Pushing the docs to dev/ for branch: master, commit 6d604d1d9342397b90e5e59e1ec1932da3374e7a

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -24,7 +24,7 @@
       "execution_count": null, 
       "cell_type": "code", 
       "source": [
-        "print(__doc__)\n\nimport numpy as np\n\nfrom time import time\nfrom scipy.stats import randint as sp_randint\n\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.model_selection import RandomizedSearchCV\nfrom sklearn.datasets import load_digits\nfrom sklearn.ensemble import RandomForestClassifier\n\n# get some data\ndigits = load_digits()\nX, y = digits.data, digits.target\n\n# build a classifier\nclf = RandomForestClassifier(n_estimators=20)\n\n\n# Utility function to report best scores\ndef report(results, n_top=3):\n    for i in range(1, n_top + 1):\n        candidates = np.flatnonzero(results['rank_test_score'] == i)\n        for candidate in candidates:\n            print(\"Model with rank: {0}\".format(i))\n            print(\"Mean validation score: {0:.3f} (std: {1:.3f})\".format(\n                  results['mean_test_score'][candidate],\n                  results['std_test_score'][candidate]))\n            print(\"Parameters: {0}\".format(results['params'][candidate]))\n            print(\"\")\n\n\n# specify parameters and distributions to sample from\nparam_dist = {\"max_depth\": [3, None],\n              \"max_features\": sp_randint(1, 11),\n              \"min_samples_split\": sp_randint(1, 11),\n              \"min_samples_leaf\": sp_randint(1, 11),\n              \"bootstrap\": [True, False],\n              \"criterion\": [\"gini\", \"entropy\"]}\n\n# run randomized search\nn_iter_search = 20\nrandom_search = RandomizedSearchCV(clf, param_distributions=param_dist,\n                                   n_iter=n_iter_search)\n\nstart = time()\nrandom_search.fit(X, y)\nprint(\"RandomizedSearchCV took %.2f seconds for %d candidates\"\n      \" parameter settings.\" % ((time() - start), n_iter_search))\nreport(random_search.cv_results_)\n\n# use a full grid over all parameters\nparam_grid = {\"max_depth\": [3, None],\n              \"max_features\": [1, 3, 10],\n              \"min_samples_split\": [1, 3, 10],\n              \"min_samples_leaf\": [1, 3, 10],\n              \"bootstrap\": [True, False],\n              \"criterion\": [\"gini\", \"entropy\"]}\n\n# run grid search\ngrid_search = GridSearchCV(clf, param_grid=param_grid)\nstart = time()\ngrid_search.fit(X, y)\n\nprint(\"GridSearchCV took %.2f seconds for %d candidate parameter settings.\"\n      % (time() - start, len(grid_search.cv_results_['params'])))\nreport(grid_search.cv_results_)"
+        "print(__doc__)\n\nimport numpy as np\n\nfrom time import time\nfrom scipy.stats import randint as sp_randint\n\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.model_selection import RandomizedSearchCV\nfrom sklearn.datasets import load_digits\nfrom sklearn.ensemble import RandomForestClassifier\n\n# get some data\ndigits = load_digits()\nX, y = digits.data, digits.target\n\n# build a classifier\nclf = RandomForestClassifier(n_estimators=20)\n\n\n# Utility function to report best scores\ndef report(results, n_top=3):\n    for i in range(1, n_top + 1):\n        candidates = np.flatnonzero(results['rank_test_score'] == i)\n        for candidate in candidates:\n            print(\"Model with rank: {0}\".format(i))\n            print(\"Mean validation score: {0:.3f} (std: {1:.3f})\".format(\n                  results['mean_test_score'][candidate],\n                  results['std_test_score'][candidate]))\n            print(\"Parameters: {0}\".format(results['params'][candidate]))\n            print(\"\")\n\n\n# specify parameters and distributions to sample from\nparam_dist = {\"max_depth\": [3, None],\n              \"max_features\": sp_randint(1, 11),\n              \"min_samples_split\": sp_randint(2, 11),\n              \"min_samples_leaf\": sp_randint(1, 11),\n              \"bootstrap\": [True, False],\n              \"criterion\": [\"gini\", \"entropy\"]}\n\n# run randomized search\nn_iter_search = 20\nrandom_search = RandomizedSearchCV(clf, param_distributions=param_dist,\n                                   n_iter=n_iter_search)\n\nstart = time()\nrandom_search.fit(X, y)\nprint(\"RandomizedSearchCV took %.2f seconds for %d candidates\"\n      \" parameter settings.\" % ((time() - start), n_iter_search))\nreport(random_search.cv_results_)\n\n# use a full grid over all parameters\nparam_grid = {\"max_depth\": [3, None],\n              \"max_features\": [1, 3, 10],\n              \"min_samples_split\": [2, 3, 10],\n              \"min_samples_leaf\": [1, 3, 10],\n              \"bootstrap\": [True, False],\n              \"criterion\": [\"gini\", \"entropy\"]}\n\n# run grid search\ngrid_search = GridSearchCV(clf, param_grid=param_grid)\nstart = time()\ngrid_search.fit(X, y)\n\nprint(\"GridSearchCV took %.2f seconds for %d candidate parameter settings.\"\n      % (time() - start, len(grid_search.cv_results_['params'])))\nreport(grid_search.cv_results_)"
       ], 
       "outputs": [], 
       "metadata": {

dev/_downloads/auto_examples_python.zip

@@ -54,7 +54,7 @@ def report(results, n_top=3):
 # specify parameters and distributions to sample from
 param_dist = {"max_depth": [3, None],
               "max_features": sp_randint(1, 11),
-              "min_samples_split": sp_randint(1, 11),
+              "min_samples_split": sp_randint(2, 11),
               "min_samples_leaf": sp_randint(1, 11),
               "bootstrap": [True, False],
               "criterion": ["gini", "entropy"]}
@@ -73,7 +73,7 @@ def report(results, n_top=3):
 # use a full grid over all parameters
 param_grid = {"max_depth": [3, None],
               "max_features": [1, 3, 10],
-              "min_samples_split": [1, 3, 10],
+              "min_samples_split": [2, 3, 10],
               "min_samples_leaf": [1, 3, 10],
               "bootstrap": [True, False],
               "criterion": ["gini", "entropy"]}