ci(hooks): add pre-commit config with ruff and mypy hooks

.pre-commit-config.yaml

@@ -0,0 +1,15 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.15.7
+    hooks:
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.19.1
+    hooks:
+      - id: mypy
+        additional_dependencies: [pandas-stubs, pydantic>=2.5.0]
+        args: [--config-file=pyproject.toml]
+        pass_filenames: false
+        entry: mypy src/

app.py

@@ -12,5 +12,3 @@ safe_paragraph(
     "career stats to compete with a Computer",
     color="white",
 )
-
-

docs/plans/2026-03-25-audit-streamlit-nba/Phase-4.md

@@ -92,9 +92,9 @@ ci(deps): consolidate to pyproject.toml, remove requirements files
 - Note: Use the latest stable versions of ruff and mypy that are compatible. Check PyPI for current versions.
 
 **Verification Checklist:**
-- [ ] `.pre-commit-config.yaml` exists at project root
-- [ ] `pre-commit` is in dev dependencies
-- [ ] `uvx pre-commit run --all-files` passes
+- [x] `.pre-commit-config.yaml` exists at project root
+- [x] `pre-commit` is in dev dependencies
+- [x] `uvx pre-commit run --all-files` passes
 
 **Testing Instructions:** Run `uvx pre-commit run --all-files` and verify all hooks pass.
 

pages/1_home_team.py

@@ -25,6 +25,7 @@ configure_page()
 def _load_nba_data() -> pd.DataFrame:
     return load_data()
 
+
 # Initialize session state before any access
 init_session_state()
 
@@ -53,7 +54,9 @@ def find_player(search_term: str) -> list[str]:
     # Validate input
     validated_term = validate_search_term(search_term)
     if validated_term is None:
-        st.warning("Invalid search term. Please use only letters, numbers, and basic punctuation.")
+        st.warning(
+            "Invalid search term. Please use only letters, numbers, and basic punctuation."
+        )
         return []
 
     try:
@@ -104,7 +107,9 @@ home_team_df = find_home_team()
 
 # Combine search results with current team and current unsaved selections
 # This ensures that selections don't disappear when the search term changes
-current_team_names = home_team_df["FULL_NAME"].tolist() if not home_team_df.empty else []
+current_team_names = (
+    home_team_df["FULL_NAME"].tolist() if not home_team_df.empty else []
+)
 current_selections = st.session_state.get("player_selector", [])
 
 # Merge all into options list, maintaining uniqueness
@@ -125,7 +130,9 @@ def save_state() -> None:
 
 col1, col2 = st.columns([7, 1])
 with col1:
-    default_selection = home_team_df["FULL_NAME"].tolist() if not home_team_df.empty else []
+    default_selection = (
+        home_team_df["FULL_NAME"].tolist() if not home_team_df.empty else []
+    )
     player_selected = st.multiselect(
         "Search Results:",
         player_search,

pages/2_play_game.py

@@ -45,6 +45,7 @@ def _load_nba_data() -> pd.DataFrame:
 def _get_model():  # type: ignore[no-untyped-def]
     return get_winner_model()
 
+
 # Initialize session state BEFORE any access
 init_session_state()
 
@@ -135,7 +136,10 @@ if home_team_df.empty or home_team_df.shape[0] != TEAM_SIZE:
     box_score = pd.DataFrame()
 else:
     # Only generate away team if we don't have one or it's empty
-    if st.session_state.get("away_team_df") is None or st.session_state.away_team_df.empty:
+    if (
+        st.session_state.get("away_team_df") is None
+        or st.session_state.away_team_df.empty
+    ):
         st.session_state.away_team_df = find_away_team(stats)
 
     away_data = st.session_state.away_team_df
@@ -207,9 +211,11 @@ if teams_good and winner_label:
 safe_heading("Away Team", level=1, color="steelblue")
 st.dataframe(st.session_state.away_team_df)
 
+
 def play_new_team() -> None:
     """Clear cached away team and rerun."""
     logger.info("New Team requested")
     st.session_state.away_team_df = pd.DataFrame()
 
+
 st.button("Play New Team", on_click=play_new_team)

pyproject.toml

@@ -19,6 +19,7 @@ dev = [
     "mypy>=1.7.0",
     "ruff>=0.1.6",
     "pandas-stubs>=2.0.0",
+    "pre-commit>=3.0.0",
 ]
 
 [tool.mypy]

scripts/compile_model.py

@@ -70,9 +70,7 @@ EPOCHS: list[int] = [500, 1000, 1500]
 BATCH_SIZES: list[int] = [50, 100, 200]
 
 
-def create_stats(
-    roster: pd.DataFrame, schedule: pd.DataFrame
-) -> list[np.ndarray]:
+def create_stats(roster: pd.DataFrame, schedule: pd.DataFrame) -> list[np.ndarray]:
     """Create feature arrays from roster and schedule data.
 
     Args:

src/config.py

@@ -91,7 +91,6 @@ def setup_logging(level: int = logging.INFO) -> logging.Logger:
     return logger
 
 
-
 def configure_page() -> None:
     """Configure Streamlit page settings and logging."""
     setup_logging()

src/database/queries.py

@@ -30,9 +30,7 @@ def search_player_by_name(df: pd.DataFrame, name: str) -> list[tuple[str]]:
     return [(player_name,) for player_name in results]
 
 
-def get_players_by_full_names(
-    df: pd.DataFrame, names: list[str]
-) -> pd.DataFrame:
+def get_players_by_full_names(df: pd.DataFrame, names: list[str]) -> pd.DataFrame:
     """Get multiple players' records in a single batch query.
 
