05f6a7a8dfe"
 DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
 DelimitedFiles = "8bb1440f-4735-579b-a4ab-409b98df4dab"
 Flux = "587475ba-b771-5e3f-ad9e-33799f191a9c"
+Functors = "d9f16b24-f501-4c13-a1f2-28368ffc5196"
 JSON = "682c06a0-de6a-54ab-a142-c8b1cf79cde6"
 Languages = "8ef0a80b-9436-5d2c-a485-80b904378c43"
 NNlib = "872c559c-99b0-510c-b3b7-b6c96a88d5cd"
@@ -24,19 +25,20 @@ WordTokenizers = "796a5d58-b03d-544a-977e-18100b691f6e"
 Zygote = "e88e6eb3-aa80-5325-afca-941959d7151f"
 
 [compat]
-BSON = "0.3.3"
-CUDA = "3"
+BSON = "0.3"
+CUDA = "3, 4, 5"
 CorpusLoaders = "0.3"
 DataDeps = "0.7"
-DataStructures = "0.18.9"
-Flux = "0.12.8"
-JSON = "0.21.1"
-Languages = "0.4.3"
-NNlib = "0.7"
-StatsBase = "0.33.6"
-TextAnalysis = "0.7.3"
-WordTokenizers = "0.5.6"
-Zygote = "0.6.10"
+DataStructures = "0.18, 0.19, 0.20"
+Flux = "0.16, 0.17"
+Functors = "0.4, 0.5, 0.6"
+JSON = "0.21, 0.22"
+Languages = "0.4"
+NNlib = "0.7, 0.8, 0.9, 0.10"
+StatsBase = "0.33, 0.34, 0.35"
+TextAnalysis = "0.8"
+WordTokenizers = "0.5, 0.6"
+Zygote = "0.7, 0.8"
 julia = "1.6"
 
 [extras]

docs/src/crf.md

@@ -5,7 +5,7 @@ This package currently provides support for Linear Chain Conditional Random Fiel
 Let us first load the dependencies-
 
     using Flux
-    using Flux: onehot, train!, Params, gradient, LSTM, Dense, reset!
+    using Flux: onehot, LSTM, Dense, reset!
     using TextModels: CRF, viterbi_decode, crf_loss
 
 Conditional Random Field layer is essentially like a softmax that operates on the top most layer.

docs/src/sentiment.md

@@ -27,7 +27,7 @@ A StringDocument{String}
 julia> m(d1)
 0.5183109f0
 
-julia> d = StringDocument("a horrible thing that everyone hates")
+julia> d2 = StringDocument("a horrible thing that everyone hates")
 A StringDocument{String}
  * Language: Languages.English()
  * Title: Untitled Document

docs/src/tagging.md

@@ -36,7 +36,7 @@ The pretrained model can also be loaded and can be used directly to predict tags
 
