Add UP007 back in, and fix a few more things, and update git workflows

Author: cleong110

.github/workflows/lint.yaml

@@ -1,26 +1,32 @@
-name: Lint
-
+name: Lint and Format
 
 on:
   push:
     branches: [ master, main ]
   pull_request:
     branches: [ master, main ]
 
-
 jobs:
-  test:
-    name: Lint
+  lint-and-format:
+    name: Lint and Format Check
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
+      - name: Checkout code
+        uses: actions/checkout@v4 # Use the latest stable version
+
+      - name: Set up Python
+        uses: actions/setup-python@v5 # Use the latest stable version
         with:
-          python-version: '3.12'
+          python-version: '3.12' # Specify your Python version
+
+      - name: Install Ruff
+        run: pip install ruff
 
-      - name: Install Requirements
-        run: pip install .[dev]
+      - name: Run Ruff Checks (Linting)
+        run: ruff check pose_evaluation
 
-      - name: Lint Code
-        run: pylint pose_evaluation
+      - name: Run Ruff Format Check
+        # The --check flag makes 'ruff format' exit with a non-zero code if files are not formatted,
+        # ensuring the CI pipeline fails.
+        run: ruff format pose_evaluation --check

.github/workflows/test.yaml

@@ -1,26 +1,30 @@
 name: Test
 
-
 on:
   push:
     branches: [ master, main ]
   pull_request:
     branches: [ master, main ]
 
-
 jobs:
   test:
-    name: Test
+    name: Run Tests
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
+      - name: Checkout code
+        uses: actions/checkout@v4 # Recommended: uses latest stable v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5 # Recommended: uses latest stable v5
         with:
           python-version: '3.12'
+          cache: 'pip' # Enable pip caching
 
-      - name: Install Requirements
+      - name: Install Dependencies
+        # This will install your project in editable mode and its dev dependencies,
+        # leveraging the pip cache if available.
         run: pip install .[dev]
 
-      - name: Test Code
-        run: pytest pose_evaluation
+      - name: Run Pytest on pose_evaluation
+        run: pytest pose_evaluation

.pre-commit-config.yaml

@@ -1,15 +1,20 @@
 files: ^pose_evaluation/
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.13 # Or the latest stable version
+    # Ruff version.
+    rev: v0.11.13
     hooks:
-      - id: ruff
-        args: [--fix] # This includes formatting and many linting fixes
+      # Run the linter.
+      - id: ruff-check
+        args: [--fix]
+      # Run the formatter.
+      - id: ruff-format
 
   - repo: local
     hooks:
       - id: pytest
         name: pytest
-        entry: pytest pose_evaluation
+        entry: pytest # Just 'pytest'
         language: system
-        types: [python]
+        types: [python]
+        pass_filenames: false

pose_evaluation/analysis/explore_metric_stats.py

@@ -91,7 +91,8 @@ def plot_pareto_frontier(df: pd.DataFrame):
                     ),
                     hovertemplate=f"{DESCRIPTIVE_NAME_COL}: %{{customdata[0]}}<br>"
                     #   f"{'METRIC: %{{customdata[1]}}<br>' if METRIC_COL in group else ''}"
-                    f"{METRIC_COL}: %{{customdata[1]}}<br>" f"{col1}: %{{x:.3f}}<br>{col2}: %{{y:.3f}}<extra></extra>",
+                    f"{METRIC_COL}: %{{customdata[1]}}<br>"
+                    f"{col1}: %{{x:.3f}}<br>{col2}: %{{y:.3f}}<extra></extra>",
                 )
             )
     else:

pose_evaluation/evaluation/combine_semantic_and_lookalike.py

@@ -94,17 +94,13 @@ def find_weird(df: pd.DataFrame, cols: list, source: str):
     # ASL-Lex Vocabulary for compatibility
     # Remove underscores unless they are immediately before digits at the end
     sem_related_df["subject"] = (
-        sem_related_df["subject"]
-        .str.replace("asllex:", "", regex=False)
-        .str.replace("#", "", regex=False)
+        sem_related_df["subject"].str.replace("asllex:", "", regex=False).str.replace("#", "", regex=False)
         # .str.upper()
         # .str.replace(r"_(?!\d+$)", "", regex=True)
     )
 
     sem_related_df["object"] = (
-        sem_related_df["object"]
-        .str.replace("asllex:", "", regex=False)
-        .str.replace("#", "", regex=False)
+        sem_related_df["object"].str.replace("asllex:", "", regex=False).str.replace("#", "", regex=False)
         # .str.upper()
         # .str.replace(r"_(?!\d+$)", "", regex=True)  # oh_i_see -> ohisee, but FISHING_2 left unchanged
     )

pose_evaluation/evaluation/create_metrics.py

@@ -10,7 +10,7 @@
 import itertools
 import re
 from pathlib import Path
-from typing import Literal, Optional
+from typing import Literal
 
 import pandas as pd
 
@@ -123,9 +123,9 @@ def construct_metric(
     # Default Distances
     name_pieces.append(f"defaultdist{default_distance}")
     distance_measure.set_default_distance(default_distance)
-    assert (
-        f"default_distance:{default_distance}" in distance_measure.get_signature().format()
-    ), f"{distance_measure.default_distance}, {default_distance}"
+    assert f"default_distance:{default_distance}" in distance_measure.get_signature().format(), (
+        f"{distance_measure.default_distance}, {default_distance}"
+    )
 
     ##########################################
     # FPS Strategy
@@ -182,7 +182,7 @@ def get_embedding_metrics(df: pd.DataFrame) -> list:
 def get_metrics(
     measures: list[DistanceMeasure] | None = None,
     include_return4=True,
-    metrics_out: Optional[Path] = None,
+    metrics_out: Path | None = None,
     include_masked: bool | None = False,
 ):
     metrics = []

pose_evaluation/evaluation/filter_parquets.py

@@ -18,7 +18,7 @@ def filter_parquet_files(
     glosses_to_include: str = typer.Option(..., help="Comma-separated list of glosses to include"),
     report_path: Path = typer.Option(None, help="Optional path to save a JSON report"),
 ):
-    glosses_set = set(g.strip().upper() for g in glosses_to_include.split(","))
+    glosses_set = {g.strip().upper() for g in glosses_to_include.split(",")}
     typer.echo(f"📂 Input path: {in_path}")
     typer.echo(f"📁 Output path: {out_path}")
     typer.echo(f"📌 Glosses to include: {len(glosses_set)}")
@@ -27,7 +27,7 @@ def filter_parquet_files(
     parquet_files = sorted(in_path.glob("*.parquet"))
     typer.echo(f"📁 Parquets found: {len(parquet_files)}")
 
-    # 1–3: Build metric → set of glosses
+    # 1-3: Build metric → set of glosses
     metric_to_glosses = defaultdict(set)
     gloss_to_files = defaultdict(list)
 

pose_evaluation/evaluation/knn_eval.py

@@ -199,9 +199,9 @@ def get_metric_filtered_datasets(
         else:
             try:
                 selected_metrics = [metric_values[int(choice) - 1]]
-            except (ValueError, IndexError) as e: # Catch the original exception as 'e' (or 'err')
+            except (ValueError, IndexError) as e:  # Catch the original exception as 'e' (or 'err')
                 typer.echo("Invalid selection.")
-                raise typer.Exit(code=1) from e # Chain the new exception to the original one
+                raise typer.Exit(code=1) from e  # Chain the new exception to the original one
     else:
         if metric == "all":
             selected_metrics = metric_values