     Args:

src/ml/model.py

@@ -64,9 +64,7 @@ def predict_winner(combined_stats: np.ndarray) -> tuple[float, int]:
         ValueError: If input shape is invalid
     """
     if combined_stats.shape != (1, 100):
-        raise ValueError(
-            f"Expected input shape (1, 100), got {combined_stats.shape}"
-        )
+        raise ValueError(f"Expected input shape (1, 100), got {combined_stats.shape}")
 
     model = get_winner_model()
     sigmoid_output = model.predict(combined_stats, verbose=0)

src/utils/html.py

@@ -64,7 +64,6 @@ def safe_paragraph(
     safe_align = escape_html(align)
 
     st.markdown(
-        f"<p style='text-align: {safe_align}; color: {safe_color};'>"
-        f"{safe_text}</p>",
+        f"<p style='text-align: {safe_align}; color: {safe_color};'>{safe_text}</p>",
         unsafe_allow_html=True,
     )

tests/test_database.py

@@ -47,7 +47,9 @@ class TestLoadData:
     @patch("src.database.connection.pd.read_csv")
     @patch("src.database.connection.CSV_PATH")
     def test_load_data_parser_error_raises_connection_error(
-        self, mock_path, mock_read_csv  # type: ignore[no-untyped-def]
+        self,
+        mock_path,
+        mock_read_csv,  # type: ignore[no-untyped-def]
     ) -> None:
         """Test that CSV parse errors raise DatabaseConnectionError."""
         mock_path.exists.return_value = True
@@ -120,10 +122,12 @@ class TestGetAwayTeamByStats:
     def test_max_attempts_raises_error(self) -> None:
         """Test that max_attempts limit works when population is too small."""
         # Create a DF with only 2 players
-        df = pd.DataFrame([
-            {"FULL_NAME": "P1", "PTS": 1001, "REB": 501, "AST": 301, "STL": 101},
-            {"FULL_NAME": "P2", "PTS": 1001, "REB": 501, "AST": 301, "STL": 101},
-        ])
+        df = pd.DataFrame(
+            [
+                {"FULL_NAME": "P1", "PTS": 1001, "REB": 501, "AST": 301, "STL": 101},
+                {"FULL_NAME": "P2", "PTS": 1001, "REB": 501, "AST": 301, "STL": 101},
+            ]
+        )
         # Add missing columns to avoid errors if needed, though queries only use these
         for col in PLAYER_COLUMNS:
             if col not in df.columns:
@@ -146,10 +150,15 @@ class TestGetAwayTeamByStats:
         # Create a DF with 10 players meeting criteria
         data = []
         for i in range(10):
-            data.append({
-                "FULL_NAME": f"Player{i}",
-                "PTS": 2000, "REB": 1000, "AST": 500, "STL": 200
-            })
+            data.append(
+                {
+                    "FULL_NAME": f"Player{i}",
+                    "PTS": 2000,
+                    "REB": 1000,
+                    "AST": 500,
+                    "STL": 200,
+                }
+            )
         df = pd.DataFrame(data)
         for col in PLAYER_COLUMNS:
             if col not in df.columns:

tests/test_ml.py

@@ -32,9 +32,7 @@ class TestAnalyzeTeamStats:
         home_stats = [[float(i * 10 + j) for j in range(10)] for i in range(5)]
         away_stats = [[float(50 + i * 10 + j) for j in range(10)] for i in range(5)]
 
-        _home_array, _away_array, combined = analyze_team_stats(
-            home_stats, away_stats
-        )
+        _home_array, _away_array, combined = analyze_team_stats(home_stats, away_stats)
 
         # Combined should have 100 values: 50 home + 50 away
         assert combined.shape == (1, 100)
@@ -100,9 +98,7 @@ class TestPredictWinner:
         assert prediction in (0, 1)
 
     @patch("src.ml.model.get_winner_model")
-    def test_high_probability_predicts_win(
-        self, mock_get_model: MagicMock
-    ) -> None:
+    def test_high_probability_predicts_win(self, mock_get_model: MagicMock) -> None:
         """Test that high probability (>0.5) predicts home win (1)."""
         mock_model = MagicMock()
         mock_model.predict.return_value = np.array([[0.8]])
@@ -115,9 +111,7 @@ class TestPredictWinner:
         assert prediction == 1
 
     @patch("src.ml.model.get_winner_model")
-    def test_low_probability_predicts_loss(
-        self, mock_get_model: MagicMock
-    ) -> None:
+    def test_low_probability_predicts_loss(self, mock_get_model: MagicMock) -> None:
         """Test that low probability (<0.5) predicts home loss (0)."""
         mock_model = MagicMock()
         mock_model.predict.return_value = np.array([[0.3]])
@@ -130,9 +124,7 @@ class TestPredictWinner:
         assert prediction == 0
 
     @patch("src.ml.model.get_winner_model")
-    def test_invalid_shape_raises_error(
-        self, mock_get_model: MagicMock
-    ) -> None:
+    def test_invalid_shape_raises_error(self, mock_get_model: MagicMock) -> None:
         """Test that invalid input shape raises ValueError."""
         mock_model = MagicMock()
         mock_get_model.return_value = mock_model
@@ -146,9 +138,7 @@ class TestPredictWinner:
         assert "Expected input shape (1, 100)" in str(exc_info.value)
 
     @patch("src.ml.model.get_winner_model")
-    def test_model_called_with_verbose_zero(
-        self, mock_get_model: MagicMock
-    ) -> None:
+    def test_model_called_with_verbose_zero(self, mock_get_model: MagicMock) -> None:
         """Test that model.predict is called with verbose=0."""
         mock_model = MagicMock()
         mock_model.predict.return_value = np.array([[0.5]])