Pushing the docs to dev/ for branch: master, commit 4d749ea4900ad5556cc0c34b4f8a3383420e7343

Author: sklearn-ci

dev/_downloads/00727cbc15047062964b3f55fc4571b7/plot_label_propagation_digits_active_learning.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Authors: Clay Woolam <[email protected]>\n# License: BSD\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\nfrom sklearn import datasets\nfrom sklearn.semi_supervised import label_propagation\nfrom sklearn.metrics import classification_report, confusion_matrix\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 = label_propagation.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,\n                          labels=lp_model.classes_)\n\n    print(\"Iteration %i %s\" % (i, 70 * \"_\"))\n    print(\"Label Spreading model: %d labeled & %d unlabeled (%d total)\"\n          % (n_labeled_points, n_total_samples - n_labeled_points,\n             n_total_samples))\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(\n        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)][: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(.05, (1 - (i + 1) * .183),\n               \"model %d\\n\\nfit with\\n%d labels\" %\n               ((i + 1), i * 5 + 10), size=10)\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(\"predict: %i\\ntrue: %i\" % (\n                lp_model.transduction_[image_index], y[image_index]), size=10)\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(\"Active learning with Label Propagation.\\nRows show 5 most \"\n           \"uncertain labels to learn with the next model.\", y=1.15)\nplt.subplots_adjust(left=0.2, bottom=0.03, right=0.9, top=0.9, wspace=0.2,\n                    hspace=0.85)\nplt.show()"
+        "print(__doc__)\n\n# Authors: Clay Woolam <[email protected]>\n# License: BSD\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\nfrom sklearn import datasets\nfrom sklearn.semi_supervised import LabelSpreading\nfrom sklearn.metrics import classification_report, confusion_matrix\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,\n                          labels=lp_model.classes_)\n\n    print(\"Iteration %i %s\" % (i, 70 * \"_\"))\n    print(\"Label Spreading model: %d labeled & %d unlabeled (%d total)\"\n          % (n_labeled_points, n_total_samples - n_labeled_points,\n             n_total_samples))\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(\n        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)][: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(.05, (1 - (i + 1) * .183),\n               \"model %d\\n\\nfit with\\n%d labels\" %\n               ((i + 1), i * 5 + 10), size=10)\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(\"predict: %i\\ntrue: %i\" % (\n                lp_model.transduction_[image_index], y[image_index]), size=10)\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(\"Active learning with Label Propagation.\\nRows show 5 most \"\n           \"uncertain labels to learn with the next model.\", y=1.15)\nplt.subplots_adjust(left=0.2, bottom=0.03, right=0.9, top=0.9, wspace=0.2,\n                    hspace=0.85)\nplt.show()"
       ]
     }
   ],

dev/_downloads/28cc51eb795f5d3f1d2b277cec0fc093/plot_gpc.py

@@ -30,7 +30,7 @@
 
 from matplotlib import pyplot as plt
 
-from sklearn.metrics.classification import accuracy_score, log_loss
+from sklearn.metrics import accuracy_score, log_loss
 from sklearn.gaussian_process import GaussianProcessClassifier
 from sklearn.gaussian_process.kernels import RBF
 

dev/_downloads/2f0fcf5590787bd2c8dc5bbbd4c18922/plot_label_propagation_structure.py

@@ -17,7 +17,7 @@
 
 import numpy as np
 import matplotlib.pyplot as plt
-from sklearn.semi_supervised import label_propagation
+from sklearn.semi_supervised import LabelSpreading
 from sklearn.datasets import make_circles
 
 # generate ring with inner box
@@ -30,7 +30,7 @@
 
 # #############################################################################
 # Learn with LabelSpreading
-label_spread = label_propagation.LabelSpreading(kernel='knn', alpha=0.8)
+label_spread = LabelSpreading(kernel='knn', alpha=0.8)
 label_spread.fit(X, labels)
 
 # #############################################################################

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -25,7 +25,7 @@ class will be very good.
 from scipy import stats
 
 from sklearn import datasets
-from sklearn.semi_supervised import label_propagation
+from sklearn.semi_supervised import LabelSpreading
 
 from sklearn.metrics import confusion_matrix, classification_report
 
@@ -52,7 +52,7 @@ class will be very good.
 