 ### To train model:
 ```julia
-julia> tagger = PerceptronTagger(false) #we can use tagger = PerceptronTagger()
+julia> tagger = TextModels.PerceptronTagger(false) #we can use tagger = TextModels.PerceptronTagger()
 julia> fit!(tagger, [[("today","NN"),("is","VBZ"),("good","JJ"),("day","NN")]])
 iteration : 1
 iteration : 2
@@ -47,7 +47,7 @@ iteration : 5
 
 ### To load pretrained model:
 ```julia
-julia> tagger = PerceptronTagger(true)
+julia> tagger = TextModels.PerceptronTagger(true)
 loaded successfully
 PerceptronTagger(AveragePerceptron(Set(Any["JJS", "NNP_VBZ", "NN_NNS", "CC", "NNP_NNS", "EX", "NNP_TO", "VBD_DT", "LS", ("Council", "NNP")  …  "NNPS", "NNP_LS", "VB", "NNS_NN", "NNP_SYM", "VBZ", "VBZ_JJ", "UH", "SYM", "NNP_NN", "CD"]), Dict{Any,Any}("i+2 word wetlands"=>Dict{Any,Any}("NNS"=>0.0,"JJ"=>0.0,"NN"=>0.0),"i-1 tag+i word NNP basic"=>Dict{Any,Any}("JJ"=>0.0,"IN"=>0.0),"i-1 tag+i word DT chloride"=>Dict{Any,Any}("JJ"=>0.0,"NN"=>0.0),"i-1 tag+i word NN choo"=>Dict{Any,Any}("NNP"=>0.0,"NN"=>0.0),"i+1 word antarctica"=>Dict{Any,Any}("FW"=>0.0,"NN"=>0.0),"i-1 tag+i word -START- appendix"=>Dict{Any,Any}("NNP"=>0.0,"NNPS"=>0.0,"NN"=>0.0),"i-1 word wahoo"=>Dict{Any,Any}("JJ"=>0.0,"VBD"=>0.0),"i-1 tag+i word DT children's"=>Dict{Any,Any}("NNS"=>0.0,"NN"=>0.0),"i word dnipropetrovsk"=>Dict{Any,Any}("NNP"=>0.003,"NN"=>-0.003),"i suffix hla"=>Dict{Any,Any}("JJ"=>0.0,"NN"=>0.0)…), DefaultDict{Any,Any,Int64}(), DefaultDict{Any,Any,Int64}(), 1, ["-START-", "-START2-"]), Dict{Any,Any}("is"=>"VBZ","at"=>"IN","a"=>"DT","and"=>"CC","for"=>"IN","by"=>"IN","Retrieved"=>"VBN","was"=>"VBD","He"=>"PRP","in"=>"IN"…), Set(Any["JJS", "NNP_VBZ", "NN_NNS", "CC", "NNP_NNS", "EX", "NNP_TO", "VBD_DT", "LS", ("Council", "NNP")  …  "NNPS", "NNP_LS", "VB", "NNS_NN", "NNP_SYM", "VBZ", "VBZ_JJ", "UH", "SYM", "NNP_NN", "CD"]), ["-START-", "-START2-"], ["-END-", "-END2-"], Any[])
 ```

src/CRF/crf.jl

@@ -25,7 +25,8 @@ function CRF(n::Integer)
     return CRF(W, n)
 end
 
-@functor CRF
+using Functors
+Functors.@functor CRF
 
 function Base.show(io::IO, c::CRF)
     print(io, "CRF with ", c.n + 2, " distinct tags (including START and STOP tags).")

src/CRF/loss.jl

@@ -25,11 +25,11 @@ thereby preventing operation.
 eltype(label_seq) = Flux.OneHotVector
 """
 function score_sequence(c::CRF, x, label_seq)
-    score = preds_first(c, label_seq[1]) + onecold(label_seq[1], x[1])
+    score = preds_first(c, label_seq[1]) + x[1][onecold(label_seq[1])]
 
     for i in 2:length(label_seq)
         score += preds_single(c, label_seq[i], label_seq[i-1]) +
-                    onecold(label_seq[i], x[i])
+                    x[i][onecold(label_seq[i])]
     end
 
     return score + preds_last(c, label_seq[end])

src/TextModels.jl

@@ -8,7 +8,8 @@ module TextModels
 
 
     using Flux, Zygote
-    using Flux: identity, onehot, onecold, @functor, onehotbatch
+    using Flux: identity, onehot, onecold, onehotbatch
+    using Functors
 
 
     using TextAnalysis
@@ -47,13 +48,15 @@ module TextModels
         using BSON
         using CorpusLoaders
         using DataDeps
+        using DelimitedFiles
         include("ULMFiT/utils.jl")
         include("ULMFiT/datadeps.jl")
         include("ULMFiT/data_loaders.jl")
         include("ULMFiT/custom_layers.jl")
         include("ULMFiT/pretrain_lm.jl")
         include("ULMFiT/fine_tune_lm.jl")
         include("ULMFiT/train_text_classifier.jl")
+        include("ULMFiT/sentiment.jl")
     end
     export ULMFiT