Pushing the docs to dev/ for branch: master, commit e030010c6c9a2073d4150decf1e1ff749bfdb837

Author: sklearn-ci

dev/_downloads/10bb40e21b74618cdeed618ff1eae595/plot_det.ipynb

@@ -15,7 +15,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n====================================\nDetection error tradeoff (DET) curve\n====================================\n\nIn this example, we compare receiver operating characteristic (ROC) and\ndetection error tradeoff (DET) curves for different classification algorithms\nfor the same classification task.\n\nDET curves are commonly plotted in normal deviate scale.\nTo achieve this we transform the error rates as returned by the\n:func:`~sklearn.metrics.detection_error_tradeoff_curve` function and the axis\nscale using :func:`scipy.stats.norm`.\n\nThe point of this example is to demonstrate two properties of DET curves,\nnamely:\n\n1. It might be easier to visually assess the overall performance of different\n   classification algorithms using DET curves over ROC curves.\n   Due to the linear scale used for plotting ROC curves, different classifiers\n   usually only differ in the top left corner of the graph and appear similar\n   for a large part of the plot. On the other hand, because DET curves\n   represent straight lines in normal deviate scale. As such, they tend to be\n   distinguishable as a whole and the area of interest spans a large part of\n   the plot.\n2. DET curves give the user direct feedback of the detection error tradeoff to\n   aid in operating point analysis.\n   The user can deduct directly from the DET-curve plot at which rate\n   false-negative error rate will improve when willing to accept an increase in\n   false-positive error rate (or vice-versa).\n\nThe plots in this example compare ROC curves on the left side to corresponding\nDET curves on the right.\nThere is no particular reason why these classifiers have been chosen for the\nexample plot over other classifiers available in scikit-learn.\n\n<div class=\"alert alert-info\"><h4>Note</h4><p>- See :func:`sklearn.metrics.roc_curve` for further information about ROC\n      curves.\n\n    - See :func:`sklearn.metrics.detection_error_tradeoff_curve` for further\n      information about DET curves.\n\n    - This example is loosely based on\n      `sphx_glr_auto_examples_classification_plot_classifier_comparison.py`\n      example.</p></div>\n"
+        "\n====================================\nDetection error tradeoff (DET) curve\n====================================\n\nIn this example, we compare receiver operating characteristic (ROC) and\ndetection error tradeoff (DET) curves for different classification algorithms\nfor the same classification task.\n\nDET curves are commonly plotted in normal deviate scale.\nTo achieve this `plot_det_curve` transforms the error rates as returned by the\n:func:`~sklearn.metrics.det_curve` and the axis scale using\n:func:`scipy.stats.norm`.\n\nThe point of this example is to demonstrate two properties of DET curves,\nnamely:\n\n1. It might be easier to visually assess the overall performance of different\n   classification algorithms using DET curves over ROC curves.\n   Due to the linear scale used for plotting ROC curves, different classifiers\n   usually only differ in the top left corner of the graph and appear similar\n   for a large part of the plot. On the other hand, because DET curves\n   represent straight lines in normal deviate scale. As such, they tend to be\n   distinguishable as a whole and the area of interest spans a large part of\n   the plot.\n2. DET curves give the user direct feedback of the detection error tradeoff to\n   aid in operating point analysis.\n   The user can deduct directly from the DET-curve plot at which rate\n   false-negative error rate will improve when willing to accept an increase in\n   false-positive error rate (or vice-versa).\n\nThe plots in this example compare ROC curves on the left side to corresponding\nDET curves on the right.\nThere is no particular reason why these classifiers have been chosen for the\nexample plot over other classifiers available in scikit-learn.\n\n<div class=\"alert alert-info\"><h4>Note</h4><p>- See :func:`sklearn.metrics.roc_curve` for further information about ROC\n      curves.\n\n    - See :func:`sklearn.metrics.det_curve` for further information about\n      DET curves.\n\n    - This example is loosely based on\n      `sphx_glr_auto_examples_classification_plot_classifier_comparison.py`\n      example.</p></div>\n"