 # #############################################################################
 # Learn with LabelSpreading
-lp_model = label_propagation.LabelSpreading(gamma=.25, max_iter=20)
+lp_model = LabelSpreading(gamma=.25, max_iter=20)
 lp_model.fit(X, y_train)
 predicted_labels = lp_model.transduction_[unlabeled_set]
 true_labels = y[unlabeled_set]

dev/_downloads/5c28e4f1ed6deeaca78c1333e1dd5a0a/plot_label_propagation_digits.py

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Authors: Clay Woolam <[email protected]>\n#          Andreas Mueller <[email protected]>\n# License: BSD\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.semi_supervised import label_propagation\nfrom sklearn.datasets import make_circles\n\n# generate ring with inner box\nn_samples = 200\nX, y = make_circles(n_samples=n_samples, shuffle=False)\nouter, inner = 0, 1\nlabels = np.full(n_samples, -1.)\nlabels[0] = outer\nlabels[-1] = inner\n\n# #############################################################################\n# Learn with LabelSpreading\nlabel_spread = label_propagation.LabelSpreading(kernel='knn', alpha=0.8)\nlabel_spread.fit(X, labels)\n\n# #############################################################################\n# Plot output labels\noutput_labels = label_spread.transduction_\nplt.figure(figsize=(8.5, 4))\nplt.subplot(1, 2, 1)\nplt.scatter(X[labels == outer, 0], X[labels == outer, 1], color='navy',\n            marker='s', lw=0, label=\"outer labeled\", s=10)\nplt.scatter(X[labels == inner, 0], X[labels == inner, 1], color='c',\n            marker='s', lw=0, label='inner labeled', s=10)\nplt.scatter(X[labels == -1, 0], X[labels == -1, 1], color='darkorange',\n            marker='.', label='unlabeled')\nplt.legend(scatterpoints=1, shadow=False, loc='upper right')\nplt.title(\"Raw data (2 classes=outer and inner)\")\n\nplt.subplot(1, 2, 2)\noutput_label_array = np.asarray(output_labels)\nouter_numbers = np.where(output_label_array == outer)[0]\ninner_numbers = np.where(output_label_array == inner)[0]\nplt.scatter(X[outer_numbers, 0], X[outer_numbers, 1], color='navy',\n            marker='s', lw=0, s=10, label=\"outer learned\")\nplt.scatter(X[inner_numbers, 0], X[inner_numbers, 1], color='c',\n            marker='s', lw=0, s=10, label=\"inner learned\")\nplt.legend(scatterpoints=1, shadow=False, loc='upper right')\nplt.title(\"Labels learned with Label Spreading (KNN)\")\n\nplt.subplots_adjust(left=0.07, bottom=0.07, right=0.93, top=0.92)\nplt.show()"
+        "print(__doc__)\n\n# Authors: Clay Woolam <[email protected]>\n#          Andreas Mueller <[email protected]>\n# License: BSD\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.semi_supervised import LabelSpreading\nfrom sklearn.datasets import make_circles\n\n# generate ring with inner box\nn_samples = 200\nX, y = make_circles(n_samples=n_samples, shuffle=False)\nouter, inner = 0, 1\nlabels = np.full(n_samples, -1.)\nlabels[0] = outer\nlabels[-1] = inner\n\n# #############################################################################\n# Learn with LabelSpreading\nlabel_spread = LabelSpreading(kernel='knn', alpha=0.8)\nlabel_spread.fit(X, labels)\n\n# #############################################################################\n# Plot output labels\noutput_labels = label_spread.transduction_\nplt.figure(figsize=(8.5, 4))\nplt.subplot(1, 2, 1)\nplt.scatter(X[labels == outer, 0], X[labels == outer, 1], color='navy',\n            marker='s', lw=0, label=\"outer labeled\", s=10)\nplt.scatter(X[labels == inner, 0], X[labels == inner, 1], color='c',\n            marker='s', lw=0, label='inner labeled', s=10)\nplt.scatter(X[labels == -1, 0], X[labels == -1, 1], color='darkorange',\n            marker='.', label='unlabeled')\nplt.legend(scatterpoints=1, shadow=False, loc='upper right')\nplt.title(\"Raw data (2 classes=outer and inner)\")\n\nplt.subplot(1, 2, 2)\noutput_label_array = np.asarray(output_labels)\nouter_numbers = np.where(output_label_array == outer)[0]\ninner_numbers = np.where(output_label_array == inner)[0]\nplt.scatter(X[outer_numbers, 0], X[outer_numbers, 1], color='navy',\n            marker='s', lw=0, s=10, label=\"outer learned\")\nplt.scatter(X[inner_numbers, 0], X[inner_numbers, 1], color='c',\n            marker='s', lw=0, s=10, label=\"inner learned\")\nplt.legend(scatterpoints=1, shadow=False, loc='upper right')\nplt.title(\"Labels learned with Label Spreading (KNN)\")\n\nplt.subplots_adjust(left=0.07, bottom=0.07, right=0.93, top=0.92)\nplt.show()"
       ]
     }
   ],

