DOCS: Fix precommit regex statement, and lint remaining tabular examp…

…les (#3298)

* Fixup precommit regex pattern

* Lint two remaining notebooks

* Minimally fixup Boston Demo, ignore undefined variable

* Simplify regex exclude pattern

---------

Co-authored-by: Jeremy Goh <30731072+thatlittleboy@users.noreply.github.com>

.pre-commit-config.yaml

@@ -1,6 +1,7 @@
 ci:
   autoupdate_schedule: monthly
 
+exclude: '.*tree_shap_paper.*|.*user_studies.*'
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
   rev: v0.0.292
@@ -30,14 +31,14 @@ repos:
   hooks:
   - id: black-jupyter
     name: black (fixed notebooks)
-    # This YAML anchor selects which notebooks are linted with ruff and black.
-    # Add a notebook here once it has been cleaned up.
+    # This regular expression selects which notebooks are linted with ruff and black.
+    # Add a notebook (or directory of notebooks) here once it has been cleaned up.
     files: &cleanNotebooks |
             (?x)^(
                 notebooks/api_examples/.*.ipynb|
                 notebooks/benchmarks/.*.ipynb|
                 notebooks/genomic_examples/.*.ipynb|
-                notebooks/tabular_examples/(?!.*tree_shap_paper).ipynb|
+                notebooks/tabular_examples/.*.ipynb|
             )$
 - repo: https://github.com/astral-sh/ruff-pre-commit
   rev: v0.0.292
@@ -46,3 +47,4 @@ repos:
     name: ruff (fixed notebooks)
     types_or: [jupyter]
     files: *cleanNotebooks
+    args: [ --fix, --exit-non-zero-on-fix ]

notebooks/tabular_examples/tree_based_models/Front page example (XGBoost).ipynb

@@ -32,7 +32,7 @@
     "import shap\n",
     "\n",
     "# train XGBoost model\n",
-    "X,y = shap.datasets.boston()\n",
+    "X, y = shap.datasets.boston()\n",
     "model = xgboost.XGBRegressor(max_depth=1).fit(X, y)\n",
     "\n",
     "# explain the model's predictions using SHAP values\n",
@@ -72,14 +72,18 @@
     "import shap\n",
     "\n",
     "# train XGBoost model\n",
-    "X,y = shap.datasets.adult()\n",
+    "X, y = shap.datasets.adult()\n",
     "model = xgboost.XGBClassifier(max_depth=1, learning_rate=0.5).fit(X, y)\n",
     "\n",
     "# explain the model's predictions using SHAP values\n",
     "# (same syntax works for LightGBM, CatBoost, and scikit-learn models)\n",
     "background = shap.maskers.TabularPartitions(X, sample=100)\n",
+    "\n",
+    "\n",
     "def f(x):\n",
-    "    return shap.links.identity(model.predict_proba(x, validate_features=False)[:,1])\n",
+    "    return shap.links.identity(model.predict_proba(x, validate_features=False)[:, 1])\n",
+    "\n",
+    "\n",
     "explainer = shap.Explainer(f, background, link=shap.links.logit)\n",
     "shap_values = explainer(X[:100])\n",
     "\n",
@@ -184,7 +188,7 @@
     }
    ],
    "source": [
-    "shap.plots.dependence(shap_values[:,\"Age\"])"
+    "shap.plots.dependence(shap_values[:, \"Age\"])"
    ]
   },
   {
@@ -210,7 +214,7 @@
     }
    ],
    "source": [
-    "shap.plots.dependence(shap_values[:,\"Age\"])"
+    "shap.plots.dependence(shap_values[:, \"Age\"])"
    ]
   },
   {
@@ -383,7 +387,7 @@
    ],
    "source": [
     "# plot the importance of a single feature across all samples\n",
-    "shap.plots.dependence(shap_values[:,\"RM\"], color=shap_values)"
+    "shap.plots.dependence(shap_values[:, \"RM\"], color=shap_values)"
    ]
   },
   {

notebooks/tabular_examples/tree_based_models/Scatter Density vs. Violin Plot Comparison.ipynb

@@ -53,7 +53,9 @@
     }
    ],
    "source": [
-    "shap.summary_plot(shap_values[:1000,:], X.iloc[:1000,:], plot_type=\"layered_violin\", color='#cccccc')"
+    "shap.summary_plot(\n",
+    "    shap_values[:1000, :], X.iloc[:1000, :], plot_type=\"layered_violin\", color=\"#cccccc\"\n",
+    ")"
    ]
   },
   {
@@ -80,7 +82,12 @@
     }
    ],
    "source": [
-    "shap.summary_plot(shap_values[:1000,:], X.iloc[:1000,:], plot_type=\"layered_violin\", color='coolwarm')"
+    "shap.summary_plot(\n",
+    "    shap_values[:1000, :],\n",
+    "    X.iloc[:1000, :],\n",
+    "    plot_type=\"layered_violin\",\n",
+    "    color=\"coolwarm\",\n",
+    ")"
    ]
   },
   {
@@ -140,7 +147,7 @@
     }
    ],
    "source": [
-    "shap.summary_plot(shap_values[:1000,:], X.iloc[:1000,:])"
+    "shap.summary_plot(shap_values[:1000, :], X.iloc[:1000, :])"
    ]
   },
   {
@@ -186,7 +193,7 @@
     }
    ],
    "source": [
-    "shap.summary_plot(shap_values[:1000,:], X.iloc[:1000,:], plot_type=\"violin\")"
+    "shap.summary_plot(shap_values[:1000, :], X.iloc[:1000, :], plot_type=\"violin\")"
    ]
   }
  ],