Pushing the docs to dev/ for branch: main, commit 75db1bc2dbd716016170241d8daae97624d01252

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Peter Prettenhofer <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import ensemble\nfrom sklearn import datasets\n\nfrom sklearn.model_selection import train_test_split\n\nX, y = datasets.make_hastie_10_2(n_samples=4000, random_state=1)\n\n# map labels from {-1, 1} to {0, 1}\nlabels, y = np.unique(y, return_inverse=True)\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.8, random_state=0)\n\noriginal_params = {\n    \"n_estimators\": 400,\n    \"max_leaf_nodes\": 4,\n    \"max_depth\": None,\n    \"random_state\": 2,\n    \"min_samples_split\": 5,\n}\n\nplt.figure()\n\nfor label, color, setting in [\n    (\"No shrinkage\", \"orange\", {\"learning_rate\": 1.0, \"subsample\": 1.0}),\n    (\"learning_rate=0.2\", \"turquoise\", {\"learning_rate\": 0.2, \"subsample\": 1.0}),\n    (\"subsample=0.5\", \"blue\", {\"learning_rate\": 1.0, \"subsample\": 0.5}),\n    (\n        \"learning_rate=0.2, subsample=0.5\",\n        \"gray\",\n        {\"learning_rate\": 0.2, \"subsample\": 0.5},\n    ),\n    (\n        \"learning_rate=0.2, max_features=2\",\n        \"magenta\",\n        {\"learning_rate\": 0.2, \"max_features\": 2},\n    ),\n]:\n    params = dict(original_params)\n    params.update(setting)\n\n    clf = ensemble.GradientBoostingClassifier(**params)\n    clf.fit(X_train, y_train)\n\n    # compute test set deviance\n    test_deviance = np.zeros((params[\"n_estimators\"],), dtype=np.float64)\n\n    for i, y_pred in enumerate(clf.staged_decision_function(X_test)):\n        # clf.loss_ assumes that y_test[i] in {0, 1}\n        test_deviance[i] = clf.loss_(y_test, y_pred)\n\n    plt.plot(\n        (np.arange(test_deviance.shape[0]) + 1)[::5],\n        test_deviance[::5],\n        \"-\",\n        color=color,\n        label=label,\n    )\n\nplt.legend(loc=\"upper right\")\nplt.xlabel(\"Boosting Iterations\")\nplt.ylabel(\"Test Set Deviance\")\n\nplt.show()"
+        "# Author: Peter Prettenhofer <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import ensemble\nfrom sklearn import datasets\nfrom sklearn.metrics import log_loss\nfrom sklearn.model_selection import train_test_split\n\nX, y = datasets.make_hastie_10_2(n_samples=4000, random_state=1)\n\n# map labels from {-1, 1} to {0, 1}\nlabels, y = np.unique(y, return_inverse=True)\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.8, random_state=0)\n\noriginal_params = {\n    \"n_estimators\": 400,\n    \"max_leaf_nodes\": 4,\n    \"max_depth\": None,\n    \"random_state\": 2,\n    \"min_samples_split\": 5,\n}\n\nplt.figure()\n\nfor label, color, setting in [\n    (\"No shrinkage\", \"orange\", {\"learning_rate\": 1.0, \"subsample\": 1.0}),\n    (\"learning_rate=0.2\", \"turquoise\", {\"learning_rate\": 0.2, \"subsample\": 1.0}),\n    (\"subsample=0.5\", \"blue\", {\"learning_rate\": 1.0, \"subsample\": 0.5}),\n    (\n        \"learning_rate=0.2, subsample=0.5\",\n        \"gray\",\n        {\"learning_rate\": 0.2, \"subsample\": 0.5},\n    ),\n    (\n        \"learning_rate=0.2, max_features=2\",\n        \"magenta\",\n        {\"learning_rate\": 0.2, \"max_features\": 2},\n    ),\n]:\n    params = dict(original_params)\n    params.update(setting)\n\n    clf = ensemble.GradientBoostingClassifier(**params)\n    clf.fit(X_train, y_train)\n\n    # compute test set deviance\n    test_deviance = np.zeros((params[\"n_estimators\"],), dtype=np.float64)\n\n    for i, y_proba in enumerate(clf.staged_predict_proba(X_test)):\n        test_deviance[i] = 2 * log_loss(y_test, y_proba[:, 1])\n\n    plt.plot(\n        (np.arange(test_deviance.shape[0]) + 1)[::5],\n        test_deviance[::5],\n        \"-\",\n        color=color,\n        label=label,\n    )\n\nplt.legend(loc=\"upper right\")\nplt.xlabel(\"Boosting Iterations\")\nplt.ylabel(\"Test Set Deviance\")\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/0a90f2b8e2dadb7d37ca67b3f7adb656/plot_gradient_boosting_regularization.ipynb

@@ -30,7 +30,7 @@
 
 from sklearn import ensemble
 from sklearn import datasets
-
+from sklearn.metrics import log_loss
 from sklearn.model_selection import train_test_split
 
 X, y = datasets.make_hastie_10_2(n_samples=4000, random_state=1)
@@ -74,9 +74,8 @@
     # compute test set deviance
     test_deviance = np.zeros((params["n_estimators"],), dtype=np.float64)
 
-    for i, y_pred in enumerate(clf.staged_decision_function(X_test)):
-        # clf.loss_ assumes that y_test[i] in {0, 1}
-        test_deviance[i] = clf.loss_(y_test, y_pred)
+    for i, y_proba in enumerate(clf.staged_predict_proba(X_test)):
+        test_deviance[i] = 2 * log_loss(y_test, y_proba[:, 1])
 
     plt.plot(
         (np.arange(test_deviance.shape[0]) + 1)[::5],