Pushing the docs to dev/ for branch: master, commit e650a207efc9dd33556b1b9678b043f73a18aecb

Author: sklearn-ci

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import svm, datasets\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.utils.multiclass import unique_labels\n\n# import some data to play with\niris = datasets.load_iris()\nX = iris.data\ny = iris.target\nclass_names = iris.target_names\n\n# Split the data into a training set and a test set\nX_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)\n\n# Run classifier, using a model that is too regularized (C too low) to see\n# the impact on the results\nclassifier = svm.SVC(kernel='linear', C=0.01)\ny_pred = classifier.fit(X_train, y_train).predict(X_test)\n\n\ndef plot_confusion_matrix(y_true, y_pred, classes,\n                          normalize=False,\n                          title=None,\n                          cmap=plt.cm.Blues):\n    \"\"\"\n    This function prints and plots the confusion matrix.\n    Normalization can be applied by setting `normalize=True`.\n    \"\"\"\n    if not title:\n        if normalize:\n            title = 'Normalized confusion matrix'\n        else:\n            title = 'Confusion matrix, without normalization'\n\n    # Compute confusion matrix\n    cm = confusion_matrix(y_true, y_pred)\n    # Only use the labels that appear in the data\n    classes = classes[unique_labels(y_true, y_pred)]\n    if normalize:\n        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n        print(\"Normalized confusion matrix\")\n    else:\n        print('Confusion matrix, without normalization')\n\n    print(cm)\n\n    fig, ax = plt.subplots()\n    im = ax.imshow(cm, interpolation='nearest', cmap=cmap)\n    ax.figure.colorbar(im, ax=ax)\n    # We want to show all ticks...\n    ax.set(xticks=np.arange(cm.shape[1]),\n           yticks=np.arange(cm.shape[0]),\n           # ... and label them with the respective list entries\n           xticklabels=classes, yticklabels=classes,\n           title=title,\n           ylabel='True label',\n           xlabel='Predicted label')\n\n    # Rotate the tick labels and set their alignment.\n    plt.setp(ax.get_xticklabels(), rotation=45, ha=\"right\",\n             rotation_mode=\"anchor\")\n\n    # Loop over data dimensions and create text annotations.\n    fmt = '.2f' if normalize else 'd'\n    thresh = cm.max() / 2.\n    for i in range(cm.shape[0]):\n        for j in range(cm.shape[1]):\n            ax.text(j, i, format(cm[i, j], fmt),\n                    ha=\"center\", va=\"center\",\n                    color=\"white\" if cm[i, j] > thresh else \"black\")\n    fig.tight_layout()\n    return ax\n\n\nnp.set_printoptions(precision=2)\n\n# Plot non-normalized confusion matrix\nplot_confusion_matrix(y_test, y_pred, classes=class_names,\n                      title='Confusion matrix, without normalization')\n\n# Plot normalized confusion matrix\nplot_confusion_matrix(y_test, y_pred, classes=class_names, normalize=True,\n                      title='Normalized confusion matrix')\n\nplt.show()"
+        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import svm, datasets\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import plot_confusion_matrix\n\n# import some data to play with\niris = datasets.load_iris()\nX = iris.data\ny = iris.target\nclass_names = iris.target_names\n\n# Split the data into a training set and a test set\nX_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)\n\n# Run classifier, using a model that is too regularized (C too low) to see\n# the impact on the results\nclassifier = svm.SVC(kernel='linear', C=0.01).fit(X_train, y_train)\n\nnp.set_printoptions(precision=2)\n\n# Plot non-normalized confusion matrix\ntitles_options = [(\"Confusion matrix, without normalization\", None),\n                  (\"Normalized confusion matrix\", 'true')]\nfor title, normalize in titles_options:\n    disp = plot_confusion_matrix(classifier, X_test, y_test,\n                                 display_labels=class_names,\n                                 cmap=plt.cm.Blues,\n                                 normalize=normalize)\n    disp.ax_.set_title(title)\n\n    print(title)\n    print(disp.confusion_matrix)\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/3a6b0f407d8829a616b0eff2bf71828a/plot_confusion_matrix.