       ]
     },
     {
@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\n\nfrom sklearn.datasets import make_classification\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import detection_error_tradeoff_curve\nfrom sklearn.metrics import plot_roc_curve\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.svm import LinearSVC\n\nfrom scipy.stats import norm\n\nN_SAMPLES = 1000\n\nclassifiers = {\n    \"Linear SVM\": make_pipeline(StandardScaler(), LinearSVC(C=0.025)),\n    \"Random Forest\": RandomForestClassifier(\n        max_depth=5, n_estimators=10, max_features=1\n    ),\n}\n\nX, y = make_classification(\n    n_samples=N_SAMPLES, n_features=2, n_redundant=0, n_informative=2,\n    random_state=1, n_clusters_per_class=1)\n\nX_train, X_test, y_train, y_test = train_test_split(\n    X, y, test_size=.4, random_state=0)\n\n# prepare plots\nfig, [ax_roc, ax_det] = plt.subplots(1, 2, figsize=(11, 5))\n\n# first prepare the ROC curve\nax_roc.set_title('Receiver Operating Characteristic (ROC) curves')\nax_roc.grid(linestyle='--')\n\n# second prepare the DET curve\nax_det.set_title('Detection Error Tradeoff (DET) curves')\nax_det.set_xlabel('False Positive Rate')\nax_det.set_ylabel('False Negative Rate')\nax_det.set_xlim(-3, 3)\nax_det.set_ylim(-3, 3)\nax_det.grid(linestyle='--')\n\n# customized ticks for DET curve plot to represent normal deviate scale\nticks = [0.001, 0.01, 0.05, 0.20, 0.5, 0.80, 0.95, 0.99, 0.999]\ntick_locs = norm.ppf(ticks)\ntick_lbls = [\n    '{:.0%}'.format(s) if (100*s).is_integer() else '{:.1%}'.format(s)\n    for s in ticks\n]\nplt.sca(ax_det)\nplt.xticks(tick_locs, tick_lbls)\nplt.yticks(tick_locs, tick_lbls)\n\n# iterate over classifiers\nfor name, clf in classifiers.items():\n    clf.fit(X_train, y_train)\n\n    if hasattr(clf, \"decision_function\"):\n        y_score = clf.decision_function(X_test)\n    else:\n        y_score = clf.predict_proba(X_test)[:, 1]\n\n    plot_roc_curve(clf, X_test, y_test, ax=ax_roc, name=name)\n    det_fpr, det_fnr, _ = detection_error_tradeoff_curve(y_test, y_score)\n\n    # transform errors into normal deviate scale\n    ax_det.plot(norm.ppf(det_fpr), norm.ppf(det_fnr), label=name)\n\nplt.legend()\nplt.show()"
+        "import matplotlib.pyplot as plt\n\nfrom sklearn.datasets import make_classification\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import plot_det_curve\nfrom sklearn.metrics import plot_roc_curve\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.svm import LinearSVC\n\nN_SAMPLES = 1000\n\nclassifiers = {\n    \"Linear SVM\": make_pipeline(StandardScaler(), LinearSVC(C=0.025)),\n    \"Random Forest\": RandomForestClassifier(\n        max_depth=5, n_estimators=10, max_features=1\n    ),\n}\n\nX, y = make_classification(\n    n_samples=N_SAMPLES, n_features=2, n_redundant=0, n_informative=2,\n    random_state=1, n_clusters_per_class=1)\n\nX_train, X_test, y_train, y_test = train_test_split(\n    X, y, test_size=.4, random_state=0)\n\n# prepare plots\nfig, [ax_roc, ax_det] = plt.subplots(1, 2, figsize=(11, 5))\n\nfor name, clf in classifiers.items():\n    clf.fit(X_train, y_train)\n\n    plot_roc_curve(clf, X_test, y_test, ax=ax_roc, name=name)\n    plot_det_curve(clf, X_test, y_test, ax=ax_det, name=name)\n\nax_roc.set_title('Receiver Operating Characteristic (ROC) curves')\nax_det.set_title('Detection Error Tradeoff (DET) curves')\n\nax_roc.grid(linestyle='--')\nax_det.grid(linestyle='--')\n\nplt.legend()\nplt.show()"
       ]
     }
   ],

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -8,9 +8,9 @@
 for the same classification task.
 
