Rename package and migrate to uv (#2)

* Rename Package to `torchTextClassifiers` and use uv to build and publish

Author: micedre

.github/workflows/python-package.yml

@@ -1,11 +1,11 @@
 # This workflow will install Python dependencies, run tests and lint with a variety of Python versions
 # For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
 
-name: Python package
+name: Python Tests
 
 on:
   push:
-    branches: [ "main" ]
+    branches: [ "main", "rename-package" ]
   pull_request:
     branches: [ "main" ]
 
@@ -16,25 +16,20 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [ "3.10", "3.11", "3.12"]
+        python-version: ["3.11", "3.12", "3.13"]
 
     steps:
     - uses: actions/checkout@v4
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        python -m pip install flake8 pytest
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-    - name: Test with pytest
-      run: |
-        pytest
+        version: 0.7.8
+        enable-cache: true
+        cache-dependency-glob: "uv.lock"
+    - name: Install the project
+      run: uv sync --locked --all-extras --dev
+
+    - name: Run tests
+        # For example, using `pytest`
+      run: uv run pytest tests

.github/workflows/python-publish.yml

@@ -16,33 +16,8 @@ permissions:
   contents: read
 
 jobs:
-  release-build:
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.x"
-
-      - name: Build release distributions
-        run: |
-          # NOTE: put your own distribution build steps here.
-          python -m pip install build poetry
-          poetry install
-          poetry build
-
-      - name: Upload distributions
-        uses: actions/upload-artifact@v4
-        with:
-          name: release-dists
-          path: dist/
-
   pypi-publish:
     runs-on: ubuntu-latest
-    needs:
-      - release-build
     permissions:
       # IMPORTANT: this permission is mandatory for trusted publishing
       id-token: write
@@ -59,13 +34,32 @@ jobs:
       # url: https://pypi.org/project/YOURPROJECT/${{ github.event.release.name }}
 
     steps:
-      - name: Retrieve release distributions
-        uses: actions/download-artifact@v4
-        with:
-          name: release-dists
-          path: dist/
+       - uses: actions/checkout@v4
+       - name: Install uv
+         uses: astral-sh/setup-uv@v5
+         with:
+          enable-cache: true
+          cache-dependency-glob: "uv.lock"
+          version: 0.7.8
+       
+       - name: Change Package Version
+         run: |
+          # Extract the tag name and remove the leading 'v'
+          TAG_NAME=${GITHUB_REF#refs/tags/v}
+          echo "Tag name: $TAG_NAME"
+
+          # Update the version in pyproject.toml
+          sed -i "s/\"0.0.0-dev\"/\"$TAG_NAME\"/" pyproject.toml
+
+          # Print the updated pyproject.toml file
+          cat pyproject.toml
+
+            
+       - name: Install build dependencies
+         run: uv sync --all-extras
+      
+       - name: Build the project
+         run: uv build
 
-      - name: Publish release distributions to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          packages-dir: dist/
+       - name: Publish to PyPI
+         run: uv publish

README.md

@@ -1,6 +1,6 @@
-# torchFastText : Efficient text classification with PyTorch
+# torchTextClassifiers : Efficient text classification with PyTorch
 
-A flexible PyTorch implementation of FastText for text classification with support for categorical features.
+A flexible PyTorch implementation of models for text classification with support for categorical features.
 
 ## Features
 
@@ -14,8 +14,17 @@ A flexible PyTorch implementation of FastText for text classification with suppo
 
 ## Installation
 
+- With `pip`:
+
+```bash
+pip install torchTextClassifiers
+```
+
+- with `uv`:
+
+
 ```bash
-pip install torchFastText
+uv add torchTextClassifiers
 ```
 
 ## Key Components
@@ -30,16 +39,16 @@ pip install torchFastText
 - `preprocess`: To preprocess text input, using `nltk` and `unidecode` libraries.
 - `explainability`: Simple methods to visualize feature attributions at word and letter levels, using `captum`library.
 
-Run `pip install torchFastText[preprocess]` or `pip install torchFastText[explainability]` to download these optional dependencies.
+Run `pip install torchTextClassifiers[preprocess]` or `pip install torchTextClassifiers[explainability]` to download these optional dependencies.
 
