Pushing the docs for revision for branch: master, commit 5fcc7e5cf0aee903bad686f1d6cf7eb4e890d682

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -0,0 +1,54 @@
+{
+  "nbformat_minor": 0, 
+  "nbformat": 4, 
+  "cells": [
+    {
+      "execution_count": null, 
+      "cell_type": "code", 
+      "source": [
+        "%matplotlib inline"
+      ], 
+      "outputs": [], 
+      "metadata": {
+        "collapsed": false
+      }
+    }, 
+    {
+      "source": [
+        "\n# Nested versus non-nested cross-validation\n\n\nThis example compares non-nested and nested cross-validation strategies on a\nclassifier of the iris data set. Nested cross-validation (CV) is often used to\ntrain a model in which hyperparameters also need to be optimized. Nested CV\nestimates the generalization error of the underlying model and its\n(hyper)parameter search. Choosing the parameters that maximize non-nested CV\nbiases the model to the dataset, yielding an overly-optimistic score.\n\nModel selection without nested CV uses the same data to tune model parameters\nand evaluate model performance. Information may thus \"leak\" into the model\nand overfit the data. The magnitude of this effect is primarily dependent on\nthe size of the dataset and the stability of the model. See Cawley and Talbot\n[1]_ for an analysis of these issues.\n\nTo avoid this problem, nested CV effectively uses a series of\ntrain/validation/test set splits. In the inner loop, the score is approximately\nmaximized by fitting a model to each training set, and then directly maximized\nin selecting (hyper)parameters over the validation set. In the outer loop,\ngeneralization error is estimated by averaging test set scores over several\ndataset splits.\n\nThe example below uses a support vector classifier with a non-linear kernel to\nbuild a model with optimized hyperparameters by grid search. We compare the\nperformance of non-nested and nested CV strategies by taking the difference\nbetween their scores.\n\n.. topic:: See Also:\n\n    - `cross_validation`\n    - `grid_search`\n\n.. topic:: References:\n\n    .. [1] `Cawley, G.C.; Talbot, N.L.C. On over-fitting in model selection and\n     subsequent selection bias in performance evaluation.\n     J. Mach. Learn. Res 2010,11, 2079-2107.\n     <http://jmlr.csail.mit.edu/papers/volume11/cawley10a/cawley10a.pdf>`_\n\n\n"
+      ], 
+      "cell_type": "markdown", 
+      "metadata": {}
+    }, 
+    {
+      "execution_count": null, 
+      "cell_type": "code", 
+      "source": [
+        "from sklearn.datasets import load_iris\nfrom matplotlib import pyplot as plt\nfrom sklearn.svm import SVC\nfrom sklearn.model_selection import GridSearchCV, cross_val_score, KFold\nimport numpy as np\n\nprint(__doc__)\n\n# Number of random trials\nNUM_TRIALS = 30\n\n# Load the dataset\niris = load_iris()\nX_iris = iris.data\ny_iris = iris.target\n\n# Set up possible values of parameters to optimize over\np_grid = {\"C\": [1, 10, 100],\n          \"gamma\": [.01, .1]}\n\n# We will use a Support Vector Classifier with \"rbf\" kernel\nsvr = SVC(kernel=\"rbf\")\n\n# Arrays to store scores\nnon_nested_scores = np.zeros(NUM_TRIALS)\nnested_scores = np.zeros(NUM_TRIALS)\n\n# Loop for each trial\nfor i in range(NUM_TRIALS):\n\n    # Choose cross-validation techniques for the inner and outer loops,\n    # independently of the dataset.\n    # E.g \"LabelKFold\", \"LeaveOneOut\", \"LeaveOneLabelOut\", etc.\n    inner_cv = KFold(n_splits=4, shuffle=True, random_state=i)\n    outer_cv = KFold(n_splits=4, shuffle=True, random_state=i)\n\n    # Non_nested parameter search and scoring\n    clf = GridSearchCV(estimator=svr, param_grid=p_grid, cv=inner_cv)\n    clf.fit(X_iris, y_iris)\n    non_nested_scores[i] = clf.best_score_\n\n    # Nested CV with parameter optimization\n    nested_score = cross_val_score(clf, X=X_iris, y=y_iris, cv=outer_cv)\n    nested_scores[i] = nested_score.mean()\n\nscore_difference = non_nested_scores - nested_scores\n\nprint(\"Average difference of {0:6f} with std. dev. of {1:6f}.\"\n      .format(score_difference.mean(), score_difference.std()))\n\n# Plot scores on each trial for nested and non-nested CV\nplt.figure()\nplt.subplot(211)\nnon_nested_scores_line, = plt.plot(non_nested_scores, color='r')\nnested_line, = plt.plot(nested_scores, color='b')\nplt.ylabel(\"score\", fontsize=\"14\")\nplt.legend([non_nested_scores_line, nested_line],\n           [\"Non-Nested CV\", \"Nested CV\"],\n           bbox_to_anchor=(0, .4, .5, 0))\nplt.title(\"Non-Nested and Nested Cross Validation on Iris Dataset\",\n          x=.5, y=1.1, fontsize=\"15\")\n\n# Plot bar chart of the difference.\nplt.subplot(212)\ndifference_plot = plt.bar(range(NUM_TRIALS), score_difference)\nplt.xlabel(\"Individual Trial #\")\nplt.legend([difference_plot],\n           [\"Non-Nested CV - Nested CV Score\"],\n           bbox_to_anchor=(0, 1, .8, 0))\nplt.ylabel(\"score difference\", fontsize=\"14\")\n\nplt.show()"
+      ], 
+      "outputs": [], 
+      "metadata": {
+        "collapsed": false
+      }
+    }
+  ], 
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 2", 
+      "name": "python2", 
+      "language": "python"
+    }, 
+    "language_info": {
+      "mimetype": "text/x-python", 
+      "nbconvert_exporter": "python", 
+      "name": "python", 
+      "file_extension": ".py", 
+      "version": "2.7.12", 
+      "pygments_lexer": "ipython2", 
+      "codemirror_mode": {
+        "version": 2, 
+        "name": "ipython"
+      }
+    }
+  }
+}

