Pushing the docs to dev/ for branch: main, commit 4493f86c463689e4fed76240bfac98f9252d1bbd

Author: sklearn-ci

dev/_downloads/010337852815f8103ac6cca38a812b3c/plot_roc_crossval.py

@@ -89,8 +89,7 @@
         X[test],
         y[test],
         name=f"ROC fold {fold}",
-        alpha=0.3,
-        lw=1,
+        curve_kwargs=dict(alpha=0.3, lw=1),
         ax=ax,
         plot_chance_level=(fold == n_splits - 1),
     )

dev/_downloads/02192f99342d6d1323161978b6c80bfc/plot_ols_ridge.zip

@@ -69,7 +69,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\n\nfrom sklearn import svm\nfrom sklearn.metrics import RocCurveDisplay, auc\nfrom sklearn.model_selection import StratifiedKFold\n\nn_splits = 6\ncv = StratifiedKFold(n_splits=n_splits)\nclassifier = svm.SVC(kernel=\"linear\", probability=True, random_state=random_state)\n\ntprs = []\naucs = []\nmean_fpr = np.linspace(0, 1, 100)\n\nfig, ax = plt.subplots(figsize=(6, 6))\nfor fold, (train, test) in enumerate(cv.split(X, y)):\n    classifier.fit(X[train], y[train])\n    viz = RocCurveDisplay.from_estimator(\n        classifier,\n        X[test],\n        y[test],\n        name=f\"ROC fold {fold}\",\n        alpha=0.3,\n        lw=1,\n        ax=ax,\n        plot_chance_level=(fold == n_splits - 1),\n    )\n    interp_tpr = np.interp(mean_fpr, viz.fpr, viz.tpr)\n    interp_tpr[0] = 0.0\n    tprs.append(interp_tpr)\n    aucs.append(viz.roc_auc)\n\nmean_tpr = np.mean(tprs, axis=0)\nmean_tpr[-1] = 1.0\nmean_auc = auc(mean_fpr, mean_tpr)\nstd_auc = np.std(aucs)\nax.plot(\n    mean_fpr,\n    mean_tpr,\n    color=\"b\",\n    label=r\"Mean ROC (AUC = %0.2f $\\pm$ %0.2f)\" % (mean_auc, std_auc),\n    lw=2,\n    alpha=0.8,\n)\n\nstd_tpr = np.std(tprs, axis=0)\ntprs_upper = np.minimum(mean_tpr + std_tpr, 1)\ntprs_lower = np.maximum(mean_tpr - std_tpr, 0)\nax.fill_between(\n    mean_fpr,\n    tprs_lower,\n    tprs_upper,\n    color=\"grey\",\n    alpha=0.2,\n    label=r\"$\\pm$ 1 std. dev.\",\n)\n\nax.set(\n    xlabel=\"False Positive Rate\",\n    ylabel=\"True Positive Rate\",\n    title=f\"Mean ROC curve with variability\\n(Positive label '{target_names[1]}')\",\n)\nax.legend(loc=\"lower right\")\nplt.show()"
+        "import matplotlib.pyplot as plt\n\nfrom sklearn import svm\nfrom sklearn.metrics import RocCurveDisplay, auc\nfrom sklearn.model_selection import StratifiedKFold\n\nn_splits = 6\ncv = StratifiedKFold(n_splits=n_splits)\nclassifier = svm.SVC(kernel=\"linear\", probability=True, random_state=random_state)\n\ntprs = []\naucs = []\nmean_fpr = np.linspace(0, 1, 100)\n\nfig, ax = plt.subplots(figsize=(6, 6))\nfor fold, (train, test) in enumerate(cv.split(X, y)):\n    classifier.fit(X[train], y[train])\n    viz = RocCurveDisplay.from_estimator(\n        classifier,\n        X[test],\n        y[test],\n        name=f\"ROC fold {fold}\",\n        curve_kwargs=dict(alpha=0.3, lw=1),\n        ax=ax,\n        plot_chance_level=(fold == n_splits - 1),\n    )\n    interp_tpr = np.interp(mean_fpr, viz.fpr, viz.tpr)\n    interp_tpr[0] = 0.0\n    tprs.append(interp_tpr)\n    aucs.append(viz.roc_auc)\n\nmean_tpr = np.mean(tprs, axis=0)\nmean_tpr[-1] = 1.0\nmean_auc = auc(mean_fpr, mean_tpr)\nstd_auc = np.std(aucs)\nax.plot(\n    mean_fpr,\n    mean_tpr,\n    color=\"b\",\n    label=r\"Mean ROC (AUC = %0.2f $\\pm$ %0.2f)\" % (mean_auc, std_auc),\n    lw=2,\n    alpha=0.8,\n)\n\nstd_tpr = np.std(tprs, axis=0)\ntprs_upper = np.minimum(mean_tpr + std_tpr, 1)\ntprs_lower = np.maximum(mean_tpr - std_tpr, 0)\nax.fill_between(\n    mean_fpr,\n    tprs_lower,\n    tprs_upper,\n    color=\"grey\",\n    alpha=0.2,\n    label=r\"$\\pm$ 1 std. dev.\",\n)\n\nax.set(\n    xlabel=\"False Positive Rate\",\n    ylabel=\"True Positive Rate\",\n    title=f\"Mean ROC curve with variability\\n(Positive label '{target_names[1]}')\",\n)\nax.legend(loc=\"lower right\")\nplt.show()"
       ]
     }
   ],