dev/_downloads/5d33e8af80b52ee08fc7055bd9785181/plot_label_propagation_structure.ipynb

@@ -19,7 +19,7 @@
 import matplotlib.pyplot as plt
 from sklearn import datasets
 from sklearn import svm
-from sklearn.semi_supervised import label_propagation
+from sklearn.semi_supervised import LabelSpreading
 
 rng = np.random.RandomState(0)
 
@@ -37,11 +37,9 @@
 y_50[rng.rand(len(y)) < 0.5] = -1
 # we create an instance of SVM and fit out data. We do not scale our
 # data since we want to plot the support vectors
-ls30 = (label_propagation.LabelSpreading().fit(X, y_30),
-        y_30)
-ls50 = (label_propagation.LabelSpreading().fit(X, y_50),
-        y_50)
-ls100 = (label_propagation.LabelSpreading().fit(X, y), y)
+ls30 = (LabelSpreading().fit(X, y_30), y_30)
+ls50 = (LabelSpreading().fit(X, y_50), y_50)
+ls100 = (LabelSpreading().fit(X, y), y)
 rbf_svc = (svm.SVC(kernel='rbf', gamma=.5).fit(X, y), y)
 
 # create a mesh to plot in

dev/_downloads/97a366ef6b2f7394d4eb409814bf4842/plot_label_propagation_versus_svm_iris.py

@@ -28,7 +28,7 @@
 from scipy import stats
 
 from sklearn import datasets
-from sklearn.semi_supervised import label_propagation
+from sklearn.semi_supervised import LabelSpreading
 from sklearn.metrics import classification_report, confusion_matrix
 
 digits = datasets.load_digits()
@@ -54,7 +54,7 @@
     y_train = np.copy(y)
     y_train[unlabeled_indices] = -1
 
-    lp_model = label_propagation.LabelSpreading(gamma=0.25, max_iter=20)
+    lp_model = LabelSpreading(gamma=0.25, max_iter=20)
     lp_model.fit(X, y_train)
 
     predicted_labels = lp_model.transduction_[unlabeled_indices]

dev/_downloads/9e3acfeb3f59990764697ab81a7cda9b/plot_label_propagation_digits_active_learning.py

