Pushing the docs to dev/ for branch: main, commit 5f91dca9f0ded71df9f82e7f120f0263f15fb18e

Author: sklearn-ci

dev/_downloads/02192f99342d6d1323161978b6c80bfc/plot_ols_ridge.zip

@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport numpy as np\nfrom matplotlib import pyplot as plt\nfrom matplotlib.collections import LineCollection\n\nfrom sklearn import manifold\nfrom sklearn.decomposition import PCA\nfrom sklearn.metrics import euclidean_distances\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(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    n_components=2,\n    max_iter=3000,\n    eps=1e-9,\n    random_state=seed,\n    dissimilarity=\"precomputed\",\n    n_jobs=1,\n)\npos = mds.fit(similarities).embedding_\n\nnmds = manifold.MDS(\n    n_components=2,\n    metric=False,\n    max_iter=3000,\n    eps=1e-12,\n    dissimilarity=\"precomputed\",\n    random_state=seed,\n    n_jobs=1,\n    n_init=1,\n)\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, 0.0, 1.0, 1.0])\n\ns = 100\nplt.scatter(X_true[:, 0], X_true[:, 1], color=\"navy\", s=s, lw=0, 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 = [\n    [X_true[i, :], X_true[j, :]] for i in range(len(pos)) for j in range(len(pos))\n]\nvalues = np.abs(similarities)\nlc = LineCollection(\n    segments, zorder=0, cmap=plt.cm.Blues, norm=plt.Normalize(0, values.max())\n)\nlc.set_array(similarities.flatten())\nlc.set_linewidths(np.full(len(segments), 0.5))\nax.add_collection(lc)\n\nplt.show()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport numpy as np\nfrom matplotlib import pyplot as plt\nfrom matplotlib.collections import LineCollection\n\nfrom sklearn import manifold\nfrom sklearn.decomposition import PCA\nfrom sklearn.metrics import euclidean_distances\n\n# Generate the data\nEPSILON = np.finfo(np.float32).eps\nn_samples = 20\nrng = np.random.RandomState(seed=3)\nX_true = rng.randint(0, 20, 2 * n_samples).astype(float)\nX_true = X_true.reshape((n_samples, 2))\n\n# Center the data\nX_true -= X_true.mean()\n\n# Compute pairwise Euclidean distances\ndistances = euclidean_distances(X_true)\n\n# Add noise to the distances\nnoise = rng.rand(n_samples, n_samples)\nnoise = noise + noise.T\nnp.fill_diagonal(noise, 0)\ndistances += noise\n\nmds = manifold.MDS(\n    n_components=2,\n    max_iter=3000,\n    eps=1e-9,\n    random_state=42,\n    dissimilarity=\"precomputed\",\n    n_jobs=1,\n)\nX_mds = mds.fit(distances).embedding_\n\nnmds = manifold.MDS(\n    n_components=2,\n    metric=False,\n    max_iter=3000,\n    eps=1e-12,\n    dissimilarity=\"precomputed\",\n    random_state=42,\n    n_jobs=1,\n    n_init=1,\n)\nX_nmds = nmds.fit_transform(distances)\n\n# Rescale the data\nX_mds *= np.sqrt((X_true**2).sum()) / np.sqrt((X_mds**2).sum())\nX_nmds *= np.sqrt((X_true**2).sum()) / np.sqrt((X_nmds**2).sum())\n\n# Rotate the data\npca = PCA(n_components=2)\nX_true = pca.fit_transform(X_true)\nX_mds = pca.fit_transform(X_mds)\nX_nmds = pca.fit_transform(X_nmds)\n\n# Align the sign of PCs\nfor i in [0, 1]:\n    if np.corrcoef(X_mds[:, i], X_true[:, i])[0, 1] < 0:\n        X_mds[:, i] *= -1\n    if np.corrcoef(X_nmds[:, i], X_true[:, i])[0, 1] < 0:\n        X_nmds[:, i] *= -1\n\nfig = plt.figure(1)\nax = plt.axes([0.0, 0.0, 1.0, 1.0])\n\ns = 100\nplt.scatter(X_true[:, 0], X_true[:, 1], color=\"navy\", s=s, lw=0, label=\"True Position\")\nplt.scatter(X_mds[:, 0], X_mds[:, 1], color=\"turquoise\", s=s, lw=0, label=\"MDS\")\nplt.scatter(X_nmds[:, 0], X_nmds[:, 1], color=\"darkorange\", s=s, lw=0, label=\"NMDS\")\nplt.legend(scatterpoints=1, loc=\"best\", shadow=False)\n\n# Plot the edges\nstart_idx, end_idx = np.where(X_mds)\n# a sequence of (*line0*, *line1*, *line2*), where::\n#            linen = (x0, y0), (x1, y1), ... (xm, ym)\nsegments = [\n    [X_true[i, :], X_true[j, :]] for i in range(len(X_true)) for j in range(len(X_true))\n]\nedges = distances.max() / (distances + EPSILON) * 100\nnp.fill_diagonal(edges, 0)\nedges = np.abs(edges)\nlc = LineCollection(\n    segments, zorder=0, cmap=plt.cm.Blues, norm=plt.Normalize(0, edges.max())\n)\nlc.set_array(edges.flatten())\nlc.set_linewidths(np.full(len(segments), 0.5))\nax.add_collection(lc)\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -21,79 +21,87 @@
 from sklearn.decomposition import PCA
 from sklearn.metrics import euclidean_distances
 