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -69,7 +69,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\n\nfrom sklearn.dummy import DummyClassifier\nfrom sklearn.metrics import DetCurveDisplay, RocCurveDisplay\n\nfig, [ax_roc, ax_det] = plt.subplots(1, 2, figsize=(11, 5))\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\nfor name, clf in classifiers.items():\n    (color, linestyle) = (\n        (\"black\", \"--\") if name == \"Non-informative baseline\" else (None, None)\n    )\n    clf.fit(X_train, y_train)\n    RocCurveDisplay.from_estimator(\n        clf, X_test, y_test, ax=ax_roc, name=name, color=color, linestyle=linestyle\n    )\n    DetCurveDisplay.from_estimator(\n        clf, X_test, y_test, ax=ax_det, name=name, color=color, linestyle=linestyle\n    )\n\nplt.legend()\nplt.show()"
+        "import matplotlib.pyplot as plt\n\nfrom sklearn.dummy import DummyClassifier\nfrom sklearn.metrics import DetCurveDisplay, RocCurveDisplay\n\nfig, [ax_roc, ax_det] = plt.subplots(1, 2, figsize=(11, 5))\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\nfor name, clf in classifiers.items():\n    (color, linestyle) = (\n        (\"black\", \"--\") if name == \"Non-informative baseline\" else (None, None)\n    )\n    clf.fit(X_train, y_train)\n    RocCurveDisplay.from_estimator(\n        clf,\n        X_test,\n        y_test,\n        ax=ax_roc,\n        name=name,\n        curve_kwargs=dict(color=color, linestyle=linestyle),\n    )\n    DetCurveDisplay.from_estimator(\n        clf, X_test, y_test, ax=ax_det, name=name, color=color, linestyle=linestyle\n    )\n\nplt.legend()\nplt.show()"
       ]
     },
     {