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>\n# License: BSD 3 clause\n\n# Standard scientific Python imports\nimport matplotlib.pyplot as plt\n\n# Import datasets, classifiers and performance metrics\nfrom sklearn import datasets, svm, metrics\nfrom sklearn.model_selection import train_test_split\n\n# The digits dataset\ndigits = datasets.load_digits()\n\n# The data that we are interested in is made of 8x8 images of digits, let's\n# have a look at the first 4 images, stored in the `images` attribute of the\n# dataset.  If we were working from image files, we could load them using\n# matplotlib.pyplot.imread.  Note that each image must have the same size. For these\n# images, we know which digit they represent: it is given in the 'target' of\n# the dataset.\nimages_and_labels = list(zip(digits.images, digits.target))\nfor index, (image, label) in enumerate(images_and_labels[:4]):\n    plt.subplot(2, 4, index + 1)\n    plt.axis('off')\n    plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')\n    plt.title('Training: %i' % label)\n\n# To apply a classifier on this data, we need to flatten the image, to\n# turn the data in a (samples, feature) matrix:\nn_samples = len(digits.images)\ndata = digits.images.reshape((n_samples, -1))\n\n# Create a classifier: a support vector classifier\nclassifier = svm.SVC(gamma=0.001)\n\n# Split data into train and test subsets\nX_train, X_test, y_train, y_test = train_test_split(\n    data, digits.target, test_size=0.5, shuffle=False)\n\n# We learn the digits on the first half of the digits\nclassifier.fit(X_train, y_train)\n\n# Now predict the value of the digit on the second half:\npredicted = classifier.predict(X_test)\n\nprint(\"Classification report for classifier %s:\\n%s\\n\"\n      % (classifier, metrics.classification_report(y_test, predicted)))\nprint(\"Confusion matrix:\\n%s\" % metrics.confusion_matrix(y_test, predicted))\n\nimages_and_predictions = list(zip(digits.images[n_samples // 2:], predicted))\nfor index, (image, prediction) in enumerate(images_and_predictions[:4]):\n    plt.subplot(2, 4, index + 5)\n    plt.axis('off')\n    plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')\n    plt.title('Prediction: %i' % prediction)\n\nplt.show()"
+        "print(__doc__)\n\n# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>\n# License: BSD 3 clause\n\n# Standard scientific Python imports\nimport matplotlib.pyplot as plt\n\n# Import datasets, classifiers and performance metrics\nfrom sklearn import datasets, svm, metrics\nfrom sklearn.model_selection import train_test_split\n\n# The digits dataset\ndigits = datasets.load_digits()\n\n# The data that we are interested in is made of 8x8 images of digits, let's\n# have a look at the first 4 images, stored in the `images` attribute of the\n# dataset.  If we were working from image files, we could load them using\n# matplotlib.pyplot.imread.  Note that each image must have the same size. For these\n# images, we know which digit they represent: it is given in the 'target' of\n# the dataset.\n_, axes = plt.subplots(2, 4)\nimages_and_labels = list(zip(digits.images, digits.target))\nfor ax, (image, label) in zip(axes[0, :], images_and_labels[:4]):\n    ax.set_axis_off()\n    ax.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')\n    ax.set_title('Training: %i' % label)\n\n# To apply a classifier on this data, we need to flatten the image, to\n# turn the data in a (samples, feature) matrix:\nn_samples = len(digits.images)\ndata = digits.images.reshape((n_samples, -1))\n\n# Create a classifier: a support vector classifier\nclassifier = svm.SVC(gamma=0.001)\n\n# Split data into train and test subsets\nX_train, X_test, y_train, y_test = train_test_split(\n    data, digits.target, test_size=0.5, shuffle=False)\n\n# We learn the digits on the first half of the digits\nclassifier.fit(X_train, y_train)\n\n# Now predict the value of the digit on the second half:\npredicted = classifier.predict(X_test)\n\nimages_and_predictions = list(zip(digits.images[n_samples // 2:], predicted))\nfor ax, (image, prediction) in zip(axes[1, :], images_and_predictions[:4]):\n    ax.set_axis_off()\n    ax.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')\n    ax.set_title('Prediction: %i' % prediction)\n\nprint(\"Classification report for classifier %s:\\n%s\\n\"\n      % (classifier, metrics.classification_report(y_test, predicted)))\ndisp = metrics.plot_confusion_matrix(classifier, X_test, y_test)\ndisp.figure_.suptitle(\"Confusion Matrix\")\nprint(\"Confusion matrix:\\n%s\" % disp.confusion_matrix)\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/622fb50f5e367eda84eb7c32d306f659/plot_digits_classification.ipynb