+# Generate the data
 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(float)
+rng = np.random.RandomState(seed=3)
+X_true = rng.randint(0, 20, 2 * n_samples).astype(float)
 X_true = X_true.reshape((n_samples, 2))
+
 # Center the data
 X_true -= X_true.mean()
 
-similarities = euclidean_distances(X_true)
+# Compute pairwise Euclidean distances
+distances = euclidean_distances(X_true)
 
-# Add noise to the similarities
-noise = np.random.rand(n_samples, n_samples)
+# Add noise to the distances
+noise = rng.rand(n_samples, n_samples)
 noise = noise + noise.T
-noise[np.arange(noise.shape[0]), np.arange(noise.shape[0])] = 0
-similarities += noise
+np.fill_diagonal(noise, 0)
+distances += noise
 
 mds = manifold.MDS(
     n_components=2,
     max_iter=3000,
     eps=1e-9,
-    random_state=seed,
+    random_state=42,
     dissimilarity="precomputed",
     n_jobs=1,
 )
-pos = mds.fit(similarities).embedding_
+X_mds = mds.fit(distances).embedding_
 
 nmds = manifold.MDS(
     n_components=2,
     metric=False,
     max_iter=3000,
     eps=1e-12,
     dissimilarity="precomputed",
-    random_state=seed,
+    random_state=42,
     n_jobs=1,
     n_init=1,
 )
-npos = nmds.fit_transform(similarities, init=pos)
+X_nmds = nmds.fit_transform(distances)
 
 # Rescale the data
-pos *= np.sqrt((X_true**2).sum()) / np.sqrt((pos**2).sum())
-npos *= np.sqrt((X_true**2).sum()) / np.sqrt((npos**2).sum())
+X_mds *= np.sqrt((X_true**2).sum()) / np.sqrt((X_mds**2).sum())
+X_nmds *= np.sqrt((X_true**2).sum()) / np.sqrt((X_nmds**2).sum())
 
 # Rotate the data
-clf = PCA(n_components=2)
-X_true = clf.fit_transform(X_true)
-
-pos = clf.fit_transform(pos)
-
-npos = clf.fit_transform(npos)
+pca = PCA(n_components=2)
+X_true = pca.fit_transform(X_true)
+X_mds = pca.fit_transform(X_mds)
+X_nmds = pca.fit_transform(X_nmds)
+
+# Align the sign of PCs
+for i in [0, 1]:
+    if np.corrcoef(X_mds[:, i], X_true[:, i])[0, 1] < 0:
+        X_mds[:, i] *= -1
+    if np.corrcoef(X_nmds[:, i], X_true[:, i])[0, 1] < 0:
+        X_nmds[:, i] *= -1
 
 fig = plt.figure(1)
 ax = plt.axes([0.0, 0.0, 1.0, 1.0])
 
 s = 100
 plt.scatter(X_true[:, 0], X_true[:, 1], color="navy", s=s, lw=0, label="True Position")
-plt.scatter(pos[:, 0], pos[:, 1], color="turquoise", s=s, lw=0, label="MDS")
-plt.scatter(npos[:, 0], npos[:, 1], color="darkorange", s=s, lw=0, label="NMDS")
+plt.scatter(X_mds[:, 0], X_mds[:, 1], color="turquoise", s=s, lw=0, label="MDS")
+plt.scatter(X_nmds[:, 0], X_nmds[:, 1], color="darkorange", s=s, lw=0, label="NMDS")
 plt.legend(scatterpoints=1, loc="best", shadow=False)
 
-similarities = similarities.max() / (similarities + EPSILON) * 100
-np.fill_diagonal(similarities, 0)
 # Plot the edges
-start_idx, end_idx = np.where(pos)
+start_idx, end_idx = np.where(X_mds)
 # a sequence of (*line0*, *line1*, *line2*), where::
 #            linen = (x0, y0), (x1, y1), ... (xm, ym)
 segments = [
-    [X_true[i, :], X_true[j, :]] for i in range(len(pos)) for j in range(len(pos))
+    [X_true[i, :], X_true[j, :]] for i in range(len(X_true)) for j in range(len(X_true))
 ]
-values = np.abs(similarities)
+edges = distances.max() / (distances + EPSILON) * 100
+np.fill_diagonal(edges, 0)
+edges = np.abs(edges)
 lc = LineCollection(
-    segments, zorder=0, cmap=plt.cm.Blues, norm=plt.Normalize(0, values.max())
+    segments, zorder=0, cmap=plt.cm.Blues, norm=plt.Normalize(0, edges.max())
 )
-lc.set_array(similarities.flatten())
+lc.set_array(edges.flatten())
 lc.set_linewidths(np.full(len(segments), 0.5))
 ax.add_collection(lc)