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -249,7 +249,7 @@
       },
       "outputs": [],
       "source": [
-        "def plot_roc_pr_curves(vanilla_model, tuned_model, *, title):\n    fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(21, 6))\n\n    linestyles = (\"dashed\", \"dotted\")\n    markerstyles = (\"o\", \">\")\n    colors = (\"tab:blue\", \"tab:orange\")\n    names = (\"Vanilla GBDT\", \"Tuned GBDT\")\n    for idx, (est, linestyle, marker, color, name) in enumerate(\n        zip((vanilla_model, tuned_model), linestyles, markerstyles, colors, names)\n    ):\n        decision_threshold = getattr(est, \"best_threshold_\", 0.5)\n        PrecisionRecallDisplay.from_estimator(\n            est,\n            X_test,\n            y_test,\n            pos_label=pos_label,\n            linestyle=linestyle,\n            color=color,\n            ax=axs[0],\n            name=name,\n        )\n        axs[0].plot(\n            scoring[\"recall\"](est, X_test, y_test),\n            scoring[\"precision\"](est, X_test, y_test),\n            marker,\n            markersize=10,\n            color=color,\n            label=f\"Cut-off point at probability of {decision_threshold:.2f}\",\n        )\n        RocCurveDisplay.from_estimator(\n            est,\n            X_test,\n            y_test,\n            pos_label=pos_label,\n            linestyle=linestyle,\n            color=color,\n            ax=axs[1],\n            name=name,\n            plot_chance_level=idx == 1,\n        )\n        axs[1].plot(\n            scoring[\"fpr\"](est, X_test, y_test),\n            scoring[\"tpr\"](est, X_test, y_test),\n            marker,\n            markersize=10,\n            color=color,\n            label=f\"Cut-off point at probability of {decision_threshold:.2f}\",\n        )\n\n    axs[0].set_title(\"Precision-Recall curve\")\n    axs[0].legend()\n    axs[1].set_title(\"ROC curve\")\n    axs[1].legend()\n\n    axs[2].plot(\n        tuned_model.cv_results_[\"thresholds\"],\n        tuned_model.cv_results_[\"scores\"],\n        color=\"tab:orange\",\n    )\n    axs[2].plot(\n        tuned_model.best_threshold_,\n        tuned_model.best_score_,\n        \"o\",\n        markersize=10,\n        color=\"tab:orange\",\n        label=\"Optimal cut-off point for the business metric\",\n    )\n    axs[2].legend()\n    axs[2].set_xlabel(\"Decision threshold (probability)\")\n    axs[2].set_ylabel(\"Objective score (using cost-matrix)\")\n    axs[2].set_title(\"Objective score as a function of the decision threshold\")\n    fig.suptitle(title)"
+        "def plot_roc_pr_curves(vanilla_model, tuned_model, *, title):\n    fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(21, 6))\n\n    linestyles = (\"dashed\", \"dotted\")\n    markerstyles = (\"o\", \">\")\n    colors = (\"tab:blue\", \"tab:orange\")\n    names = (\"Vanilla GBDT\", \"Tuned GBDT\")\n    for idx, (est, linestyle, marker, color, name) in enumerate(\n        zip((vanilla_model, tuned_model), linestyles, markerstyles, colors, names)\n    ):\n        decision_threshold = getattr(est, \"best_threshold_\", 0.5)\n        PrecisionRecallDisplay.from_estimator(\n            est,\n            X_test,\n            y_test,\n            pos_label=pos_label,\n            linestyle=linestyle,\n            color=color,\n            ax=axs[0],\n            name=name,\n        )\n        axs[0].plot(\n            scoring[\"recall\"](est, X_test, y_test),\n            scoring[\"precision\"](est, X_test, y_test),\n            marker,\n            markersize=10,\n            color=color,\n            label=f\"Cut-off point at probability of {decision_threshold:.2f}\",\n        )\n        RocCurveDisplay.from_estimator(\n            est,\n            X_test,\n            y_test,\n            pos_label=pos_label,\n            curve_kwargs=dict(linestyle=linestyle, color=color),\n            ax=axs[1],\n            name=name,\n            plot_chance_level=idx == 1,\n        )\n        axs[1].plot(\n            scoring[\"fpr\"](est, X_test, y_test),\n            scoring[\"tpr\"](est, X_test, y_test),\n            marker,\n            markersize=10,\n            color=color,\n            label=f\"Cut-off point at probability of {decision_threshold:.2f}\",\n        )\n\n    axs[0].set_title(\"Precision-Recall curve\")\n    axs[0].legend()\n    axs[1].set_title(\"ROC curve\")\n    axs[1].legend()\n\n    axs[2].plot(\n        tuned_model.cv_results_[\"thresholds\"],\n        tuned_model.cv_results_[\"scores\"],\n        color=\"tab:orange\",\n    )\n    axs[2].plot(\n        tuned_model.best_threshold_,\n        tuned_model.best_score_,\n        \"o\",\n        markersize=10,\n        color=\"tab:orange\",\n        label=\"Optimal cut-off point for the business metric\",\n    )\n    axs[2].legend()\n    axs[2].set_xlabel(\"Decision threshold (probability)\")\n    axs[2].set_ylabel(\"Objective score (using cost-matrix)\")\n    axs[2].set_title(\"Objective score as a function of the decision threshold\")\n    fig.suptitle(title)"
       ]
     },
     {