@@ -31,8 +31,7 @@
 
 from sklearn import svm, datasets
 from sklearn.model_selection import train_test_split
-from sklearn.metrics import confusion_matrix
-from sklearn.utils.multiclass import unique_labels
+from sklearn.metrics import plot_confusion_matrix
 
 # import some data to play with
 iris = datasets.load_iris()
@@ -45,72 +44,21 @@
 
 # Run classifier, using a model that is too regularized (C too low) to see
 # the impact on the results
-classifier = svm.SVC(kernel='linear', C=0.01)
-y_pred = classifier.fit(X_train, y_train).predict(X_test)
-
-
-def plot_confusion_matrix(y_true, y_pred, classes,
-                          normalize=False,
-                          title=None,
-                          cmap=plt.cm.Blues):
-    """
-    This function prints and plots the confusion matrix.
-    Normalization can be applied by setting `normalize=True`.
-    """
-    if not title:
-        if normalize:
-            title = 'Normalized confusion matrix'
-        else:
-            title = 'Confusion matrix, without normalization'
-
-    # Compute confusion matrix
-    cm = confusion_matrix(y_true, y_pred)
-    # Only use the labels that appear in the data
-    classes = classes[unique_labels(y_true, y_pred)]
-    if normalize:
-        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
-        print("Normalized confusion matrix")
-    else:
-        print('Confusion matrix, without normalization')
-
-    print(cm)
-
-    fig, ax = plt.subplots()
-    im = ax.imshow(cm, interpolation='nearest', cmap=cmap)
-    ax.figure.colorbar(im, ax=ax)
-    # We want to show all ticks...
-    ax.set(xticks=np.arange(cm.shape[1]),
-           yticks=np.arange(cm.shape[0]),
-           # ... and label them with the respective list entries
-           xticklabels=classes, yticklabels=classes,
-           title=title,
-           ylabel='True label',
-           xlabel='Predicted label')
-
-    # Rotate the tick labels and set their alignment.
-    plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
-             rotation_mode="anchor")
-
-    # Loop over data dimensions and create text annotations.
-    fmt = '.2f' if normalize else 'd'
-    thresh = cm.max() / 2.
-    for i in range(cm.shape[0]):
-        for j in range(cm.shape[1]):
-            ax.text(j, i, format(cm[i, j], fmt),
-                    ha="center", va="center",
-                    color="white" if cm[i, j] > thresh else "black")
-    fig.tight_layout()
-    return ax
-
+classifier = svm.SVC(kernel='linear', C=0.01).fit(X_train, y_train)
 
 np.set_printoptions(precision=2)
 
 # Plot non-normalized confusion matrix
-plot_confusion_matrix(y_test, y_pred, classes=class_names,
-                      title='Confusion matrix, without normalization')
-
-# Plot normalized confusion matrix
-plot_confusion_matrix(y_test, y_pred, classes=class_names, normalize=True,
-                      title='Normalized confusion matrix')
+titles_options = [("Confusion matrix, without normalization", None),
+                  ("Normalized confusion matrix", 'true')]
+for title, normalize in titles_options:
+    disp = plot_confusion_matrix(classifier, X_test, y_test,
+                                 display_labels=class_names,
+                                 cmap=plt.cm.Blues,
+                                 normalize=normalize)
+    disp.ax_.set_title(title)
+
+    print(title)
+    print(disp.confusion_matrix)
 
 plt.show()

dev/_downloads/7e0e90df87894c2fadaf3004c5316545/plot_confusion_matrix.py

@@ -31,12 +31,12 @@
 # matplotlib.pyplot.imread.  Note that each image must have the same size. For these
 # images, we know which digit they represent: it is given in the 'target' of
 # the dataset.
+_, axes = plt.subplots(2, 4)
 images_and_labels = list(zip(digits.images, digits.target))
-for index, (image, label) in enumerate(images_and_labels[:4]):
-    plt.subplot(2, 4, index + 1)
-    plt.axis('off')
-    plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
-    plt.title('Training: %i' % label)
+for ax, (image, label) in zip(axes[0, :], images_and_labels[:4]):
+    ax.set_axis_off()
+    ax.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
+    ax.set_title('Training: %i' % label)
 
 # To apply a classifier on this data, we need to flatten the image, to
 # turn the data in a (samples, feature) matrix:
@@ -56,15 +56,16 @@
 # Now predict the value of the digit on the second half:
 predicted = classifier.predict(X_test)
 
+images_and_predictions = list(zip(digits.images[n_samples // 2:], predicted))
+for ax, (image, prediction) in zip(axes[1, :], images_and_predictions[:4]):
+    ax.set_axis_off()
+    ax.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
+    ax.set_title('Prediction: %i' % prediction)
+
 print("Classification report for classifier %s:\n%s\n"
       % (classifier, metrics.classification_report(y_test, predicted)))
-print("Confusion matrix:\n%s" % metrics.confusion_matrix(y_test, predicted))
-
-images_and_predictions = list(zip(digits.images[n_samples // 2:], predicted))
-for index, (image, prediction) in enumerate(images_and_predictions[:4]):
-    plt.subplot(2, 4, index + 5)
-    plt.axis('off')
-    plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
-    plt.title('Prediction: %i' % prediction)
+disp = metrics.plot_confusion_matrix(classifier, X_test, y_test)
+disp.figure_.suptitle("Confusion Matrix")
+print("Confusion matrix:\n%s" % disp.confusion_matrix)
 
 plt.show()