Pushing the docs to dev/ for branch: main, commit 832513a7fb6570c41f3c8bf4bf7cbaf110da300e

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Vighnesh Birodkar <[email protected]>\n#          Raghav RV <[email protected]>\n# License: BSD 3 clause\n\nimport time\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import ensemble\nfrom sklearn import datasets\nfrom sklearn.model_selection import train_test_split\n\ndata_list = [datasets.load_iris(), datasets.load_digits()]\ndata_list = [(d.data, d.target) for d in data_list]\ndata_list += [datasets.make_hastie_10_2()]\nnames = [\"Iris Data\", \"Digits Data\", \"Hastie Data\"]\n\nn_gb = []\nscore_gb = []\ntime_gb = []\nn_gbes = []\nscore_gbes = []\ntime_gbes = []\n\nn_estimators = 500\n\nfor X, y in data_list:\n    X_train, X_test, y_train, y_test = train_test_split(\n        X, y, test_size=0.2, random_state=0\n    )\n\n    # We specify that if the scores don't improve by at least 0.01 for the last\n    # 10 stages, stop fitting additional stages\n    gbes = ensemble.GradientBoostingClassifier(\n        n_estimators=n_estimators,\n        validation_fraction=0.2,\n        n_iter_no_change=5,\n        tol=0.01,\n        random_state=0,\n    )\n    gb = ensemble.GradientBoostingClassifier(n_estimators=n_estimators, random_state=0)\n    start = time.time()\n    gb.fit(X_train, y_train)\n    time_gb.append(time.time() - start)\n\n    start = time.time()\n    gbes.fit(X_train, y_train)\n    time_gbes.append(time.time() - start)\n\n    score_gb.append(gb.score(X_test, y_test))\n    score_gbes.append(gbes.score(X_test, y_test))\n\n    n_gb.append(gb.n_estimators_)\n    n_gbes.append(gbes.n_estimators_)\n\nbar_width = 0.2\nn = len(data_list)\nindex = np.arange(0, n * bar_width, bar_width) * 2.5\nindex = index[0:n]"
+        "# Authors: Vighnesh Birodkar <[email protected]>\n#          Raghav RV <[email protected]>\n# License: BSD 3 clause\n\nimport time\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import ensemble\nfrom sklearn import datasets\nfrom sklearn.model_selection import train_test_split\n\ndata_list = [\n    datasets.load_iris(return_X_y=True),\n    datasets.make_classification(n_samples=800, random_state=0),\n    datasets.make_hastie_10_2(n_samples=2000, random_state=0),\n]\nnames = [\"Iris Data\", \"Classification Data\", \"Hastie Data\"]\n\nn_gb = []\nscore_gb = []\ntime_gb = []\nn_gbes = []\nscore_gbes = []\ntime_gbes = []\n\nn_estimators = 200\n\nfor X, y in data_list:\n    X_train, X_test, y_train, y_test = train_test_split(\n        X, y, test_size=0.2, random_state=0\n    )\n\n    # We specify that if the scores don't improve by at least 0.01 for the last\n    # 10 stages, stop fitting additional stages\n    gbes = ensemble.GradientBoostingClassifier(\n        n_estimators=n_estimators,\n        validation_fraction=0.2,\n        n_iter_no_change=5,\n        tol=0.01,\n        random_state=0,\n    )\n    gb = ensemble.GradientBoostingClassifier(n_estimators=n_estimators, random_state=0)\n    start = time.time()\n    gb.fit(X_train, y_train)\n    time_gb.append(time.time() - start)\n\n    start = time.time()\n    gbes.fit(X_train, y_train)\n    time_gbes.append(time.time() - start)\n\n    score_gb.append(gb.score(X_test, y_test))\n    score_gbes.append(gbes.score(X_test, y_test))\n\n    n_gb.append(gb.n_estimators_)\n    n_gbes.append(gbes.n_estimators_)\n\nbar_width = 0.2\nn = len(data_list)\nindex = np.arange(0, n * bar_width, bar_width) * 2.5\nindex = index[0:n]"
       ]
     },
     {

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -45,10 +45,12 @@
 from sklearn import datasets
 from sklearn.model_selection import train_test_split
 
-data_list = [datasets.load_iris(), datasets.load_digits()]
-data_list = [(d.data, d.target) for d in data_list]
-data_list += [datasets.make_hastie_10_2()]
-names = ["Iris Data", "Digits Data", "Hastie Data"]
+data_list = [
+    datasets.load_iris(return_X_y=True),
+    datasets.make_classification(n_samples=800, random_state=0),
+    datasets.make_hastie_10_2(n_samples=2000, random_state=0),
+]
+names = ["Iris Data", "Classification Data", "Hastie Data"]
 
 n_gb = []
 score_gb = []
@@ -57,7 +59,7 @@
 score_gbes = []
 time_gbes = []
 
-n_estimators = 500
+n_estimators = 200
 
 for X, y in data_list:
     X_train, X_test, y_train, y_test = train_test_split(