Fix the Lint job, which is failing on main

.github/workflows/pr_code_changes.yaml

@@ -16,7 +16,7 @@ jobs:
         uses: astral-sh/setup-uv@v8.1.0
       - name: Install relevant dependencies
         run: |
-          uv pip install "ruff>=0.9.0" --system
+          uv pip install "ruff>=0.9.0,<0.17.0" --system
       - name: Check code formatting
         run: make check-format
 

changelog.d/lint-on-main.fixed.md

@@ -0,0 +1 @@
+Reformats five documentation files so the Lint job passes again, and bounds the ruff version the job installs.

docs/imputation-benchmarking/cross-validation.md

@@ -41,23 +41,23 @@ Returns a dictionary containing separate results for each metric type:
 ```python
 {
     "quantile_loss": {
-        "results": pd.DataFrame,      # rows: ["train", "test"], cols: quantiles (mean across folds)
+        "results": pd.DataFrame,  # rows: ["train", "test"], cols: quantiles (mean across folds)
         "results_std": pd.DataFrame,  # rows: ["train", "test"], cols: quantiles (std across folds)
         "mean_train": float,
         "mean_test": float,
         "std_train": float,
         "std_test": float,
-        "variables": List[str]        # numerical variables evaluated
+        "variables": List[str],  # numerical variables evaluated
     },
     "log_loss": {
-        "results": pd.DataFrame,      # rows: ["train", "test"], cols: quantiles
+        "results": pd.DataFrame,  # rows: ["train", "test"], cols: quantiles
         "results_std": pd.DataFrame,  # rows: ["train", "test"], cols: quantiles (std across folds)
         "mean_train": float,
         "mean_test": float,
         "std_train": float,
         "std_test": float,
-        "variables": List[str]        # categorical variables evaluated
-    }
+        "variables": List[str],  # categorical variables evaluated
+    },
 }
 ```
 
@@ -77,7 +77,7 @@ results = cross_validate_model(
     data=diabetes_df,
     predictors=["age", "sex", "bmi", "bp"],
     imputed_variables=["s1", "s4"],
-    n_splits=5
+    n_splits=5,
 )
 
 # Check performance for numerical variables

docs/imputation-benchmarking/preprocessing.md

@@ -117,10 +117,10 @@ result = autoimpute(
     predictors=["age", "education"],
     imputed_variables=["income", "wealth"],
     preprocessing={
-        "income": "log",       # Log transform (positive values only)
-        "wealth": "asinh",     # Asinh transform (handles zeros/negatives)
-        "age": "normalize"     # Z-score normalization
-    }
+        "income": "log",  # Log transform (positive values only)
+        "wealth": "asinh",  # Asinh transform (handles zeros/negatives)
+        "age": "normalize",  # Z-score normalization
+    },
 )
 ```
 

docs/imputation-benchmarking/visualizations.md

@@ -83,11 +83,7 @@ comparison_viz = method_comparison_results(
 )
 
 # Generate plot
-fig = comparison_viz.plot(
-    title="Method comparison",
-    show_mean=True,
-    plot_type="bar"
-)
+fig = comparison_viz.plot(title="Method comparison", show_mean=True, plot_type="bar")
 fig.show()
 
 # Get summary statistics
@@ -165,7 +161,7 @@ perf_viz = model_performance_results(
     results=cv_results,
     model_name="QRF",
     method_name="Cross-validation",
-    metric="quantile_loss"
+    metric="quantile_loss",
 )
 
 fig = perf_viz.plot(title="QRF performance")

docs/models/imputer/implement-new-model.md

@@ -73,9 +73,7 @@ class NewModelResults(ImputerResults):
 
         except Exception as e:
             self.logger.error(f"Error during Model prediction: {str(e)}")
-            raise RuntimeError(
-                f"Failed to predict with Model: {str(e)}"
-            ) from e
+            raise RuntimeError(f"Failed to predict with Model: {str(e)}") from e
 ```
 
 ## Implementing the main model class

docs/use_cases/index.md

@@ -23,27 +23,27 @@ Before imputation, make sure both datasets have compatible variables. Identify c
 
 ```python
 # Identify common variables
-common_variables = ['age', 'income', 'education', 'marital_status', 'region']
+common_variables = ["age", "income", "education", "marital_status", "region"]
 
 # Ensure variable formats match (example: education coding)
 education_mapping = {
     1: "less_than_hs",
     2: "high_school",
     3: "some_college",
     4: "bachelor",
-    5: "graduate"
+    5: "graduate",
 }
 
 # Apply standardization to both datasets
 for dataset in [scf_data, cps_data]:
-    dataset['education'] = dataset['education'].map(education_mapping)
+    dataset["education"] = dataset["education"].map(education_mapping)
 
     # Convert income to same units (thousands)
-    if 'income' in dataset.columns:
-        dataset['income'] = dataset['income'] / 1000
+    if "income" in dataset.columns:
+        dataset["income"] = dataset["income"] / 1000
 
 # Identify target variable in donor dataset
-target_variable = ['networth']
+target_variable = ["networth"]
 ```
 
 ## Performing imputation