Pushing the docs to dev/ for branch: main, commit d400723a2112f15c5d5b4d40dfac2ed8a19cca5c

Author: sklearn-ci

dev/_downloads/00ae629d652473137a3905a5e08ea815/plot_iris_dtc.py

@@ -25,7 +25,11 @@
 # Display the decision functions of trees trained on all pairs of features.
 import numpy as np
 import matplotlib.pyplot as plt
+
+from sklearn.datasets import load_iris
 from sklearn.tree import DecisionTreeClassifier
+from sklearn.inspection import DecisionBoundaryDisplay
+
 
 # Parameters
 n_classes = 3
@@ -42,21 +46,17 @@
     clf = DecisionTreeClassifier().fit(X, y)
 
     # Plot the decision boundary
-    plt.subplot(2, 3, pairidx + 1)
-
-    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
-    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
-    xx, yy = np.meshgrid(
-        np.arange(x_min, x_max, plot_step), np.arange(y_min, y_max, plot_step)
-    )
+    ax = plt.subplot(2, 3, pairidx + 1)
     plt.tight_layout(h_pad=0.5, w_pad=0.5, pad=2.5)
-
-    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
-    Z = Z.reshape(xx.shape)
-    cs = plt.contourf(xx, yy, Z, cmap=plt.cm.RdYlBu)
-
-    plt.xlabel(iris.feature_names[pair[0]])
-    plt.ylabel(iris.feature_names[pair[1]])
+    DecisionBoundaryDisplay.from_estimator(
+        clf,
+        X,
+        cmap=plt.cm.RdYlBu,
+        response_method="predict",
+        ax=ax,
+        xlabel=iris.feature_names[pair[0]],
+        ylabel=iris.feature_names[pair[1]],
+    )
 
     # Plot the training points
     for i, color in zip(range(n_classes), plot_colors):

dev/_downloads/036b9372e2e7802453cbb994da7a6786/plot_linearsvc_support_vectors.py

@@ -13,6 +13,7 @@
 import matplotlib.pyplot as plt
 from sklearn.datasets import make_blobs
 from sklearn.svm import LinearSVC
+from sklearn.inspection import DecisionBoundaryDisplay
 
 X, y = make_blobs(n_samples=40, centers=2, random_state=0)
 
@@ -32,17 +33,12 @@
     plt.subplot(1, 2, i + 1)
     plt.scatter(X[:, 0], X[:, 1], c=y, s=30, cmap=plt.cm.Paired)
     ax = plt.gca()
-    xlim = ax.get_xlim()
-    ylim = ax.get_ylim()
-    xx, yy = np.meshgrid(
-        np.linspace(xlim[0], xlim[1], 50), np.linspace(ylim[0], ylim[1], 50)
-    )
-    Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
-    Z = Z.reshape(xx.shape)
-    plt.contour(
-        xx,
-        yy,
-        Z,
+    DecisionBoundaryDisplay.from_estimator(
+        clf,
+        X,
+        ax=ax,
+        grid_resolution=50,
+        plot_method="contour",
         colors="k",
         levels=[-1, 0, 1],
         alpha=0.5,