 DET curves are commonly plotted in normal deviate scale.
-To achieve this we transform the error rates as returned by the
-:func:`~sklearn.metrics.detection_error_tradeoff_curve` function and the axis
-scale using :func:`scipy.stats.norm`.
+To achieve this `plot_det_curve` transforms the error rates as returned by the
+:func:`~sklearn.metrics.det_curve` and the axis scale using
+:func:`scipy.stats.norm`.
 
 The point of this example is to demonstrate two properties of DET curves,
 namely:
@@ -39,8 +39,8 @@
     - See :func:`sklearn.metrics.roc_curve` for further information about ROC
       curves.
 
-    - See :func:`sklearn.metrics.detection_error_tradeoff_curve` for further
-      information about DET curves.
+    - See :func:`sklearn.metrics.det_curve` for further information about
+      DET curves.
 
     - This example is loosely based on
       :ref:`sphx_glr_auto_examples_classification_plot_classifier_comparison.py`
@@ -51,15 +51,13 @@
 
 from sklearn.datasets import make_classification
 from sklearn.ensemble import RandomForestClassifier
-from sklearn.metrics import detection_error_tradeoff_curve
+from sklearn.metrics import plot_det_curve
 from sklearn.metrics import plot_roc_curve
 from sklearn.model_selection import train_test_split
 from sklearn.pipeline import make_pipeline
 from sklearn.preprocessing import StandardScaler
 from sklearn.svm import LinearSVC
 
-from scipy.stats import norm
-
 N_SAMPLES = 1000
 
 classifiers = {
@@ -79,43 +77,17 @@
 # prepare plots
 fig, [ax_roc, ax_det] = plt.subplots(1, 2, figsize=(11, 5))
 
-# first prepare the ROC curve
-ax_roc.set_title('Receiver Operating Characteristic (ROC) curves')
-ax_roc.grid(linestyle='--')
-
-# second prepare the DET curve
-ax_det.set_title('Detection Error Tradeoff (DET) curves')
-ax_det.set_xlabel('False Positive Rate')
-ax_det.set_ylabel('False Negative Rate')
-ax_det.set_xlim(-3, 3)
-ax_det.set_ylim(-3, 3)
-ax_det.grid(linestyle='--')
-
-# customized ticks for DET curve plot to represent normal deviate scale
-ticks = [0.001, 0.01, 0.05, 0.20, 0.5, 0.80, 0.95, 0.99, 0.999]
-tick_locs = norm.ppf(ticks)
-tick_lbls = [
-    '{:.0%}'.format(s) if (100*s).is_integer() else '{:.1%}'.format(s)
-    for s in ticks
-]
-plt.sca(ax_det)
-plt.xticks(tick_locs, tick_lbls)
-plt.yticks(tick_locs, tick_lbls)
-
-# iterate over classifiers
 for name, clf in classifiers.items():
     clf.fit(X_train, y_train)
 
-    if hasattr(clf, "decision_function"):
-        y_score = clf.decision_function(X_test)
-    else:
-        y_score = clf.predict_proba(X_test)[:, 1]
-
     plot_roc_curve(clf, X_test, y_test, ax=ax_roc, name=name)
-    det_fpr, det_fnr, _ = detection_error_tradeoff_curve(y_test, y_score)
+    plot_det_curve(clf, X_test, y_test, ax=ax_det, name=name)
+
+ax_roc.set_title('Receiver Operating Characteristic (ROC) curves')
+ax_det.set_title('Detection Error Tradeoff (DET) curves')
 
-    # transform errors into normal deviate scale
-    ax_det.plot(norm.ppf(det_fpr), norm.ppf(det_fnr), label=name)
+ax_roc.grid(linestyle='--')
+ax_det.grid(linestyle='--')
 
 plt.legend()
 plt.show()