 
 ## Quick Start
 
 ```python
-from torchFastText import torchFastText
+from torchTextClassifiers import torchTextClassifiers
 
 # Initialize the model
-model = torchFastText(
+model = torchTextclassifiers(
     num_tokens=1000000,
     embedding_dim=100,
     min_count=5,

pyproject.toml

@@ -1,5 +1,5 @@
 [project]
-name = "torchFastText"
+name = "torchtextclassifiers"
 description = "An implementation of the https://github.com/facebookresearch/fastText supervised learning algorithm for text classification using Pytorch."
 authors = [
     { name = "Tom Seimandi", email = "tom.seimandi@gmail.com" },
@@ -8,7 +8,7 @@ authors = [
     { name = "Cédric Couralet", email = "cedric.couralet@insee.fr" },
 ]
 readme = "README.md"
-repository = "https://github.com/InseeFrLab/torch-fastText"
+repository = "https://github.com/InseeFrLab/torchTextClassifiers"
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: MIT License",
@@ -19,29 +19,35 @@ dependencies = [
     "numpy>=1.26.4",
     "pytorch-lightning>=2.4.0"
 ]
-requires-python = ">=3.10"
-dynamic = ["version"]
+requires-python = ">=3.11"
+version="0.0.0-dev"
 
 
+[dependency-groups]
+dev = [
+  "pytest >=8.1.1,<9",
+  "pandas",
+  "scikit-learn",
+  "nltk",
+  "unidecode",
+  "captum"
+]
+
 [project.optional-dependencies]
 explainability = ["unidecode", "nltk", "captum"]
 preprocess =     ["unidecode", "nltk"]
 
 [build-system]
-requires = ["poetry-core>=2.0.0"]
-build-backend = "poetry.core.masonry.api"
+requires = ["uv_build>=0.7.8,<0.8.0"]
+build-backend = "uv_build"
 
 [tool.ruff]
 line-length = 100
 
-[tool.poetry]
-version = "0.0.1-dev"  # base version
-packages = [{include = "torchFastText"}]
 
-[tool.poetry.requires-plugins]
-poetry-dynamic-versioning = { version = ">=1.0.0,<2.0.0", extras = ["plugin"] }
+[tool.uv.build-backend]
+module-name="torchTextClassifiers"
+module-root = ""
+
+
 
-[tool.poetry-dynamic-versioning]
-enable = true
-vcs = "git"
-style = "semver"

requirements.txt

@@ -7,9 +7,9 @@
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import LabelEncoder
 
-from torchFastText import torchFastText
-from torchFastText.preprocess import clean_text_feature
-from torchFastText.datasets import NGramTokenizer
+from torchTextClassifiers import torchTextClassifiers
+from torchTextClassifiers.preprocess import clean_text_feature
+from torchTextClassifiers.datasets import NGramTokenizer
 
 source_path = Path(__file__).resolve()
 source_dir = source_path.parent
@@ -111,7 +111,7 @@ def test_building(data):
     for vocab, cat_embedding_dim, num_cat in product(
         vocab_possible_values, cat_embedding_dim_possible_values, num_cat_possible_values
     ):
-        model = torchFastText(
+        model = torchTextClassifiers(
             num_tokens=num_tokens,
             num_rows=num_tokens,
             embedding_dim=embedding_dim,
@@ -152,7 +152,7 @@ def test_training(data):
         vocab_possible_values, cat_embedding_dim_possible_values, num_cat_possible_values
     ):
         print(vocab, cat_embedding_dim, num_cat)
-        model = torchFastText(
+        model = torchTextClassifiers(
             num_tokens=num_tokens,
             embedding_dim=embedding_dim,
             min_count=min_count,

tests/test_all.py

@@ -1,6 +1,6 @@
 import pytest
-from torchFastText.datasets.dataset import FastTextModelDataset
-from torchFastText.datasets.tokenizer import NGramTokenizer
+from torchTextClassifiers.datasets.dataset import FastTextModelDataset
+from torchTextClassifiers.datasets.tokenizer import NGramTokenizer
 
 
 @pytest.fixture

tests/test_fasttext_model_dataset.py

@@ -1,5 +1,5 @@
 import pytest
-from torchFastText.datasets.tokenizer import NGramTokenizer
+from torchTextClassifiers.datasets.tokenizer import NGramTokenizer
 
 
 def test_ngramtokenizer_init_valid():

tests/test_ngramtokenizer.py

@@ -0,0 +1 @@
+from .torchTextClassifiers import torchTextClassifiers as torchTextClassifiers