dev/_downloads/06ffeb4f0ded6447302acd5a712f8490/plot_nearest_centroid.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib.colors import ListedColormap\nfrom sklearn import datasets\nfrom sklearn.neighbors import NearestCentroid\n\nn_neighbors = 15\n\n# import some data to play with\niris = datasets.load_iris()\n# we only take the first two features. We could avoid this ugly\n# slicing by using a two-dim dataset\nX = iris.data[:, :2]\ny = iris.target\n\nh = 0.02  # step size in the mesh\n\n# Create color maps\ncmap_light = ListedColormap([\"orange\", \"cyan\", \"cornflowerblue\"])\ncmap_bold = ListedColormap([\"darkorange\", \"c\", \"darkblue\"])\n\nfor shrinkage in [None, 0.2]:\n    # we create an instance of Neighbours Classifier and fit the data.\n    clf = NearestCentroid(shrink_threshold=shrinkage)\n    clf.fit(X, y)\n    y_pred = clf.predict(X)\n    print(shrinkage, np.mean(y == y_pred))\n    # Plot the decision boundary. For that, we will assign a color to each\n    # point in the mesh [x_min, x_max]x[y_min, y_max].\n    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1\n    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1\n    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))\n    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])\n\n    # Put the result into a color plot\n    Z = Z.reshape(xx.shape)\n    plt.figure()\n    plt.pcolormesh(xx, yy, Z, cmap=cmap_light)\n\n    # Plot also the training points\n    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold, edgecolor=\"k\", s=20)\n    plt.title(\"3-Class classification (shrink_threshold=%r)\" % shrinkage)\n    plt.axis(\"tight\")\n\nplt.show()"
+        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib.colors import ListedColormap\nfrom sklearn import datasets\nfrom sklearn.neighbors import NearestCentroid\nfrom sklearn.inspection import DecisionBoundaryDisplay\n\nn_neighbors = 15\n\n# import some data to play with\niris = datasets.load_iris()\n# we only take the first two features. We could avoid this ugly\n# slicing by using a two-dim dataset\nX = iris.data[:, :2]\ny = iris.target\n\n# Create color maps\ncmap_light = ListedColormap([\"orange\", \"cyan\", \"cornflowerblue\"])\ncmap_bold = ListedColormap([\"darkorange\", \"c\", \"darkblue\"])\n\nfor shrinkage in [None, 0.2]:\n    # we create an instance of Neighbours Classifier and fit the data.\n    clf = NearestCentroid(shrink_threshold=shrinkage)\n    clf.fit(X, y)\n    y_pred = clf.predict(X)\n    print(shrinkage, np.mean(y == y_pred))\n\n    _, ax = plt.subplots()\n    DecisionBoundaryDisplay.from_estimator(\n        clf, X, cmap=cmap_light, ax=ax, response_method=\"predict\"\n    )\n\n    # Plot also the training points\n    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold, edgecolor=\"k\", s=20)\n    plt.title(\"3-Class classification (shrink_threshold=%r)\" % shrinkage)\n    plt.axis(\"tight\")\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn import svm, datasets\n\n# import some data to play with\niris = datasets.load_iris()\nX = iris.data[:, :2]  # we only take the first two features. We could\n# avoid this ugly slicing by using a two-dim dataset\nY = iris.target\n\n\ndef my_kernel(X, Y):\n    \"\"\"\n    We create a custom kernel:\n\n                 (2  0)\n    k(X, Y) = X  (    ) Y.T\n                 (0  1)\n    \"\"\"\n    M = np.array([[2, 0], [0, 1.0]])\n    return np.dot(np.dot(X, M), Y.T)\n\n\nh = 0.02  # step size in the mesh\n\n# we create an instance of SVM and fit out data.\nclf = svm.SVC(kernel=my_kernel)\nclf.fit(X, Y)\n\n# Plot the decision boundary. For that, we will assign a color to each\n# point in the mesh [x_min, x_max]x[y_min, y_max].\nx_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1\ny_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1\nxx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))\nZ = clf.predict(np.c_[xx.ravel(), yy.ravel()])\n\n# Put the result into a color plot\nZ = Z.reshape(xx.shape)\nplt.pcolormesh(xx, yy, Z, cmap=plt.cm.Paired)\n\n# Plot also the training points\nplt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired, edgecolors=\"k\")\nplt.title(\"3-Class classification using Support Vector Machine with custom kernel\")\nplt.axis(\"tight\")\nplt.show()"
+        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn import svm, datasets\nfrom sklearn.inspection import DecisionBoundaryDisplay\n\n# import some data to play with\niris = datasets.load_iris()\nX = iris.data[:, :2]  # we only take the first two features. We could\n# avoid this ugly slicing by using a two-dim dataset\nY = iris.target\n\n\ndef my_kernel(X, Y):\n    \"\"\"\n    We create a custom kernel:\n\n                 (2  0)\n    k(X, Y) = X  (    ) Y.T\n                 (0  1)\n    \"\"\"\n    M = np.array([[2, 0], [0, 1.0]])\n    return np.dot(np.dot(X, M), Y.T)\n\n\nh = 0.02  # step size in the mesh\n\n# we create an instance of SVM and fit out data.\nclf = svm.SVC(kernel=my_kernel)\nclf.fit(X, Y)\n\nax = plt.gca()\nDecisionBoundaryDisplay.from_estimator(\n    clf,\n    X,\n    cmap=plt.cm.Paired,\n    ax=ax,\n    response_method=\"predict\",\n    plot_method=\"pcolormesh\",\n    shading=\"auto\",\n)\n\n# Plot also the training points\nplt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired, edgecolors=\"k\")\nplt.title(\"3-Class classification using Support Vector Machine with custom kernel\")\nplt.axis(\"tight\")\nplt.show()"
       ]
     }
   ],