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Authors: Jan Hendrik Metzen <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\n\nfrom matplotlib import pyplot as plt\n\nfrom sklearn.metrics.classification import accuracy_score, log_loss\nfrom sklearn.gaussian_process import GaussianProcessClassifier\nfrom sklearn.gaussian_process.kernels import RBF\n\n\n# Generate data\ntrain_size = 50\nrng = np.random.RandomState(0)\nX = rng.uniform(0, 5, 100)[:, np.newaxis]\ny = np.array(X[:, 0] > 2.5, dtype=int)\n\n# Specify Gaussian Processes with fixed and optimized hyperparameters\ngp_fix = GaussianProcessClassifier(kernel=1.0 * RBF(length_scale=1.0),\n                                   optimizer=None)\ngp_fix.fit(X[:train_size], y[:train_size])\n\ngp_opt = GaussianProcessClassifier(kernel=1.0 * RBF(length_scale=1.0))\ngp_opt.fit(X[:train_size], y[:train_size])\n\nprint(\"Log Marginal Likelihood (initial): %.3f\"\n      % gp_fix.log_marginal_likelihood(gp_fix.kernel_.theta))\nprint(\"Log Marginal Likelihood (optimized): %.3f\"\n      % gp_opt.log_marginal_likelihood(gp_opt.kernel_.theta))\n\nprint(\"Accuracy: %.3f (initial) %.3f (optimized)\"\n      % (accuracy_score(y[:train_size], gp_fix.predict(X[:train_size])),\n         accuracy_score(y[:train_size], gp_opt.predict(X[:train_size]))))\nprint(\"Log-loss: %.3f (initial) %.3f (optimized)\"\n      % (log_loss(y[:train_size], gp_fix.predict_proba(X[:train_size])[:, 1]),\n         log_loss(y[:train_size], gp_opt.predict_proba(X[:train_size])[:, 1])))\n\n\n# Plot posteriors\nplt.figure()\nplt.scatter(X[:train_size, 0], y[:train_size], c='k', label=\"Train data\",\n            edgecolors=(0, 0, 0))\nplt.scatter(X[train_size:, 0], y[train_size:], c='g', label=\"Test data\",\n            edgecolors=(0, 0, 0))\nX_ = np.linspace(0, 5, 100)\nplt.plot(X_, gp_fix.predict_proba(X_[:, np.newaxis])[:, 1], 'r',\n         label=\"Initial kernel: %s\" % gp_fix.kernel_)\nplt.plot(X_, gp_opt.predict_proba(X_[:, np.newaxis])[:, 1], 'b',\n         label=\"Optimized kernel: %s\" % gp_opt.kernel_)\nplt.xlabel(\"Feature\")\nplt.ylabel(\"Class 1 probability\")\nplt.xlim(0, 5)\nplt.ylim(-0.25, 1.5)\nplt.legend(loc=\"best\")\n\n# Plot LML landscape\nplt.figure()\ntheta0 = np.logspace(0, 8, 30)\ntheta1 = np.logspace(-1, 1, 29)\nTheta0, Theta1 = np.meshgrid(theta0, theta1)\nLML = [[gp_opt.log_marginal_likelihood(np.log([Theta0[i, j], Theta1[i, j]]))\n        for i in range(Theta0.shape[0])] for j in range(Theta0.shape[1])]\nLML = np.array(LML).T\nplt.plot(np.exp(gp_fix.kernel_.theta)[0], np.exp(gp_fix.kernel_.theta)[1],\n         'ko', zorder=10)\nplt.plot(np.exp(gp_opt.kernel_.theta)[0], np.exp(gp_opt.kernel_.theta)[1],\n         'ko', zorder=10)\nplt.pcolor(Theta0, Theta1, LML)\nplt.xscale(\"log\")\nplt.yscale(\"log\")\nplt.colorbar()\nplt.xlabel(\"Magnitude\")\nplt.ylabel(\"Length-scale\")\nplt.title(\"Log-marginal-likelihood\")\n\nplt.show()"
