misc updates (#23)

.github/dependabot.yml

@@ -0,0 +1,7 @@
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "weekly"

.github/workflows/CI.yml

@@ -19,7 +19,7 @@ jobs:
       matrix:
         version:
           - '1.9'
-          - '1' # add back when 1.10 is out
+          - '1'
           - 'nightly'
         os:
           - ubuntu-latest
@@ -44,18 +44,19 @@ jobs:
     name: Documentation
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: julia-actions/setup-julia@v1
+      - uses: actions/checkout@v4.2.1
+      - uses: julia-actions/setup-julia@v2
         with:
           version: '1'
-      - uses: julia-actions/julia-buildpkg@v1
-      - uses: julia-actions/julia-docdeploy@v1
+      - run: |
+          julia --project=docs -e '
+            using Pkg
+            Pkg.develop(PackageSpec(path=pwd()))
+            Pkg.instantiate()'
+      - run: julia --color=yes --project=docs docs/make.jl
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           DOCUMENTER_KEY: ${{ secrets.DOCUMENTER_KEY }}
-      - run: |
-          julia --project=docs -e '
-            using Documenter: DocMeta, doctest
-            using HuggingFaceDatasets
-            DocMeta.setdocmeta!(HuggingFaceDatasets, :DocTestSetup, :(using HuggingFaceDatasets); recursive=true)
-            doctest(HuggingFaceDatasets)'
+          JULIA_CONDAPKG_OPENSSL_VERSION: "ignore"
+
+

.github/workflows/CompatHelper.yml

@@ -15,7 +15,7 @@ jobs:
         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@v1
+        uses: julia-actions/setup-julia@v2
         with:
           version: '1'
           arch: ${{ runner.arch }}
@@ -41,5 +41,10 @@ jobs:
         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 }}
           # COMPATHELPER_PRIV: ${{ secrets.COMPATHELPER_PRIV }}

.github/workflows/TagBot.yml

@@ -6,7 +6,7 @@ on:
   workflow_dispatch:
     inputs:
       lookback:
-        default: 3
+        default: "3"
 permissions:
   actions: read
   checks: read

CondaPkg.toml

@@ -1,10 +1,5 @@
-channels = ["conda-forge"]
-
 [deps]
-# h5py = ""
-# pillow = ">=9.1, <10"
-# pyarrow = "==6.0.0"
-datasets = ">=2.12, <3"
-numpy = ">=1.20, <2"
+datasets = ">=3.0, <4"
+numpy = ">=2.0, <3"
 pillow = ""
 

Project.toml

@@ -12,7 +12,7 @@ PythonCall = "6099a3de-0909-46bc-b1f4-468b9a2dfc0d"
 
 [compat]
 CondaPkg = "0.2"
-DLPack = "0.1"
+DLPack = "0.3"
 ImageCore = "0.9, 0.10"
 MLUtils = "0.4.1"
 PythonCall = "0.9"

README.md

@@ -23,31 +23,33 @@ HuggingFaceDatasets.jl provides wrappers around types from the `datasets` python
 Check out the [examples/](https://github.com/JuliaGenAI/HuggingFaceDatasets.jl/tree/main/examples) folder for usage examples.
 
 ```julia
+julia> using HuggingFaceDatasets
+
 julia> train_data = load_dataset("mnist", split = "train")
 Dataset({
     features: ['image', 'label'],
     num_rows: 60000
 })
 
-# Indexing starts with 1. 
-# Python types are returned by default.
 julia> train_data[1]
-Python: {'image': <PIL.PngImagePlugin.PngImageFile image mode=L size=28x28 at 0x7F04DE661CD0>, 'label': 5}
+Python: {'image': <PIL.PngImagePlugin.PngImageFile image mode=L size=28x28 at 0x3340B0290>, 'label': 5}
 
 julia> length(train_data)
 60000
 
-# Now we set the julia format
 julia> train_data = load_dataset("mnist", split = "train").with_format("julia");
 
-# Returned observations are now julia objects
-julia> train_data[1]
+julia> train_data[1] # Returned observations are now julia objects
 Dict{String, Any} with 2 entries:
   "label" => 5
-  "image" => Gray{N0f8}[Gray{N0f8}(0.0) Gray{N0f8}(0.0) … Gray{N0f8}(0.0) Gray{N0f8}(0.0); Gray{N0f8}(0.0) Gray{N0f8}(0.0) … Gray{N0f8}(0.0) Gray{N0f8}(0.0); … ; Gray{N0f8}(0.0) Gray{N0f8}(0.0) ……
+  "image" => Gray{N0f8}[0.0 0.0 … 0.0 0.0; 0.0 0.0 … 0.0 0.0; … ; 0.0 0.0 … 0.0 0.0; 0.0 0.0 … 0.0 0.0]
 
 julia> train_data[1:2]
 Dict{String, Vector} with 2 entries:
   "label" => [5, 0]
-  "image" => ReinterpretArray{Gray{N0f8}, 2, UInt8, Matrix{UInt8}, false}[[Gray{N0f8}(0.0) Gray{N0f8}(0.0) … Gray{N0f8}(0.0) Gray{N0f8}(0.0); Gray{N0f8}(0.0) Gray{N0f8}(0.0) … Gray{N0f8}(0.0) Gra…
+  "image" => ReinterpretArray{Gray{N0f8}, 2, UInt8, Matrix{UInt8}, false}[[0.0 0.0 … 0.0 0.0; 0.0 0.0 … 0.0 0.0; … ; 0…
 ```
+
+## Troubleshooting
+
+- If having problems in resolving the CondaPkg environment, try to set `ENV["JULIA_CONDAPKG_OPENSSL_VERSION"] = true`before loading the package. See more details [here](https://github.com/JuliaPy/CondaPkg.jl?tab=readme-ov-file#preferences)

