Pushing the docs to dev/ for branch: main, commit cb15a82e6439feda50b0605d70ce6d06c2eac7fd

Author: sklearn-ci

dev/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: f22854fbba193671ecfa9e2d51734347
+config: df917163c3917b65e42063dbd2aaffb4
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -79,7 +79,7 @@
     # select up to 5 digit examples that the classifier is most uncertain about
     uncertainty_index = np.argsort(pred_entropies)[::-1]
     uncertainty_index = uncertainty_index[
-        np.in1d(uncertainty_index, unlabeled_indices)
+        np.isin(uncertainty_index, unlabeled_indices)
     ][:5]
 
     # keep track of indices that we get labels for

dev/_downloads/0dd5e0a7942f1446accf7dffd47aed28/plot_label_propagation_digits_active_learning.py

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Clay Woolam <[email protected]>\n# License: BSD\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom scipy import stats\n\nfrom sklearn import datasets\nfrom sklearn.metrics import classification_report, confusion_matrix\nfrom sklearn.semi_supervised import LabelSpreading\n\ndigits = datasets.load_digits()\nrng = np.random.RandomState(0)\nindices = np.arange(len(digits.data))\nrng.shuffle(indices)\n\nX = digits.data[indices[:330]]\ny = digits.target[indices[:330]]\nimages = digits.images[indices[:330]]\n\nn_total_samples = len(y)\nn_labeled_points = 40\nmax_iterations = 5\n\nunlabeled_indices = np.arange(n_total_samples)[n_labeled_points:]\nf = plt.figure()\n\nfor i in range(max_iterations):\n    if len(unlabeled_indices) == 0:\n        print(\"No unlabeled items left to label.\")\n        break\n    y_train = np.copy(y)\n    y_train[unlabeled_indices] = -1\n\n    lp_model = LabelSpreading(gamma=0.25, max_iter=20)\n    lp_model.fit(X, y_train)\n\n    predicted_labels = lp_model.transduction_[unlabeled_indices]\n    true_labels = y[unlabeled_indices]\n\n    cm = confusion_matrix(true_labels, predicted_labels, labels=lp_model.classes_)\n\n    print(\"Iteration %i %s\" % (i, 70 * \"_\"))\n    print(\n        \"Label Spreading model: %d labeled & %d unlabeled (%d total)\"\n        % (n_labeled_points, n_total_samples - n_labeled_points, n_total_samples)\n    )\n\n    print(classification_report(true_labels, predicted_labels))\n\n    print(\"Confusion matrix\")\n    print(cm)\n\n    # compute the entropies of transduced label distributions\n    pred_entropies = stats.distributions.entropy(lp_model.label_distributions_.T)\n\n    # select up to 5 digit examples that the classifier is most uncertain about\n    uncertainty_index = np.argsort(pred_entropies)[::-1]\n    uncertainty_index = uncertainty_index[\n        np.in1d(uncertainty_index, unlabeled_indices)\n    ][:5]\n\n    # keep track of indices that we get labels for\n    delete_indices = np.array([], dtype=int)\n\n    # for more than 5 iterations, visualize the gain only on the first 5\n    if i < 5:\n        f.text(\n            0.05,\n            (1 - (i + 1) * 0.183),\n            \"model %d\\n\\nfit with\\n%d labels\" % ((i + 1), i * 5 + 10),\n            size=10,\n        )\n    for index, image_index in enumerate(uncertainty_index):\n        image = images[image_index]\n\n        # for more than 5 iterations, visualize the gain only on the first 5\n        if i < 5:\n            sub = f.add_subplot(5, 5, index + 1 + (5 * i))\n            sub.imshow(image, cmap=plt.cm.gray_r, interpolation=\"none\")\n            sub.set_title(\n                \"predict: %i\\ntrue: %i\"\n                % (lp_model.transduction_[image_index], y[image_index]),\n                size=10,\n            )\n            sub.axis(\"off\")\n\n        # labeling 5 points, remote from labeled set\n        (delete_index,) = np.where(unlabeled_indices == image_index)\n        delete_indices = np.concatenate((delete_indices, delete_index))\n\n    unlabeled_indices = np.delete(unlabeled_indices, delete_indices)\n    n_labeled_points += len(uncertainty_index)\n\nf.suptitle(\n    (\n        \"Active learning with Label Propagation.\\nRows show 5 most \"\n        \"uncertain labels to learn with the next model.\"\n    ),\n    y=1.15,\n)\nplt.subplots_adjust(left=0.2, bottom=0.03, right=0.9, top=0.9, wspace=0.2, hspace=0.85)\nplt.show()"
