migrate to uv and ruff

.github/workflows/publish.yml

@@ -9,8 +9,14 @@ jobs:
     runs-on: ubuntu-latest
     if: github.event_name == 'release'
     steps:
-    - uses: actions/checkout@v3
-    - name: Publish to pypi
-      uses: JRubics/poetry-publish@v1.16
-      with:
-        pypi_token: ${{ secrets.PYPI_TOKEN }}
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Build
+        run: uv build
+
+      - name: Publish to pypi
+        run: uv publish --token ${{ secrets.PYPI_TOKEN }}

.github/workflows/test.yml

@@ -8,40 +8,22 @@ jobs:
 
     strategy:
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.12"]
 
     steps:
-      - name: Set up python
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-
       - name: Check out repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
         with:
-          virtualenvs-create: true
-          virtualenvs-in-project: true
-          installer-parallel: true
-
-      - name: Load cached venv
-        id: cached-poetry-dependencies
-        uses: actions/cache@v3
-        with:
-          path: .venv
-          key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}
+          python-version: ${{ matrix.python-version }}
 
       - name: Install dependencies
-        if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-        run: poetry install --no-interaction --no-root
-
-      - name: Install project
-        run: poetry install --no-interaction
+        run: uv sync
 
       - name: Lint
-        run: make pysen-lint
+        run: make lint
 
       - name: Test
-        run: make pytest
+        run: make test

Dockerfile

@@ -1,14 +1,8 @@
-FROM ubuntu:22.04
-
-RUN apt update -y \
-    && apt install -y python3 python3-dev python3-pip \
-    && rm -rf /var/lib/apt/lists
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm
 
 WORKDIR /work
-COPY pyproject.toml poetry.lock ./
+COPY pyproject.toml uv.lock ./
 
-RUN pip3 install -U pip \
-    && pip3 install poetry \
-    && poetry install
+RUN uv sync --frozen --no-install-project
 
 CMD ["/bin/bash"]

Makefile

@@ -15,11 +15,14 @@ remove-image:
 remove-container:
 	docker rm -f $(CONTAINER_NAME)
 
-pytest:
-	env PYTHONPATH=. poetry run pytest -vv
+test:
+	uv run pytest -vv
 
-pysen-lint:
-	poetry run pysen run lint
+lint:
+	uv run ruff check .
+	uv run ruff format --check .
+	uv run mypy
 
-pysen-format:
-	poetry run pysen run format
+format:
+	uv run ruff check --fix .
+	uv run ruff format .

ncnc/c_value.py

@@ -3,9 +3,10 @@
 from typing import List
 
 import pandas as pd
-from ncnc.logging import logger
 from tqdm import tqdm
 
+from ncnc.logging import logger
+
 
 def calc_c_value(df: pd.DataFrame) -> pd.DataFrame:
     ngrams = df.index.values

ncnc/nc_value.py

@@ -2,9 +2,10 @@
 from typing import Dict
 
 import pandas as pd
-from ncnc.logging import logger
 from tqdm import tqdm
 
+from ncnc.logging import logger
+
 
 def calc_nc_value(df: pd.DataFrame, n: int = 100) -> pd.DataFrame:
     logger.info('started setting df["nc-value"]')
@@ -20,7 +21,8 @@ def _extract_context(df: pd.DataFrame, n: int = 100) -> Dict[str, float]:
 
     n = min(n, len(df))
 
-    # use the top candidate terms from the C-value list as pseudo real terms (see 3.4 in the paper)
+    # use the top candidate terms from the C-value list as pseudo real terms
+    # (see 3.4 in the paper)
     df = df.sort_values(by="c-value", ascending=False)[:n]
 
     # ngram => "basal cell carcinoma"
@@ -67,7 +69,7 @@ def _extract_context(df: pd.DataFrame, n: int = 100) -> Dict[str, float]:
     return context_to_weight
 
 
-def replaced_string(match: re.Match) -> str:
+def replaced_string(match: re.Match[str]) -> str:
     if not match.group(0).startswith(" "):
         return "[term] "
     elif not match.group(0).endswith(" "):