+        "print(__doc__)\n\n# Authors: Jan Hendrik Metzen <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\n\nfrom matplotlib import pyplot as plt\n\nfrom sklearn.metrics import accuracy_score, log_loss\nfrom sklearn.gaussian_process import GaussianProcessClassifier\nfrom sklearn.gaussian_process.kernels import RBF\n\n\n# Generate data\ntrain_size = 50\nrng = np.random.RandomState(0)\nX = rng.uniform(0, 5, 100)[:, np.newaxis]\ny = np.array(X[:, 0] > 2.5, dtype=int)\n\n# Specify Gaussian Processes with fixed and optimized hyperparameters\ngp_fix = GaussianProcessClassifier(kernel=1.0 * RBF(length_scale=1.0),\n                                   optimizer=None)\ngp_fix.fit(X[:train_size], y[:train_size])\n\ngp_opt = GaussianProcessClassifier(kernel=1.0 * RBF(length_scale=1.0))\ngp_opt.fit(X[:train_size], y[:train_size])\n\nprint(\"Log Marginal Likelihood (initial): %.3f\"\n      % gp_fix.log_marginal_likelihood(gp_fix.kernel_.theta))\nprint(\"Log Marginal Likelihood (optimized): %.3f\"\n      % gp_opt.log_marginal_likelihood(gp_opt.kernel_.theta))\n\nprint(\"Accuracy: %.3f (initial) %.3f (optimized)\"\n      % (accuracy_score(y[:train_size], gp_fix.predict(X[:train_size])),\n         accuracy_score(y[:train_size], gp_opt.predict(X[:train_size]))))\nprint(\"Log-loss: %.3f (initial) %.3f (optimized)\"\n      % (log_loss(y[:train_size], gp_fix.predict_proba(X[:train_size])[:, 1]),\n         log_loss(y[:train_size], gp_opt.predict_proba(X[:train_size])[:, 1])))\n\n\n# Plot posteriors\nplt.figure()\nplt.scatter(X[:train_size, 0], y[:train_size], c='k', label=\"Train data\",\n            edgecolors=(0, 0, 0))\nplt.scatter(X[train_size:, 0], y[train_size:], c='g', label=\"Test data\",\n            edgecolors=(0, 0, 0))\nX_ = np.linspace(0, 5, 100)\nplt.plot(X_, gp_fix.predict_proba(X_[:, np.newaxis])[:, 1], 'r',\n         label=\"Initial kernel: %s\" % gp_fix.kernel_)\nplt.plot(X_, gp_opt.predict_proba(X_[:, np.newaxis])[:, 1], 'b',\n         label=\"Optimized kernel: %s\" % gp_opt.kernel_)\nplt.xlabel(\"Feature\")\nplt.ylabel(\"Class 1 probability\")\nplt.xlim(0, 5)\nplt.ylim(-0.25, 1.5)\nplt.legend(loc=\"best\")\n\n# Plot LML landscape\nplt.figure()\ntheta0 = np.logspace(0, 8, 30)\ntheta1 = np.logspace(-1, 1, 29)\nTheta0, Theta1 = np.meshgrid(theta0, theta1)\nLML = [[gp_opt.log_marginal_likelihood(np.log([Theta0[i, j], Theta1[i, j]]))\n        for i in range(Theta0.shape[0])] for j in range(Theta0.shape[1])]\nLML = np.array(LML).T\nplt.plot(np.exp(gp_fix.kernel_.theta)[0], np.exp(gp_fix.kernel_.theta)[1],\n         'ko', zorder=10)\nplt.plot(np.exp(gp_opt.kernel_.theta)[0], np.exp(gp_opt.kernel_.theta)[1],\n         'ko', zorder=10)\nplt.pcolor(Theta0, Theta1, LML)\nplt.xscale(\"log\")\nplt.yscale(\"log\")\nplt.colorbar()\nplt.xlabel(\"Magnitude\")\nplt.ylabel(\"Length-scale\")\nplt.title(\"Log-marginal-likelihood\")\n\nplt.show()"
       ]
     }
   ],