dev/_downloads/038d1885eb5f5ea53aca42da3031fe38/plot_document_clustering.zip

@@ -69,7 +69,7 @@
       },
       "outputs": [],
       "source": [
-        "rfc = RandomForestClassifier(n_estimators=10, random_state=42)\nrfc.fit(X_train, y_train)\nax = plt.gca()\nrfc_disp = RocCurveDisplay.from_estimator(rfc, X_test, y_test, ax=ax, alpha=0.8)\nsvc_disp.plot(ax=ax, alpha=0.8)\nplt.show()"
+        "rfc = RandomForestClassifier(n_estimators=10, random_state=42)\nrfc.fit(X_train, y_train)\nax = plt.gca()\nrfc_disp = RocCurveDisplay.from_estimator(\n    rfc, X_test, y_test, ax=ax, curve_kwargs=dict(alpha=0.8)\n)\nsvc_disp.plot(ax=ax, curve_kwargs=dict(alpha=0.8))\nplt.show()"
       ]
     }
   ],

dev/_downloads/03c018a16384c69f3a89e473650d57ee/plot_svm_margin.zip

@@ -116,7 +116,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\n\nfrom sklearn.metrics import RocCurveDisplay\n\ndisplay = RocCurveDisplay.from_predictions(\n    y_onehot_test[:, class_id],\n    y_score[:, class_id],\n    name=f\"{class_of_interest} vs the rest\",\n    color=\"darkorange\",\n    plot_chance_level=True,\n    despine=True,\n)\n_ = display.ax_.set(\n    xlabel=\"False Positive Rate\",\n    ylabel=\"True Positive Rate\",\n    title=\"One-vs-Rest ROC curves:\\nVirginica vs (Setosa & Versicolor)\",\n)"
+        "import matplotlib.pyplot as plt\n\nfrom sklearn.metrics import RocCurveDisplay\n\ndisplay = RocCurveDisplay.from_predictions(\n    y_onehot_test[:, class_id],\n    y_score[:, class_id],\n    name=f\"{class_of_interest} vs the rest\",\n    curve_kwargs=dict(color=\"darkorange\"),\n    plot_chance_level=True,\n    despine=True,\n)\n_ = display.ax_.set(\n    xlabel=\"False Positive Rate\",\n    ylabel=\"True Positive Rate\",\n    title=\"One-vs-Rest ROC curves:\\nVirginica vs (Setosa & Versicolor)\",\n)"
       ]
     },
     {
@@ -152,7 +152,7 @@
       },
       "outputs": [],
       "source": [
-        "display = RocCurveDisplay.from_predictions(\n    y_onehot_test.ravel(),\n    y_score.ravel(),\n    name=\"micro-average OvR\",\n    color=\"darkorange\",\n    plot_chance_level=True,\n    despine=True,\n)\n_ = display.ax_.set(\n    xlabel=\"False Positive Rate\",\n    ylabel=\"True Positive Rate\",\n    title=\"Micro-averaged One-vs-Rest\\nReceiver Operating Characteristic\",\n)"
+        "display = RocCurveDisplay.from_predictions(\n    y_onehot_test.ravel(),\n    y_score.ravel(),\n    name=\"micro-average OvR\",\n    curve_kwargs=dict(color=\"darkorange\"),\n    plot_chance_level=True,\n    despine=True,\n)\n_ = display.ax_.set(\n    xlabel=\"False Positive Rate\",\n    ylabel=\"True Positive Rate\",\n    title=\"Micro-averaged One-vs-Rest\\nReceiver Operating Characteristic\",\n)"
       ]
     },
     {