dev/_downloads/auto_examples_python.zip

@@ -0,0 +1,115 @@
+"""
+=========================================
+Nested versus non-nested cross-validation
+=========================================
+
+This example compares non-nested and nested cross-validation strategies on a
+classifier of the iris data set. Nested cross-validation (CV) is often used to
+train a model in which hyperparameters also need to be optimized. Nested CV
+estimates the generalization error of the underlying model and its
+(hyper)parameter search. Choosing the parameters that maximize non-nested CV
+biases the model to the dataset, yielding an overly-optimistic score.
+
+Model selection without nested CV uses the same data to tune model parameters
+and evaluate model performance. Information may thus "leak" into the model
+and overfit the data. The magnitude of this effect is primarily dependent on
+the size of the dataset and the stability of the model. See Cawley and Talbot
+[1]_ for an analysis of these issues.
+
+To avoid this problem, nested CV effectively uses a series of
+train/validation/test set splits. In the inner loop, the score is approximately
+maximized by fitting a model to each training set, and then directly maximized
+in selecting (hyper)parameters over the validation set. In the outer loop,
+generalization error is estimated by averaging test set scores over several
+dataset splits.
+
+The example below uses a support vector classifier with a non-linear kernel to
+build a model with optimized hyperparameters by grid search. We compare the
+performance of non-nested and nested CV strategies by taking the difference
+between their scores.
+
+.. topic:: See Also:
+
+    - :ref:`cross_validation`
+    - :ref:`grid_search`
+
+.. topic:: References:
+
+    .. [1] `Cawley, G.C.; Talbot, N.L.C. On over-fitting in model selection and
+     subsequent selection bias in performance evaluation.
+     J. Mach. Learn. Res 2010,11, 2079-2107.
+     <http://jmlr.csail.mit.edu/papers/volume11/cawley10a/cawley10a.pdf>`_
+
+"""
+from sklearn.datasets import load_iris
+from matplotlib import pyplot as plt
+from sklearn.svm import SVC
+from sklearn.model_selection import GridSearchCV, cross_val_score, KFold
+import numpy as np
+
+print(__doc__)
+
+# Number of random trials
+NUM_TRIALS = 30
+
+# Load the dataset
+iris = load_iris()
+X_iris = iris.data
+y_iris = iris.target
+
+# Set up possible values of parameters to optimize over
+p_grid = {"C": [1, 10, 100],
+          "gamma": [.01, .1]}
+
+# We will use a Support Vector Classifier with "rbf" kernel
+svr = SVC(kernel="rbf")
+
+# Arrays to store scores
+non_nested_scores = np.zeros(NUM_TRIALS)
+nested_scores = np.zeros(NUM_TRIALS)
+
+# Loop for each trial
+for i in range(NUM_TRIALS):
+
+    # Choose cross-validation techniques for the inner and outer loops,
+    # independently of the dataset.
+    # E.g "LabelKFold", "LeaveOneOut", "LeaveOneLabelOut", etc.
+    inner_cv = KFold(n_splits=4, shuffle=True, random_state=i)
+    outer_cv = KFold(n_splits=4, shuffle=True, random_state=i)
+
+    # Non_nested parameter search and scoring
+    clf = GridSearchCV(estimator=svr, param_grid=p_grid, cv=inner_cv)
+    clf.fit(X_iris, y_iris)
+    non_nested_scores[i] = clf.best_score_
+
+    # Nested CV with parameter optimization
+    nested_score = cross_val_score(clf, X=X_iris, y=y_iris, cv=outer_cv)
+    nested_scores[i] = nested_score.mean()
+
+score_difference = non_nested_scores - nested_scores
+
+print("Average difference of {0:6f} with std. dev. of {1:6f}."
+      .format(score_difference.mean(), score_difference.std()))
+
+# Plot scores on each trial for nested and non-nested CV
+plt.figure()
+plt.subplot(211)
+non_nested_scores_line, = plt.plot(non_nested_scores, color='r')
+nested_line, = plt.plot(nested_scores, color='b')
+plt.ylabel("score", fontsize="14")
+plt.legend([non_nested_scores_line, nested_line],
+           ["Non-Nested CV", "Nested CV"],
+           bbox_to_anchor=(0, .4, .5, 0))
+plt.title("Non-Nested and Nested Cross Validation on Iris Dataset",
+          x=.5, y=1.1, fontsize="15")
+
+# Plot bar chart of the difference.
+plt.subplot(212)
+difference_plot = plt.bar(range(NUM_TRIALS), score_difference)
+plt.xlabel("Individual Trial #")
+plt.legend([difference_plot],
+           ["Non-Nested CV - Nested CV Score"],
+           bbox_to_anchor=(0, 1, .8, 0))
+plt.ylabel("score difference", fontsize="14")
+
+plt.show()