+        "# Authors: Clay Woolam <[email protected]>\n# License: BSD\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom scipy import stats\n\nfrom sklearn import datasets\nfrom sklearn.metrics import classification_report, confusion_matrix\nfrom sklearn.semi_supervised import LabelSpreading\n\ndigits = datasets.load_digits()\nrng = np.random.RandomState(0)\nindices = np.arange(len(digits.data))\nrng.shuffle(indices)\n\nX = digits.data[indices[:330]]\ny = digits.target[indices[:330]]\nimages = digits.images[indices[:330]]\n\nn_total_samples = len(y)\nn_labeled_points = 40\nmax_iterations = 5\n\nunlabeled_indices = np.arange(n_total_samples)[n_labeled_points:]\nf = plt.figure()\n\nfor i in range(max_iterations):\n    if len(unlabeled_indices) == 0:\n        print(\"No unlabeled items left to label.\")\n        break\n    y_train = np.copy(y)\n    y_train[unlabeled_indices] = -1\n\n    lp_model = LabelSpreading(gamma=0.25, max_iter=20)\n    lp_model.fit(X, y_train)\n\n    predicted_labels = lp_model.transduction_[unlabeled_indices]\n    true_labels = y[unlabeled_indices]\n\n    cm = confusion_matrix(true_labels, predicted_labels, labels=lp_model.classes_)\n\n    print(\"Iteration %i %s\" % (i, 70 * \"_\"))\n    print(\n        \"Label Spreading model: %d labeled & %d unlabeled (%d total)\"\n        % (n_labeled_points, n_total_samples - n_labeled_points, n_total_samples)\n    )\n\n    print(classification_report(true_labels, predicted_labels))\n\n    print(\"Confusion matrix\")\n    print(cm)\n\n    # compute the entropies of transduced label distributions\n    pred_entropies = stats.distributions.entropy(lp_model.label_distributions_.T)\n\n    # select up to 5 digit examples that the classifier is most uncertain about\n    uncertainty_index = np.argsort(pred_entropies)[::-1]\n    uncertainty_index = uncertainty_index[\n        np.isin(uncertainty_index, unlabeled_indices)\n    ][:5]\n\n    # keep track of indices that we get labels for\n    delete_indices = np.array([], dtype=int)\n\n    # for more than 5 iterations, visualize the gain only on the first 5\n    if i < 5:\n        f.text(\n            0.05,\n            (1 - (i + 1) * 0.183),\n            \"model %d\\n\\nfit with\\n%d labels\" % ((i + 1), i * 5 + 10),\n            size=10,\n        )\n    for index, image_index in enumerate(uncertainty_index):\n        image = images[image_index]\n\n        # for more than 5 iterations, visualize the gain only on the first 5\n        if i < 5:\n            sub = f.add_subplot(5, 5, index + 1 + (5 * i))\n            sub.imshow(image, cmap=plt.cm.gray_r, interpolation=\"none\")\n            sub.set_title(\n                \"predict: %i\\ntrue: %i\"\n                % (lp_model.transduction_[image_index], y[image_index]),\n                size=10,\n            )\n            sub.axis(\"off\")\n\n        # labeling 5 points, remote from labeled set\n        (delete_index,) = np.where(unlabeled_indices == image_index)\n        delete_indices = np.concatenate((delete_indices, delete_index))\n\n    unlabeled_indices = np.delete(unlabeled_indices, delete_indices)\n    n_labeled_points += len(uncertainty_index)\n\nf.suptitle(\n    (\n        \"Active learning with Label Propagation.\\nRows show 5 most \"\n        \"uncertain labels to learn with the next model.\"\n    ),\n    y=1.15,\n)\nplt.subplots_adjust(left=0.2, bottom=0.03, right=0.9, top=0.9, wspace=0.2, hspace=0.85)\nplt.show()"
       ]
     }
   ],