@@ -242,7 +242,7 @@
       },
       "outputs": [],
       "source": [
-        "from itertools import cycle\n\nfig, ax = plt.subplots(figsize=(6, 6))\n\nplt.plot(\n    fpr[\"micro\"],\n    tpr[\"micro\"],\n    label=f\"micro-average ROC curve (AUC = {roc_auc['micro']:.2f})\",\n    color=\"deeppink\",\n    linestyle=\":\",\n    linewidth=4,\n)\n\nplt.plot(\n    fpr[\"macro\"],\n    tpr[\"macro\"],\n    label=f\"macro-average ROC curve (AUC = {roc_auc['macro']:.2f})\",\n    color=\"navy\",\n    linestyle=\":\",\n    linewidth=4,\n)\n\ncolors = cycle([\"aqua\", \"darkorange\", \"cornflowerblue\"])\nfor class_id, color in zip(range(n_classes), colors):\n    RocCurveDisplay.from_predictions(\n        y_onehot_test[:, class_id],\n        y_score[:, class_id],\n        name=f\"ROC curve for {target_names[class_id]}\",\n        color=color,\n        ax=ax,\n        plot_chance_level=(class_id == 2),\n        despine=True,\n    )\n\n_ = ax.set(\n    xlabel=\"False Positive Rate\",\n    ylabel=\"True Positive Rate\",\n    title=\"Extension of Receiver Operating Characteristic\\nto One-vs-Rest multiclass\",\n)"
+        "from itertools import cycle\n\nfig, ax = plt.subplots(figsize=(6, 6))\n\nplt.plot(\n    fpr[\"micro\"],\n    tpr[\"micro\"],\n    label=f\"micro-average ROC curve (AUC = {roc_auc['micro']:.2f})\",\n    color=\"deeppink\",\n    linestyle=\":\",\n    linewidth=4,\n)\n\nplt.plot(\n    fpr[\"macro\"],\n    tpr[\"macro\"],\n    label=f\"macro-average ROC curve (AUC = {roc_auc['macro']:.2f})\",\n    color=\"navy\",\n    linestyle=\":\",\n    linewidth=4,\n)\n\ncolors = cycle([\"aqua\", \"darkorange\", \"cornflowerblue\"])\nfor class_id, color in zip(range(n_classes), colors):\n    RocCurveDisplay.from_predictions(\n        y_onehot_test[:, class_id],\n        y_score[:, class_id],\n        name=f\"ROC curve for {target_names[class_id]}\",\n        curve_kwargs=dict(color=color),\n        ax=ax,\n        plot_chance_level=(class_id == 2),\n        despine=True,\n    )\n\n_ = ax.set(\n    xlabel=\"False Positive Rate\",\n    ylabel=\"True Positive Rate\",\n    title=\"Extension of Receiver Operating Characteristic\\nto One-vs-Rest multiclass\",\n)"
       ]
     },
     {

dev/_downloads/04b9a7769df5b331f4d94e1d065b4311/plot_voting_decision_regions.zip

@@ -103,7 +103,12 @@
     )
     clf.fit(X_train, y_train)
     RocCurveDisplay.from_estimator(
-        clf, X_test, y_test, ax=ax_roc, name=name, color=color, linestyle=linestyle
+        clf,
+        X_test,
+        y_test,
+        ax=ax_roc,
+        name=name,
+        curve_kwargs=dict(color=color, linestyle=linestyle),
     )
     DetCurveDisplay.from_estimator(
         clf, X_test, y_test, ax=ax_det, name=name, color=color, linestyle=linestyle

