Pushing the docs to dev/ for branch: main, commit 935f7e66068fc130971646225a95ade649f57928

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -38,6 +38,7 @@
 # License: BSD 3-Clause or CC-0
 
 import matplotlib.pyplot as plt
+import matplotlib.patheffects as PathEffects
 import numpy as np
 
 from sklearn.cluster import AgglomerativeClustering
@@ -80,18 +81,20 @@ def sqr(x):
 
 labels = ("Waveform 1", "Waveform 2", "Waveform 3")
 
+colors = ["#f7bd01", "#377eb8", "#f781bf"]
+
 # Plot the ground-truth labelling
 plt.figure()
 plt.axes([0, 0, 1, 1])
-for l, c, n in zip(range(n_clusters), "rgb", labels):
-    lines = plt.plot(X[y == l].T, c=c, alpha=0.5)
+for l, color, n in zip(range(n_clusters), colors, labels):
+    lines = plt.plot(X[y == l].T, c=color, alpha=0.5)
     lines[0].set_label(n)
 
 plt.legend(loc="best")
 
 plt.axis("tight")
 plt.axis("off")
-plt.suptitle("Ground truth", size=20)
+plt.suptitle("Ground truth", size=20, y=1)
 
 
 # Plot the distances
@@ -106,19 +109,22 @@ def sqr(x):
     avg_dist /= avg_dist.max()
     for i in range(n_clusters):
         for j in range(n_clusters):
-            plt.text(
+            t = plt.text(
                 i,
                 j,
                 "%5.3f" % avg_dist[i, j],
                 verticalalignment="center",
                 horizontalalignment="center",
             )
+            t.set_path_effects(
+                [PathEffects.withStroke(linewidth=5, foreground="w", alpha=0.5)]
+            )
 
-    plt.imshow(avg_dist, interpolation="nearest", cmap=plt.cm.gnuplot2, vmin=0)
+    plt.imshow(avg_dist, interpolation="nearest", cmap="cividis", vmin=0)
     plt.xticks(range(n_clusters), labels, rotation=45)
     plt.yticks(range(n_clusters), labels)
     plt.colorbar()
-    plt.suptitle("Interclass %s distances" % metric, size=18)
+    plt.suptitle("Interclass %s distances" % metric, size=18, y=1)
     plt.tight_layout()
 
 
@@ -130,11 +136,11 @@ def sqr(x):
     model.fit(X)
     plt.figure()
     plt.axes([0, 0, 1, 1])
-    for l, c in zip(np.arange(model.n_clusters), "rgbk"):
-        plt.plot(X[model.labels_ == l].T, c=c, alpha=0.5)
+    for l, color in zip(np.arange(model.n_clusters), colors):
+        plt.plot(X[model.labels_ == l].T, c=color, alpha=0.5)
     plt.axis("tight")
     plt.axis("off")
-    plt.suptitle("AgglomerativeClustering(metric=%s)" % metric, size=20)
+    plt.suptitle("AgglomerativeClustering(metric=%s)" % metric, size=20, y=1)
 
 
 plt.show()