dev/_downloads/1160eee327e01cad702c4964e1c69f45/plot_custom_kernel.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import make_blobs\nfrom sklearn.svm import LinearSVC\n\nX, y = make_blobs(n_samples=40, centers=2, random_state=0)\n\nplt.figure(figsize=(10, 5))\nfor i, C in enumerate([1, 100]):\n    # \"hinge\" is the standard SVM loss\n    clf = LinearSVC(C=C, loss=\"hinge\", random_state=42).fit(X, y)\n    # obtain the support vectors through the decision function\n    decision_function = clf.decision_function(X)\n    # we can also calculate the decision function manually\n    # decision_function = np.dot(X, clf.coef_[0]) + clf.intercept_[0]\n    # The support vectors are the samples that lie within the margin\n    # boundaries, whose size is conventionally constrained to 1\n    support_vector_indices = np.where(np.abs(decision_function) <= 1 + 1e-15)[0]\n    support_vectors = X[support_vector_indices]\n\n    plt.subplot(1, 2, i + 1)\n    plt.scatter(X[:, 0], X[:, 1], c=y, s=30, cmap=plt.cm.Paired)\n    ax = plt.gca()\n    xlim = ax.get_xlim()\n    ylim = ax.get_ylim()\n    xx, yy = np.meshgrid(\n        np.linspace(xlim[0], xlim[1], 50), np.linspace(ylim[0], ylim[1], 50)\n    )\n    Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])\n    Z = Z.reshape(xx.shape)\n    plt.contour(\n        xx,\n        yy,\n        Z,\n        colors=\"k\",\n        levels=[-1, 0, 1],\n        alpha=0.5,\n        linestyles=[\"--\", \"-\", \"--\"],\n    )\n    plt.scatter(\n        support_vectors[:, 0],\n        support_vectors[:, 1],\n        s=100,\n        linewidth=1,\n        facecolors=\"none\",\n        edgecolors=\"k\",\n    )\n    plt.title(\"C=\" + str(C))\nplt.tight_layout()\nplt.show()"
+        "import numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import make_blobs\nfrom sklearn.svm import LinearSVC\nfrom sklearn.inspection import DecisionBoundaryDisplay\n\nX, y = make_blobs(n_samples=40, centers=2, random_state=0)\n\nplt.figure(figsize=(10, 5))\nfor i, C in enumerate([1, 100]):\n    # \"hinge\" is the standard SVM loss\n    clf = LinearSVC(C=C, loss=\"hinge\", random_state=42).fit(X, y)\n    # obtain the support vectors through the decision function\n    decision_function = clf.decision_function(X)\n    # we can also calculate the decision function manually\n    # decision_function = np.dot(X, clf.coef_[0]) + clf.intercept_[0]\n    # The support vectors are the samples that lie within the margin\n    # boundaries, whose size is conventionally constrained to 1\n    support_vector_indices = np.where(np.abs(decision_function) <= 1 + 1e-15)[0]\n    support_vectors = X[support_vector_indices]\n\n    plt.subplot(1, 2, i + 1)\n    plt.scatter(X[:, 0], X[:, 1], c=y, s=30, cmap=plt.cm.Paired)\n    ax = plt.gca()\n    DecisionBoundaryDisplay.from_estimator(\n        clf,\n        X,\n        ax=ax,\n        grid_resolution=50,\n        plot_method=\"contour\",\n        colors=\"k\",\n        levels=[-1, 0, 1],\n        alpha=0.5,\n        linestyles=[\"--\", \"-\", \"--\"],\n    )\n    plt.scatter(\n        support_vectors[:, 0],\n        support_vectors[:, 1],\n        s=100,\n        linewidth=1,\n        facecolors=\"none\",\n        edgecolors=\"k\",\n    )\n    plt.title(\"C=\" + str(C))\nplt.tight_layout()\nplt.show()"
       ]
     }
   ],

