Pushing the docs to dev/ for branch: master, commit 6c56316e73949f23f84db6ebe52230f87f977e4d

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Nelle Varoquaux <[email protected]>\n# License: BSD\n\nprint(__doc__)\nimport numpy as np\n\nfrom matplotlib import pyplot as plt\nfrom matplotlib.collections import LineCollection\n\nfrom sklearn import manifold\nfrom sklearn.metrics import euclidean_distances\nfrom sklearn.decomposition import PCA\n\nn_samples = 20\nseed = np.random.RandomState(seed=3)\nX_true = seed.randint(0, 20, 2 * n_samples).astype(np.float)\nX_true = X_true.reshape((n_samples, 2))\n# Center the data\nX_true -= X_true.mean()\n\nsimilarities = euclidean_distances(X_true)\n\n# Add noise to the similarities\nnoise = np.random.rand(n_samples, n_samples)\nnoise = noise + noise.T\nnoise[np.arange(noise.shape[0]), np.arange(noise.shape[0])] = 0\nsimilarities += noise\n\nmds = manifold.MDS(n_components=2, max_iter=3000, eps=1e-9, random_state=seed,\n                   dissimilarity=\"precomputed\", n_jobs=1)\npos = mds.fit(similarities).embedding_\n\nnmds = manifold.MDS(n_components=2, metric=False, max_iter=3000, eps=1e-12,\n                    dissimilarity=\"precomputed\", random_state=seed, n_jobs=1,\n                    n_init=1)\nnpos = nmds.fit_transform(similarities, init=pos)\n\n# Rescale the data\npos *= np.sqrt((X_true ** 2).sum()) / np.sqrt((pos ** 2).sum())\nnpos *= np.sqrt((X_true ** 2).sum()) / np.sqrt((npos ** 2).sum())\n\n# Rotate the data\nclf = PCA(n_components=2)\nX_true = clf.fit_transform(X_true)\n\npos = clf.fit_transform(pos)\n\nnpos = clf.fit_transform(npos)\n\nfig = plt.figure(1)\nax = plt.axes([0., 0., 1., 1.])\n\ns = 100\nplt.scatter(X_true[:, 0], X_true[:, 1], color='navy', s=s, lw=0,\n            label='True Position')\nplt.scatter(pos[:, 0], pos[:, 1], color='turquoise', s=s, lw=0, label='MDS')\nplt.scatter(npos[:, 0], npos[:, 1], color='darkorange', s=s, lw=0, label='NMDS')\nplt.legend(scatterpoints=1, loc='best', shadow=False)\n\nsimilarities = similarities.max() / similarities * 100\nsimilarities[np.isinf(similarities)] = 0\n\n# Plot the edges\nstart_idx, end_idx = np.where(pos)\n# a sequence of (*line0*, *line1*, *line2*), where::\n#            linen = (x0, y0), (x1, y1), ... (xm, ym)\nsegments = [[X_true[i, :], X_true[j, :]]\n            for i in range(len(pos)) for j in range(len(pos))]\nvalues = np.abs(similarities)\nlc = LineCollection(segments,\n                    zorder=0, cmap=plt.cm.Blues,\n                    norm=plt.Normalize(0, values.max()))\nlc.set_array(similarities.flatten())\nlc.set_linewidths(np.full(len(segments), 0.5))\nax.add_collection(lc)\n\nplt.show()"
+        "# Author: Nelle Varoquaux <[email protected]>\n# License: BSD\n\nprint(__doc__)\nimport numpy as np\n\nfrom matplotlib import pyplot as plt\nfrom matplotlib.collections import LineCollection\n\nfrom sklearn import manifold\nfrom sklearn.metrics import euclidean_distances\nfrom sklearn.decomposition import PCA\n\nEPSILON = np.finfo(np.float32).eps\nn_samples = 20\nseed = np.random.RandomState(seed=3)\nX_true = seed.randint(0, 20, 2 * n_samples).astype(np.float)\nX_true = X_true.reshape((n_samples, 2))\n# Center the data\nX_true -= X_true.mean()\n\nsimilarities = euclidean_distances(X_true)\n\n# Add noise to the similarities\nnoise = np.random.rand(n_samples, n_samples)\nnoise = noise + noise.T\nnoise[np.arange(noise.shape[0]), np.arange(noise.shape[0])] = 0\nsimilarities += noise\n\nmds = manifold.MDS(n_components=2, max_iter=3000, eps=1e-9, random_state=seed,\n                   dissimilarity=\"precomputed\", n_jobs=1)\npos = mds.fit(similarities).embedding_\n\nnmds = manifold.MDS(n_components=2, metric=False, max_iter=3000, eps=1e-12,\n                    dissimilarity=\"precomputed\", random_state=seed, n_jobs=1,\n                    n_init=1)\nnpos = nmds.fit_transform(similarities, init=pos)\n\n# Rescale the data\npos *= np.sqrt((X_true ** 2).sum()) / np.sqrt((pos ** 2).sum())\nnpos *= np.sqrt((X_true ** 2).sum()) / np.sqrt((npos ** 2).sum())\n\n# Rotate the data\nclf = PCA(n_components=2)\nX_true = clf.fit_transform(X_true)\n\npos = clf.fit_transform(pos)\n\nnpos = clf.fit_transform(npos)\n\nfig = plt.figure(1)\nax = plt.axes([0., 0., 1., 1.])\n\ns = 100\nplt.scatter(X_true[:, 0], X_true[:, 1], color='navy', s=s, lw=0,\n            label='True Position')\nplt.scatter(pos[:, 0], pos[:, 1], color='turquoise', s=s, lw=0, label='MDS')\nplt.scatter(npos[:, 0], npos[:, 1], color='darkorange', s=s, lw=0, label='NMDS')\nplt.legend(scatterpoints=1, loc='best', shadow=False)\n\nsimilarities = similarities.max() / (similarities + EPSILON) * 100\nnp.fill_diagonal(similarities, 0)\n# Plot the edges\nstart_idx, end_idx = np.where(pos)\n# a sequence of (*line0*, *line1*, *line2*), where::\n#            linen = (x0, y0), (x1, y1), ... (xm, ym)\nsegments = [[X_true[i, :], X_true[j, :]]\n            for i in range(len(pos)) for j in range(len(pos))]\nvalues = np.abs(similarities)\nlc = LineCollection(segments,\n                    zorder=0, cmap=plt.cm.Blues,\n                    norm=plt.Normalize(0, values.max()))\nlc.set_array(similarities.flatten())\nlc.set_linewidths(np.full(len(segments), 0.5))\nax.add_collection(lc)\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -22,6 +22,7 @@
 from sklearn.metrics import euclidean_distances
 from sklearn.decomposition import PCA
 
+EPSILON = np.finfo(np.float32).eps
 n_samples = 20
 seed = np.random.RandomState(seed=3)
 X_true = seed.randint(0, 20, 2 * n_samples).astype(np.float)
@@ -68,9 +69,8 @@
 plt.scatter(npos[:, 0], npos[:, 1], color='darkorange', s=s, lw=0, label='NMDS')
 plt.legend(scatterpoints=1, loc='best', shadow=False)
 
-similarities = similarities.max() / similarities * 100
-similarities[np.isinf(similarities)] = 0
-
+similarities = similarities.max() / (similarities + EPSILON) * 100
+np.fill_diagonal(similarities, 0)
 # Plot the edges
 start_idx, end_idx = np.where(pos)
 # a sequence of (*line0*, *line1*, *line2*), where::