Pushing the docs to dev/ for branch: main, commit 7ec1bfc2ab7425bcd984d631b5bfeb9082ce11bf

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Robert Layton <[email protected]>\n#          Olivier Grisel <[email protected]>\n#          Mathieu Blondel <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.cluster import KMeans\nfrom sklearn.metrics import pairwise_distances_argmin\nfrom sklearn.datasets import load_sample_image\nfrom sklearn.utils import shuffle\nfrom time import time\n\nn_colors = 64\n\n# Load the Summer Palace photo\nchina = load_sample_image(\"china.jpg\")\n\n# Convert to floats instead of the default 8 bits integer coding. Dividing by\n# 255 is important so that plt.imshow behaves works well on float data (need to\n# be in the range [0-1])\nchina = np.array(china, dtype=np.float64) / 255\n\n# Load Image and transform to a 2D numpy array.\nw, h, d = original_shape = tuple(china.shape)\nassert d == 3\nimage_array = np.reshape(china, (w * h, d))\n\nprint(\"Fitting model on a small sub-sample of the data\")\nt0 = time()\nimage_array_sample = shuffle(image_array, random_state=0, n_samples=1_000)\nkmeans = KMeans(n_clusters=n_colors, random_state=0).fit(image_array_sample)\nprint(f\"done in {time() - t0:0.3f}s.\")\n\n# Get labels for all points\nprint(\"Predicting color indices on the full image (k-means)\")\nt0 = time()\nlabels = kmeans.predict(image_array)\nprint(f\"done in {time() - t0:0.3f}s.\")\n\n\ncodebook_random = shuffle(image_array, random_state=0, n_samples=n_colors)\nprint(\"Predicting color indices on the full image (random)\")\nt0 = time()\nlabels_random = pairwise_distances_argmin(codebook_random, image_array, axis=0)\nprint(f\"done in {time() - t0:0.3f}s.\")\n\n\ndef recreate_image(codebook, labels, w, h):\n    \"\"\"Recreate the (compressed) image from the code book & labels\"\"\"\n    return codebook[labels].reshape(w, h, -1)\n\n\n# Display all results, alongside original image\nplt.figure(1)\nplt.clf()\nplt.axis(\"off\")\nplt.title(\"Original image (96,615 colors)\")\nplt.imshow(china)\n\nplt.figure(2)\nplt.clf()\nplt.axis(\"off\")\nplt.title(f\"Quantized image ({n_colors} colors, K-Means)\")\nplt.imshow(recreate_image(kmeans.cluster_centers_, labels, w, h))\n\nplt.figure(3)\nplt.clf()\nplt.axis(\"off\")\nplt.title(f\"Quantized image ({n_colors} colors, Random)\")\nplt.imshow(recreate_image(codebook_random, labels_random, w, h))\nplt.show()"
+        "# Authors: Robert Layton <[email protected]>\n#          Olivier Grisel <[email protected]>\n#          Mathieu Blondel <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.cluster import KMeans\nfrom sklearn.metrics import pairwise_distances_argmin\nfrom sklearn.datasets import load_sample_image\nfrom sklearn.utils import shuffle\nfrom time import time\n\nn_colors = 64\n\n# Load the Summer Palace photo\nchina = load_sample_image(\"china.jpg\")\n\n# Convert to floats instead of the default 8 bits integer coding. Dividing by\n# 255 is important so that plt.imshow behaves works well on float data (need to\n# be in the range [0-1])\nchina = np.array(china, dtype=np.float64) / 255\n\n# Load Image and transform to a 2D numpy array.\nw, h, d = original_shape = tuple(china.shape)\nassert d == 3\nimage_array = np.reshape(china, (w * h, d))\n\nprint(\"Fitting model on a small sub-sample of the data\")\nt0 = time()\nimage_array_sample = shuffle(image_array, random_state=0, n_samples=1_000)\nkmeans = KMeans(n_clusters=n_colors, n_init=\"auto\", random_state=0).fit(\n    image_array_sample\n)\nprint(f\"done in {time() - t0:0.3f}s.\")\n\n# Get labels for all points\nprint(\"Predicting color indices on the full image (k-means)\")\nt0 = time()\nlabels = kmeans.predict(image_array)\nprint(f\"done in {time() - t0:0.3f}s.\")\n\n\ncodebook_random = shuffle(image_array, random_state=0, n_samples=n_colors)\nprint(\"Predicting color indices on the full image (random)\")\nt0 = time()\nlabels_random = pairwise_distances_argmin(codebook_random, image_array, axis=0)\nprint(f\"done in {time() - t0:0.3f}s.\")\n\n\ndef recreate_image(codebook, labels, w, h):\n    \"\"\"Recreate the (compressed) image from the code book & labels\"\"\"\n    return codebook[labels].reshape(w, h, -1)\n\n\n# Display all results, alongside original image\nplt.figure(1)\nplt.clf()\nplt.axis(\"off\")\nplt.title(\"Original image (96,615 colors)\")\nplt.imshow(china)\n\nplt.figure(2)\nplt.clf()\nplt.axis(\"off\")\nplt.title(f\"Quantized image ({n_colors} colors, K-Means)\")\nplt.imshow(recreate_image(kmeans.cluster_centers_, labels, w, h))\n\nplt.figure(3)\nplt.clf()\nplt.axis(\"off\")\nplt.title(f\"Quantized image ({n_colors} colors, Random)\")\nplt.imshow(recreate_image(codebook_random, labels_random, w, h))\nplt.show()"
       ]
     }
   ],

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -52,7 +52,9 @@
 print("Fitting model on a small sub-sample of the data")
 t0 = time()
 image_array_sample = shuffle(image_array, random_state=0, n_samples=1_000)
-kmeans = KMeans(n_clusters=n_colors, random_state=0).fit(image_array_sample)
+kmeans = KMeans(n_clusters=n_colors, n_init="auto", random_state=0).fit(
+    image_array_sample
+)
 print(f"done in {time() - t0:0.3f}s.")
 
 # Get labels for all points