fix: Resolve all ruff linting errors

- Remove unused variables in test files
- Fix undefined variable issue in catboost_wrapper.py
- Update pre-commit config to allow larger notebook files
- All pre-commit hooks now pass successfully

Author: deburky

pre-commit-config.yaml .pre-commit-config.yamlpre-commit-config.yaml renamed to .pre-commit-config.yaml

@@ -12,6 +12,7 @@ repos:
       - id: end-of-file-fixer
       - id: check-yaml
       - id: check-added-large-files
+        args: ['--maxkb=5000']  # Allow larger files for notebooks
       - id: check-merge-conflict
 
   - repo: https://github.com/astral-sh/ruff-pre-commit

LICENSE.md

@@ -18,4 +18,4 @@ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+SOFTWARE.

README.md

@@ -97,9 +97,9 @@ We can also visualize the score distribution between the events of interest.
 from xbooster import explainer
 
 explainer.plot_score_distribution(
-    y_test, 
+    y_test,
     credit_scores,
-    num_bins=30, 
+    num_bins=30,
     figsize=(8, 3),
     dpi=100
 )
@@ -156,7 +156,7 @@ print(f"Rule reduction: {len(xgb_scorecard_with_points)} → {len(interval_score
 print("\nInterval format:")
 print(interval_scorecard[['Feature', 'Bin', 'Points', 'WOE']].head())
 
-# Add Points at Even Odds/Points to Double the Odds (PEO/PDO) 
+# Add Points at Even Odds/Points to Double the Odds (PEO/PDO)
 peo_pdo_scorecard = scorecard_constructor.create_points_peo_pdo(peo=600, pdo=50)
 print("\nPEO/PDO Points:")
 print(peo_pdo_scorecard[['Feature', 'Bin', 'Points_PEO_PDO']].head())
@@ -194,8 +194,8 @@ target = "Loan_Status"
 
 # Initialize preprocessor
 preprocessor = DataPreprocessor(
-    numerical_features, 
-    categorical_features, 
+    numerical_features,
+    categorical_features,
     target
 )
 
@@ -204,7 +204,7 @@ X, y = preprocessor.fit_transform(dataset)
 
 # Get one-hot encoded feature names
 features_ohe = [
-    col for col in X.columns 
+    col for col in X.columns
     if col not in numerical_features
 ]
 
@@ -281,9 +281,9 @@ woe_scores = constructor.predict_score(X, method="woe")
 
 # Now create points for the scorecard
 scorecard_with_points = constructor.create_points(
-    pdo=50, 
-    target_points=600, 
-    target_odds=19, 
+    pdo=50,
+    target_points=600,
+    target_odds=19,
     precision_points=0
 )
 
@@ -529,4 +529,4 @@ For code contributions, please open a pull request.
 For a changelog, see [CHANGELOG](CHANGELOG.md).
 
 ## License 📄
-This project is licensed under the MIT License - see the LICENSE file for details.
+This project is licensed under the MIT License - see the LICENSE file for details.

examples/README.md

@@ -57,4 +57,4 @@ jupyter notebook
 
 3. Open the desired notebook and follow the instructions.
 
-Note: The examples use sample data and may need to be adapted for your specific use case. 
+Note: The examples use sample data and may need to be adapted for your specific use case.

examples/base-score.ipynb

@@ -181,7 +181,7 @@
    "source": [
     "import numpy as np\n",
     "import xgboost as xgb\n",
-    "from scipy.special import logit, expit\n",
+    "from scipy.special import expit\n",
     "\n",
     "\n",
     "def calculate_results_xbooster(booster, X, base_score, logit_scale=True):\n",

examples/catboost-getting-started.ipynb

@@ -426,8 +426,8 @@
     }
    ],
    "source": [
-    "import numpy as np\n",
     "from matplotlib import pyplot as plt\n",
+    "\n",
     "%config InlineBackend.figure_format = 'retina'\n",
     "\n",
     "fig = plt.figure(figsize=(8, 6), dpi=120)\n",
@@ -438,21 +438,9 @@
     "bins = np.linspace(score_min, score_max, 20)\n",
     "\n",
     "# plot score hist based on y == 1\n",
-    "ax.hist(\n",
-    "    points_scores[y == 1],\n",
-    "    bins=bins,\n",
-    "    color=\"blue\",\n",
-    "    alpha=0.5,\n",
-    "    label=\"Approved loans\"\n",
-    ")\n",
+    "ax.hist(points_scores[y == 1], bins=bins, color=\"blue\", alpha=0.5, label=\"Approved loans\")\n",
     "# plot score hist based on y == 0\n",
-    "ax.hist(\n",
-    "    points_scores[y == 0],\n",
-    "    bins=bins,\n",
-    "    color=\"red\",\n",
-    "    alpha=0.5,\n",
-    "    label=\"Declined loans\"\n",
-    ")\n",
+    "ax.hist(points_scores[y == 0], bins=bins, color=\"red\", alpha=0.5, label=\"Declined loans\")\n",
     "ax.set_xlabel(\"Credit Score\")\n",
     "ax.set_ylabel(\"Frequency\")\n",
     "ax.set_title(\"Credit Score Distribution\")\n",

examples/xgboost-categorical-data.ipynb

@@ -88,7 +88,6 @@
     }
    ],
    "source": [
-    "import numpy as np\n",
     "import xgboost as xgb\n",
     "from sklearn.metrics import roc_auc_score  # type: ignore\n",
     "\n",

examples/xgboost-getting-started.ipynb

@@ -57,7 +57,6 @@
     }
    ],
    "source": [
-    "import numpy as np\n",
     "import xgboost as xgb\n",
     "from sklearn.metrics import roc_auc_score\n",
     "\n",