Pushing the docs to dev/ for branch: main, commit f19bf4c406e9b0155038d995cc6e1c792d38bc4e

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\n\nX, y = datasets.make_hastie_10_2(n_samples=12000, random_state=1)\nX = X.astype(np.float32)\n\n# map labels from {-1, 1} to {0, 1}\nlabels, y = np.unique(y, return_inverse=True)\n\nX_train, X_test = X[:2000], X[2000:]\ny_train, y_test = y[:2000], y[2000:]\n\noriginal_params = {\n    \"n_estimators\": 1000,\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=0.1\", \"turquoise\", {\"learning_rate\": 0.1, \"subsample\": 1.0}),\n    (\"subsample=0.5\", \"blue\", {\"learning_rate\": 1.0, \"subsample\": 0.5}),\n    (\n        \"learning_rate=0.1, subsample=0.5\",\n        \"gray\",\n        {\"learning_rate\": 0.1, \"subsample\": 0.5},\n    ),\n    (\n        \"learning_rate=0.1, max_features=2\",\n        \"magenta\",\n        {\"learning_rate\": 0.1, \"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 left\")\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\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 left\")\nplt.xlabel(\"Boosting Iterations\")\nplt.ylabel(\"Test Set Deviance\")\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/0a90f2b8e2dadb7d37ca67b3f7adb656/plot_gradient_boosting_regularization.ipynb

@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "rng = np.random.RandomState(0)\n\nX, y = datasets.make_classification(n_samples=700, random_state=rng)\n\nclf = RandomForestClassifier(n_estimators=20, random_state=rng)\n\nparam_dist = {\n    \"max_depth\": [3, None],\n    \"max_features\": randint(1, 11),\n    \"min_samples_split\": randint(2, 11),\n    \"bootstrap\": [True, False],\n    \"criterion\": [\"gini\", \"entropy\"],\n}\n\nrsh = HalvingRandomSearchCV(\n    estimator=clf, param_distributions=param_dist, factor=2, random_state=rng\n)\nrsh.fit(X, y)"
+        "rng = np.random.RandomState(0)\n\nX, y = datasets.make_classification(n_samples=400, n_features=12, random_state=rng)\n\nclf = RandomForestClassifier(n_estimators=20, random_state=rng)\n\nparam_dist = {\n    \"max_depth\": [3, None],\n    \"max_features\": randint(1, 6),\n    \"min_samples_split\": randint(2, 11),\n    \"bootstrap\": [True, False],\n    \"criterion\": [\"gini\", \"entropy\"],\n}\n\nrsh = HalvingRandomSearchCV(\n    estimator=clf, param_distributions=param_dist, factor=2, random_state=rng\n)\nrsh.fit(X, y)"
       ]
     },
     {

dev/_downloads/23fb33f64b3c23edf25165a3a4f04237/plot_successive_halving_iterations.ipynb

@@ -27,13 +27,13 @@
 
 rng = np.random.RandomState(0)
 
-X, y = datasets.make_classification(n_samples=700, random_state=rng)
+X, y = datasets.make_classification(n_samples=400, n_features=12, random_state=rng)
 
 clf = RandomForestClassifier(n_estimators=20, random_state=rng)
 
 param_dist = {
     "max_depth": [3, None],
-    "max_features": randint(1, 11),
+    "max_features": randint(1, 6),
     "min_samples_split": randint(2, 11),
     "bootstrap": [True, False],
     "criterion": ["gini", "entropy"],