dev/_downloads/053b58bbfc8177072856c743b2c93424/plot_varimax_fa.zip

@@ -129,7 +129,7 @@
     y_onehot_test[:, class_id],
     y_score[:, class_id],
     name=f"{class_of_interest} vs the rest",
-    color="darkorange",
+    curve_kwargs=dict(color="darkorange"),
     plot_chance_level=True,
     despine=True,
 )
@@ -165,7 +165,7 @@
     y_onehot_test.ravel(),
     y_score.ravel(),
     name="micro-average OvR",
-    color="darkorange",
+    curve_kwargs=dict(color="darkorange"),
     plot_chance_level=True,
     despine=True,
 )
@@ -290,7 +290,7 @@
         y_onehot_test[:, class_id],
         y_score[:, class_id],
         name=f"ROC curve for {target_names[class_id]}",
-        color=color,
+        curve_kwargs=dict(color=color),
         ax=ax,
         plot_chance_level=(class_id == 2),
         despine=True,

dev/_downloads/055e8313e28f2f3b5fd508054dfe5fe0/plot_roc_crossval.ipynb

@@ -54,6 +54,8 @@
 rfc = RandomForestClassifier(n_estimators=10, random_state=42)
 rfc.fit(X_train, y_train)
 ax = plt.gca()
-rfc_disp = RocCurveDisplay.from_estimator(rfc, X_test, y_test, ax=ax, alpha=0.8)
-svc_disp.plot(ax=ax, alpha=0.8)
+rfc_disp = RocCurveDisplay.from_estimator(
+    rfc, X_test, y_test, ax=ax, curve_kwargs=dict(alpha=0.8)
+)
+svc_disp.plot(ax=ax, curve_kwargs=dict(alpha=0.8))
 plt.show()

dev/_downloads/06c18f4675ecd124f98537d05e10abd0/plot_nca_dim_reduction.zip

@@ -321,8 +321,7 @@ def plot_roc_pr_curves(vanilla_model, tuned_model, *, title):
             X_test,
             y_test,
             pos_label=pos_label,
-            linestyle=linestyle,
-            color=color,
+            curve_kwargs=dict(linestyle=linestyle, color=color),
             ax=axs[1],
             name=name,
             plot_chance_level=idx == 1,

dev/_downloads/06e5cfec52777b1f220312b4ada9469d/plot_document_classification_20newsgroups.zip

@@ -355,8 +355,7 @@ def fit_predict(estimator, X):
         ax=ax,
         plot_chance_level=(model_idx == len(n_neighbors_list) - 1),
         chance_level_kw={"linestyle": (0, (1, 10))},
-        linestyle=linestyle,
-        linewidth=2,
+        curve_kwargs=dict(linestyle=linestyle, linewidth=2),
     )
 _ = ax.set_title("RobustScaler with varying n_neighbors\non forestcover dataset")
 
@@ -395,8 +394,7 @@ def fit_predict(estimator, X):
         ax=ax,
         plot_chance_level=(model_idx == len(preprocessor_list) - 1),
         chance_level_kw={"linestyle": (0, (1, 10))},
-        linestyle=linestyle,
-        linewidth=2,
+        curve_kwargs=dict(linestyle=linestyle, linewidth=2),
     )
 _ = ax.set_title("Fixed n_neighbors with varying preprocessing\non forestcover dataset")
 
@@ -447,8 +445,7 @@ def fit_predict(estimator, X):
         ax=ax,
         plot_chance_level=(model_idx == len(preprocessor_list) - 1),
         chance_level_kw={"linestyle": (0, (1, 10))},
-        linestyle=linestyle,
-        linewidth=2,
+        curve_kwargs=dict(linestyle=linestyle, linewidth=2),
     )
 ax.set_title(
     "Fixed n_neighbors with varying preprocessing\non cardiotocography dataset"