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Gael Varoquaux\n# License: BSD 3-Clause or CC-0\n\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom sklearn.cluster import AgglomerativeClustering\nfrom sklearn.metrics import pairwise_distances\n\nnp.random.seed(0)\n\n# Generate waveform data\nn_features = 2000\nt = np.pi * np.linspace(0, 1, n_features)\n\n\ndef sqr(x):\n    return np.sign(np.cos(x))\n\n\nX = list()\ny = list()\nfor i, (phi, a) in enumerate([(0.5, 0.15), (0.5, 0.6), (0.3, 0.2)]):\n    for _ in range(30):\n        phase_noise = 0.01 * np.random.normal()\n        amplitude_noise = 0.04 * np.random.normal()\n        additional_noise = 1 - 2 * np.random.rand(n_features)\n        # Make the noise sparse\n        additional_noise[np.abs(additional_noise) < 0.997] = 0\n\n        X.append(\n            12\n            * (\n                (a + amplitude_noise) * (sqr(6 * (t + phi + phase_noise)))\n                + additional_noise\n            )\n        )\n        y.append(i)\n\nX = np.array(X)\ny = np.array(y)\n\nn_clusters = 3\n\nlabels = (\"Waveform 1\", \"Waveform 2\", \"Waveform 3\")\n\n# Plot the ground-truth labelling\nplt.figure()\nplt.axes([0, 0, 1, 1])\nfor l, c, n in zip(range(n_clusters), \"rgb\", labels):\n    lines = plt.plot(X[y == l].T, c=c, alpha=0.5)\n    lines[0].set_label(n)\n\nplt.legend(loc=\"best\")\n\nplt.axis(\"tight\")\nplt.axis(\"off\")\nplt.suptitle(\"Ground truth\", size=20)\n\n\n# Plot the distances\nfor index, metric in enumerate([\"cosine\", \"euclidean\", \"cityblock\"]):\n    avg_dist = np.zeros((n_clusters, n_clusters))\n    plt.figure(figsize=(5, 4.5))\n    for i in range(n_clusters):\n        for j in range(n_clusters):\n            avg_dist[i, j] = pairwise_distances(\n                X[y == i], X[y == j], metric=metric\n            ).mean()\n    avg_dist /= avg_dist.max()\n    for i in range(n_clusters):\n        for j in range(n_clusters):\n            plt.text(\n                i,\n                j,\n                \"%5.3f\" % avg_dist[i, j],\n                verticalalignment=\"center\",\n                horizontalalignment=\"center\",\n            )\n\n    plt.imshow(avg_dist, interpolation=\"nearest\", cmap=plt.cm.gnuplot2, vmin=0)\n    plt.xticks(range(n_clusters), labels, rotation=45)\n    plt.yticks(range(n_clusters), labels)\n    plt.colorbar()\n    plt.suptitle(\"Interclass %s distances\" % metric, size=18)\n    plt.tight_layout()\n\n\n# Plot clustering results\nfor index, metric in enumerate([\"cosine\", \"euclidean\", \"cityblock\"]):\n    model = AgglomerativeClustering(\n        n_clusters=n_clusters, linkage=\"average\", metric=metric\n    )\n    model.fit(X)\n    plt.figure()\n    plt.axes([0, 0, 1, 1])\n    for l, c in zip(np.arange(model.n_clusters), \"rgbk\"):\n        plt.plot(X[model.labels_ == l].T, c=c, alpha=0.5)\n    plt.axis(\"tight\")\n    plt.axis(\"off\")\n    plt.suptitle(\"AgglomerativeClustering(metric=%s)\" % metric, size=20)\n\n\nplt.show()"
+        "# Author: Gael Varoquaux\n# License: BSD 3-Clause or CC-0\n\nimport matplotlib.pyplot as plt\nimport matplotlib.patheffects as PathEffects\nimport numpy as np\n\nfrom sklearn.cluster import AgglomerativeClustering\nfrom sklearn.metrics import pairwise_distances\n\nnp.random.seed(0)\n\n# Generate waveform data\nn_features = 2000\nt = np.pi * np.linspace(0, 1, n_features)\n\n\ndef sqr(x):\n    return np.sign(np.cos(x))\n\n\nX = list()\ny = list()\nfor i, (phi, a) in enumerate([(0.5, 0.15), (0.5, 0.6), (0.3, 0.2)]):\n    for _ in range(30):\n        phase_noise = 0.01 * np.random.normal()\n        amplitude_noise = 0.04 * np.random.normal()\n        additional_noise = 1 - 2 * np.random.rand(n_features)\n        # Make the noise sparse\n        additional_noise[np.abs(additional_noise) < 0.997] = 0\n\n        X.append(\n            12\n            * (\n                (a + amplitude_noise) * (sqr(6 * (t + phi + phase_noise)))\n                + additional_noise\n            )\n        )\n        y.append(i)\n\nX = np.array(X)\ny = np.array(y)\n\nn_clusters = 3\n\nlabels = (\"Waveform 1\", \"Waveform 2\", \"Waveform 3\")\n\ncolors = [\"#f7bd01\", \"#377eb8\", \"#f781bf\"]\n\n# Plot the ground-truth labelling\nplt.figure()\nplt.axes([0, 0, 1, 1])\nfor l, color, n in zip(range(n_clusters), colors, labels):\n    lines = plt.plot(X[y == l].T, c=color, alpha=0.5)\n    lines[0].set_label(n)\n\nplt.legend(loc=\"best\")\n\nplt.axis(\"tight\")\nplt.axis(\"off\")\nplt.suptitle(\"Ground truth\", size=20, y=1)\n\n\n# Plot the distances\nfor index, metric in enumerate([\"cosine\", \"euclidean\", \"cityblock\"]):\n    avg_dist = np.zeros((n_clusters, n_clusters))\n    plt.figure(figsize=(5, 4.5))\n    for i in range(n_clusters):\n        for j in range(n_clusters):\n            avg_dist[i, j] = pairwise_distances(\n                X[y == i], X[y == j], metric=metric\n            ).mean()\n    avg_dist /= avg_dist.max()\n    for i in range(n_clusters):\n        for j in range(n_clusters):\n            t = plt.text(\n                i,\n                j,\n                \"%5.3f\" % avg_dist[i, j],\n                verticalalignment=\"center\",\n                horizontalalignment=\"center\",\n            )\n            t.set_path_effects(\n                [PathEffects.withStroke(linewidth=5, foreground=\"w\", alpha=0.5)]\n            )\n\n    plt.imshow(avg_dist, interpolation=\"nearest\", cmap=\"cividis\", vmin=0)\n    plt.xticks(range(n_clusters), labels, rotation=45)\n    plt.yticks(range(n_clusters), labels)\n    plt.colorbar()\n    plt.suptitle(\"Interclass %s distances\" % metric, size=18, y=1)\n    plt.tight_layout()\n\n\n# Plot clustering results\nfor index, metric in enumerate([\"cosine\", \"euclidean\", \"cityblock\"]):\n    model = AgglomerativeClustering(\n        n_clusters=n_clusters, linkage=\"average\", metric=metric\n    )\n    model.fit(X)\n    plt.figure()\n    plt.axes([0, 0, 1, 1])\n    for l, color in zip(np.arange(model.n_clusters), colors):\n        plt.plot(X[model.labels_ == l].T, c=color, alpha=0.5)\n    plt.axis(\"tight\")\n    plt.axis(\"off\")\n    plt.suptitle(\"AgglomerativeClustering(metric=%s)\" % metric, size=20, y=1)\n\n\nplt.show()"
       ]
     }
   ],