dev/_downloads/12a392e818ac5fa47dd91461855f3f77/plot_linearsvc_support_vectors.ipynb

@@ -25,14 +25,14 @@
 
 from itertools import product
 
-import numpy as np
 import matplotlib.pyplot as plt
 
 from sklearn import datasets
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.svm import SVC
 from sklearn.ensemble import VotingClassifier
+from sklearn.inspection import DecisionBoundaryDisplay
 
 # Loading some example data
 iris = datasets.load_iris()
@@ -55,22 +55,15 @@
 eclf.fit(X, y)
 
 # Plotting decision regions
-x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
-y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
-xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1), np.arange(y_min, y_max, 0.1))
-
 f, axarr = plt.subplots(2, 2, sharex="col", sharey="row", figsize=(10, 8))
-
 for idx, clf, tt in zip(
     product([0, 1], [0, 1]),
     [clf1, clf2, clf3, eclf],
     ["Decision Tree (depth=4)", "KNN (k=7)", "Kernel SVM", "Soft Voting"],
 ):
-
-    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
-    Z = Z.reshape(xx.shape)
-
-    axarr[idx[0], idx[1]].contourf(xx, yy, Z, alpha=0.4)
+    DecisionBoundaryDisplay.from_estimator(
+        clf, X, alpha=0.4, ax=axarr[idx[0], idx[1]], response_method="predict"
+    )
     axarr[idx[0], idx[1]].scatter(X[:, 0], X[:, 1], c=y, s=20, edgecolor="k")
     axarr[idx[0], idx[1]].set_title(tt)
 

dev/_downloads/12b6dbb270865986bd1c9bbf7ce24cb0/plot_voting_decision_regions.py

@@ -13,6 +13,7 @@
 from matplotlib.colors import ListedColormap
 from sklearn import datasets
 from sklearn.neighbors import NearestCentroid
+from sklearn.inspection import DecisionBoundaryDisplay
 
 n_neighbors = 15
 
@@ -23,8 +24,6 @@
 X = iris.data[:, :2]
 y = iris.target
 
-h = 0.02  # step size in the mesh
-
 # Create color maps
 cmap_light = ListedColormap(["orange", "cyan", "cornflowerblue"])
 cmap_bold = ListedColormap(["darkorange", "c", "darkblue"])
@@ -35,17 +34,11 @@
     clf.fit(X, y)
     y_pred = clf.predict(X)
     print(shrinkage, np.mean(y == y_pred))
-    # Plot the decision boundary. For that, we will assign a color to each
-    # point in the mesh [x_min, x_max]x[y_min, y_max].
-    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
-    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
-    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
-    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
-
-    # Put the result into a color plot
-    Z = Z.reshape(xx.shape)
-    plt.figure()
-    plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
+
+    _, ax = plt.subplots()
+    DecisionBoundaryDisplay.from_estimator(
+        clf, X, cmap=cmap_light, ax=ax, response_method="predict"
+    )
 
