Pushing the docs to dev/ for branch: main, commit 3d16a21b6c9c6940509d98e5e0c030658f7c348c

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -27,7 +27,7 @@
 X, y = make_blobs(n_samples=n_samples, random_state=random_state)
 
 # Incorrect number of clusters
-y_pred = KMeans(n_clusters=2, random_state=random_state).fit_predict(X)
+y_pred = KMeans(n_clusters=2, n_init="auto", random_state=random_state).fit_predict(X)
 
 plt.subplot(221)
 plt.scatter(X[:, 0], X[:, 1], c=y_pred)
@@ -36,7 +36,9 @@
 # Anisotropicly distributed data
 transformation = [[0.60834549, -0.63667341], [-0.40887718, 0.85253229]]
 X_aniso = np.dot(X, transformation)
-y_pred = KMeans(n_clusters=3, random_state=random_state).fit_predict(X_aniso)
+y_pred = KMeans(n_clusters=3, n_init=10, random_state=random_state).fit_predict(
+    X_aniso
+)
 
 plt.subplot(222)
 plt.scatter(X_aniso[:, 0], X_aniso[:, 1], c=y_pred)
@@ -46,15 +48,19 @@
 X_varied, y_varied = make_blobs(
     n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=random_state
 )
-y_pred = KMeans(n_clusters=3, random_state=random_state).fit_predict(X_varied)
+y_pred = KMeans(n_clusters=3, n_init="auto", random_state=random_state).fit_predict(
+    X_varied
+)
 
 plt.subplot(223)
 plt.scatter(X_varied[:, 0], X_varied[:, 1], c=y_pred)
 plt.title("Unequal Variance")
 
 # Unevenly sized blobs
 X_filtered = np.vstack((X[y == 0][:500], X[y == 1][:100], X[y == 2][:10]))
-y_pred = KMeans(n_clusters=3, random_state=random_state).fit_predict(X_filtered)
+y_pred = KMeans(n_clusters=3, n_init=10, random_state=random_state).fit_predict(
+    X_filtered
+)
 
 plt.subplot(224)
 plt.scatter(X_filtered[:, 0], X_filtered[:, 1], c=y_pred)

dev/_downloads/5d2d581a4569eb0718dbdb8abf7cbbdf/plot_kmeans_assumptions.py

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Phil Roth <[email protected]>\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn.cluster import KMeans\nfrom sklearn.datasets import make_blobs\n\nplt.figure(figsize=(12, 12))\n\nn_samples = 1500\nrandom_state = 170\nX, y = make_blobs(n_samples=n_samples, random_state=random_state)\n\n# Incorrect number of clusters\ny_pred = KMeans(n_clusters=2, random_state=random_state).fit_predict(X)\n\nplt.subplot(221)\nplt.scatter(X[:, 0], X[:, 1], c=y_pred)\nplt.title(\"Incorrect Number of Blobs\")\n\n# Anisotropicly distributed data\ntransformation = [[0.60834549, -0.63667341], [-0.40887718, 0.85253229]]\nX_aniso = np.dot(X, transformation)\ny_pred = KMeans(n_clusters=3, random_state=random_state).fit_predict(X_aniso)\n\nplt.subplot(222)\nplt.scatter(X_aniso[:, 0], X_aniso[:, 1], c=y_pred)\nplt.title(\"Anisotropicly Distributed Blobs\")\n\n# Different variance\nX_varied, y_varied = make_blobs(\n    n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=random_state\n)\ny_pred = KMeans(n_clusters=3, random_state=random_state).fit_predict(X_varied)\n\nplt.subplot(223)\nplt.scatter(X_varied[:, 0], X_varied[:, 1], c=y_pred)\nplt.title(\"Unequal Variance\")\n\n# Unevenly sized blobs\nX_filtered = np.vstack((X[y == 0][:500], X[y == 1][:100], X[y == 2][:10]))\ny_pred = KMeans(n_clusters=3, random_state=random_state).fit_predict(X_filtered)\n\nplt.subplot(224)\nplt.scatter(X_filtered[:, 0], X_filtered[:, 1], c=y_pred)\nplt.title(\"Unevenly Sized Blobs\")\n\nplt.show()"
+        "# Author: Phil Roth <[email protected]>\n# License: BSD 3 clause\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn.cluster import KMeans\nfrom sklearn.datasets import make_blobs\n\nplt.figure(figsize=(12, 12))\n\nn_samples = 1500\nrandom_state = 170\nX, y = make_blobs(n_samples=n_samples, random_state=random_state)\n\n# Incorrect number of clusters\ny_pred = KMeans(n_clusters=2, n_init=\"auto\", random_state=random_state).fit_predict(X)\n\nplt.subplot(221)\nplt.scatter(X[:, 0], X[:, 1], c=y_pred)\nplt.title(\"Incorrect Number of Blobs\")\n\n# Anisotropicly distributed data\ntransformation = [[0.60834549, -0.63667341], [-0.40887718, 0.85253229]]\nX_aniso = np.dot(X, transformation)\ny_pred = KMeans(n_clusters=3, n_init=10, random_state=random_state).fit_predict(\n    X_aniso\n)\n\nplt.subplot(222)\nplt.scatter(X_aniso[:, 0], X_aniso[:, 1], c=y_pred)\nplt.title(\"Anisotropicly Distributed Blobs\")\n\n# Different variance\nX_varied, y_varied = make_blobs(\n    n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=random_state\n)\ny_pred = KMeans(n_clusters=3, n_init=\"auto\", random_state=random_state).fit_predict(\n    X_varied\n)\n\nplt.subplot(223)\nplt.scatter(X_varied[:, 0], X_varied[:, 1], c=y_pred)\nplt.title(\"Unequal Variance\")\n\n# Unevenly sized blobs\nX_filtered = np.vstack((X[y == 0][:500], X[y == 1][:100], X[y == 2][:10]))\ny_pred = KMeans(n_clusters=3, n_init=10, random_state=random_state).fit_predict(\n    X_filtered\n)\n\nplt.subplot(224)\nplt.scatter(X_filtered[:, 0], X_filtered[:, 1], c=y_pred)\nplt.title(\"Unevenly Sized Blobs\")\n\nplt.show()"
       ]
     }
   ],