docs/make.jl

@@ -15,6 +15,7 @@ makedocs(;
     ),
     pages=[
         "Home" => "index.md",
+        "API" => "api.md",
     ],
 )
 

docs/src/api.md

@@ -1,12 +1,9 @@
-# API
-
-## Index
-
-```@index
-Pages   = ["api.md"]
+```@meta
+CurrentModule = HuggingFaceDatasets
+CollapsedDocStrings = true
 ```
 
-## Docs
+# API
 
 ```@autodocs
 Modules = [HuggingFaceDatasets]

docs/src/index.md

@@ -26,26 +26,30 @@ HuggingFaceDatasets.jl provides wrappers around types from the `datasets` python
 Check out the `examples/` folder for usage examples.
 
 ```julia
+# Returned observations are now julia objects
+julia> using HuggingFaceDatasets
+
 julia> train_data = load_dataset("mnist", split = "train")
-Dataset(<py Dataset({
+Dataset({
     features: ['image', 'label'],
     num_rows: 60000
-})>, identity)
+})
 
-# Indexing starts with 1. 
-# By defaul, python types are returned.
 julia> train_data[1]
-Python dict: {'image': <PIL.PngImagePlugin.PngImageFile image mode=L size=28x28 at 0x2B64E2E90>, 'label': 5}
+Python: {'image': <PIL.PngImagePlugin.PngImageFile image mode=L size=28x28 at 0x3340B0290>, 'label': 5}
 
-julia> set_format!(train_data, "julia")
-Dataset(<py Dataset({
-    features: ['image', 'label'],
-    num_rows: 60000
-})>, HuggingFaceDatasets.py2jl)
+julia> length(train_data)
+60000
 
-# Now we have julia types
-julia> train_data[1]
+julia> train_data = load_dataset("mnist", split = "train").with_format("julia");
+
+julia> train_data[1] # Returned observations are now julia objects
 Dict{String, Any} with 2 entries:
   "label" => 5
-  "image" => UInt8[0x00 0x00 … 0x00 0x00; 0x00 0x00 … 0x00 0x00; … ; 0x00 0x00 … 0x00 0x00; 0x00 0x00 … 0x00 0x00]
+  "image" => Gray{N0f8}[0.0 0.0 … 0.0 0.0; 0.0 0.0 … 0.0 0.0; … ; 0.0 0.0 … 0.0 0.0; 0.0 0.0 … 0.0 0.0]
+
+julia> train_data[1:2]
+Dict{String, Vector} with 2 entries:
+  "label" => [5, 0]
+  "image" => ReinterpretArray{Gray{N0f8}, 2, UInt8, Matrix{UInt8}, false}[[0.0 0.0 … 0.0 0.0; 0.0 0.0 … 0.0 0.0; … ; 0…
 ```

src/HuggingFaceDatasets.jl

@@ -3,7 +3,7 @@ module HuggingFaceDatasets
 using PythonCall
 using MLUtils: getobs, numobs
 import MLUtils
-using DLPack
+using DLPack: DLPack
 using ImageCore
 
 const datasets = PythonCall.pynew()
@@ -37,8 +37,9 @@ include("load_dataset.jl")
 export load_dataset
 
 function __init__()
+    ENV["JULIA_CONDAPKG_OPENSSL_VERSION"] = "ignore"
     # Since it is illegal in PythonCall to import a python module in a module, we need to do this here.
-    # https://cjdoris.github.io/PythonCall.jl/dev/pythoncall-reference/#PythonCall.pycopy!
+    # https://juliapy.github.io/PythonCall.jl/dev/pythoncall-reference/#PythonCall.Core.pycopy!
     PythonCall.pycopy!(datasets, pyimport("datasets"))
     PythonCall.pycopy!(PIL, pyimport("PIL"))
     pyimport("PIL.PngImagePlugin")