     # Plot also the training points
     plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold, edgecolor="k", s=20)

dev/_downloads/1ee82dc6471486cb5b088fc473cd945b/plot_nearest_centroid.py

@@ -40,8 +40,7 @@
 from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
 from sklearn.naive_bayes import GaussianNB
 from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
-
-h = 0.02  # step size in the mesh
+from sklearn.inspection import DecisionBoundaryDisplay
 
 names = [
     "Nearest Neighbors",
@@ -95,7 +94,6 @@
 
     x_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5
     y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5
-    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
 
     # just plot the dataset first
     cm = plt.cm.RdBu
@@ -109,8 +107,8 @@
     ax.scatter(
         X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6, edgecolors="k"
     )
-    ax.set_xlim(xx.min(), xx.max())
-    ax.set_ylim(yy.min(), yy.max())
+    ax.set_xlim(x_min, x_max)
+    ax.set_ylim(y_min, y_max)
     ax.set_xticks(())
     ax.set_yticks(())
     i += 1
@@ -120,17 +118,9 @@
         ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
         clf.fit(X_train, y_train)
         score = clf.score(X_test, y_test)
-
-        # Plot the decision boundary. For that, we will assign a color to each
-        # point in the mesh [x_min, x_max]x[y_min, y_max].
-        if hasattr(clf, "decision_function"):
-            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
-        else:
-            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
-
-        # Put the result into a color plot
-        Z = Z.reshape(xx.shape)
-        ax.contourf(xx, yy, Z, cmap=cm, alpha=0.8)
+        DecisionBoundaryDisplay.from_estimator(
+            clf, X, cmap=cm, alpha=0.8, ax=ax, eps=0.5
+        )
 
         # Plot the training points
         ax.scatter(
@@ -146,15 +136,15 @@
             alpha=0.6,
         )
 
-        ax.set_xlim(xx.min(), xx.max())
-        ax.set_ylim(yy.min(), yy.max())
+        ax.set_xlim(x_min, x_max)
+        ax.set_ylim(y_min, y_max)
         ax.set_xticks(())
         ax.set_yticks(())
         if ds_cnt == 0:
             ax.set_title(name)
         ax.text(
-            xx.max() - 0.3,
-            yy.min() + 0.3,
+            x_max - 0.3,
+            y_min + 0.3,
             ("%.2f" % score).lstrip("0"),
             size=15,
             horizontalalignment="right",

dev/_downloads/2da0534ab0e0c8241033bcc2d912e419/plot_classifier_comparison.py

@@ -11,6 +11,7 @@
 import numpy as np
 import matplotlib.pyplot as plt
 from sklearn import svm, datasets
+from sklearn.inspection import DecisionBoundaryDisplay
 
 # import some data to play with
 iris = datasets.load_iris()
@@ -37,16 +38,16 @@ def my_kernel(X, Y):
 clf = svm.SVC(kernel=my_kernel)
 clf.fit(X, Y)
 
-# Plot the decision boundary. For that, we will assign a color to each
-# point in the mesh [x_min, x_max]x[y_min, y_max].
-x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
-y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
-xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
-Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
-
-# Put the result into a color plot
-Z = Z.reshape(xx.shape)
-plt.pcolormesh(xx, yy, Z, cmap=plt.cm.Paired)
+ax = plt.gca()
+DecisionBoundaryDisplay.from_estimator(
+    clf,
+    X,
+    cmap=plt.cm.Paired,
+    ax=ax,
+    response_method="predict",
+    plot_method="pcolormesh",
+    shading="auto",
+)
 
 # Plot also the training points
 plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired, edgecolors="k")