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

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -98,7 +98,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.decomposition import TruncatedSVD\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis\nfrom sklearn.ensemble import RandomTreesEmbedding\nfrom sklearn.manifold import (\n    Isomap,\n    LocallyLinearEmbedding,\n    MDS,\n    SpectralEmbedding,\n    TSNE,\n)\nfrom sklearn.neighbors import NeighborhoodComponentsAnalysis\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.random_projection import SparseRandomProjection\n\nembeddings = {\n    \"Random projection embedding\": SparseRandomProjection(\n        n_components=2, random_state=42\n    ),\n    \"Truncated SVD embedding\": TruncatedSVD(n_components=2),\n    \"Linear Discriminant Analysis embedding\": LinearDiscriminantAnalysis(\n        n_components=2\n    ),\n    \"Isomap embedding\": Isomap(n_neighbors=n_neighbors, n_components=2),\n    \"Standard LLE embedding\": LocallyLinearEmbedding(\n        n_neighbors=n_neighbors, n_components=2, method=\"standard\"\n    ),\n    \"Modified LLE embedding\": LocallyLinearEmbedding(\n        n_neighbors=n_neighbors, n_components=2, method=\"modified\"\n    ),\n    \"Hessian LLE embedding\": LocallyLinearEmbedding(\n        n_neighbors=n_neighbors, n_components=2, method=\"hessian\"\n    ),\n    \"LTSA LLE embedding\": LocallyLinearEmbedding(\n        n_neighbors=n_neighbors, n_components=2, method=\"ltsa\"\n    ),\n    \"MDS embedding\": MDS(n_components=2, n_init=1, max_iter=120, n_jobs=2),\n    \"Random Trees embedding\": make_pipeline(\n        RandomTreesEmbedding(n_estimators=200, max_depth=5, random_state=0),\n        TruncatedSVD(n_components=2),\n    ),\n    \"Spectral embedding\": SpectralEmbedding(\n        n_components=2, random_state=0, eigen_solver=\"arpack\"\n    ),\n    \"t-SNE embeedding\": TSNE(\n        n_components=2,\n        n_iter=500,\n        n_iter_without_progress=150,\n        n_jobs=2,\n        random_state=0,\n    ),\n    \"NCA embedding\": NeighborhoodComponentsAnalysis(\n        n_components=2, init=\"pca\", random_state=0\n    ),\n}"
+        "from sklearn.decomposition import TruncatedSVD\nfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis\nfrom sklearn.ensemble import RandomTreesEmbedding\nfrom sklearn.manifold import (\n    Isomap,\n    LocallyLinearEmbedding,\n    MDS,\n    SpectralEmbedding,\n    TSNE,\n)\nfrom sklearn.neighbors import NeighborhoodComponentsAnalysis\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.random_projection import SparseRandomProjection\n\nembeddings = {\n    \"Random projection embedding\": SparseRandomProjection(\n        n_components=2, random_state=42\n    ),\n    \"Truncated SVD embedding\": TruncatedSVD(n_components=2),\n    \"Linear Discriminant Analysis embedding\": LinearDiscriminantAnalysis(\n        n_components=2\n    ),\n    \"Isomap embedding\": Isomap(n_neighbors=n_neighbors, n_components=2),\n    \"Standard LLE embedding\": LocallyLinearEmbedding(\n        n_neighbors=n_neighbors, n_components=2, method=\"standard\"\n    ),\n    \"Modified LLE embedding\": LocallyLinearEmbedding(\n        n_neighbors=n_neighbors, n_components=2, method=\"modified\"\n    ),\n    \"Hessian LLE embedding\": LocallyLinearEmbedding(\n        n_neighbors=n_neighbors, n_components=2, method=\"hessian\"\n    ),\n    \"LTSA LLE embedding\": LocallyLinearEmbedding(\n        n_neighbors=n_neighbors, n_components=2, method=\"ltsa\"\n    ),\n    \"MDS embedding\": MDS(\n        n_components=2, n_init=1, max_iter=120, n_jobs=2, normalized_stress=\"auto\"\n    ),\n    \"Random Trees embedding\": make_pipeline(\n        RandomTreesEmbedding(n_estimators=200, max_depth=5, random_state=0),\n        TruncatedSVD(n_components=2),\n    ),\n    \"Spectral embedding\": SpectralEmbedding(\n        n_components=2, random_state=0, eigen_solver=\"arpack\"\n    ),\n    \"t-SNE embeedding\": TSNE(\n        n_components=2,\n        n_iter=500,\n        n_iter_without_progress=150,\n        n_jobs=2,\n        random_state=0,\n    ),\n    \"NCA embedding\": NeighborhoodComponentsAnalysis(\n        n_components=2, init=\"pca\", random_state=0\n    ),\n}"
       ]
     },
     {

dev/_downloads/1e0968da80ca868bbdf21c1d0547f68c/plot_lle_digits.ipynb

@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\n\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.utils import shuffle\n\n\ndef load_ames_housing():\n    df = fetch_openml(name=\"house_prices\", as_frame=True, parser=\"pandas\")\n    X = df.data\n    y = df.target\n\n    features = [\n        \"YrSold\",\n        \"HeatingQC\",\n        \"Street\",\n        \"YearRemodAdd\",\n        \"Heating\",\n        \"MasVnrType\",\n        \"BsmtUnfSF\",\n        \"Foundation\",\n        \"MasVnrArea\",\n        \"MSSubClass\",\n        \"ExterQual\",\n        \"Condition2\",\n        \"GarageCars\",\n        \"GarageType\",\n        \"OverallQual\",\n        \"TotalBsmtSF\",\n        \"BsmtFinSF1\",\n        \"HouseStyle\",\n        \"MiscFeature\",\n        \"MoSold\",\n    ]\n\n    X = X[features]\n    X, y = shuffle(X, y, random_state=0)\n\n    X = X[:600]\n    y = y[:600]\n    return X, np.log(y)\n\n\nX, y = load_ames_housing()"
+        "import numpy as np\n\nfrom sklearn.datasets import fetch_openml\nfrom sklearn.utils import shuffle\n\n\ndef load_ames_housing():\n    df = fetch_openml(name=\"house_prices\", as_frame=True, parser=\"pandas\")\n    X = df.data\n    y = df.target\n\n    features = [\n        \"YrSold\",\n        \"HeatingQC\",\n        \"Street\",\n        \"YearRemodAdd\",\n        \"Heating\",\n        \"MasVnrType\",\n        \"BsmtUnfSF\",\n        \"Foundation\",\n        \"MasVnrArea\",\n        \"MSSubClass\",\n        \"ExterQual\",\n        \"Condition2\",\n        \"GarageCars\",\n        \"GarageType\",\n        \"OverallQual\",\n        \"TotalBsmtSF\",\n        \"BsmtFinSF1\",\n        \"HouseStyle\",\n        \"MiscFeature\",\n        \"MoSold\",\n    ]\n\n    X = X.loc[:,features]\n    X, y = shuffle(X, y, random_state=0)\n\n    X = X.iloc[:600]\n    y = y.iloc[:600]\n    return X, np.log(y)\n\n\nX, y = load_ames_housing()"
       ]
     },
     {

dev/_downloads/3c9b7bcd0b16f172ac12ffad61f3b5f0/plot_stack_predictors.ipynb

@@ -191,6 +191,7 @@ def plot_gallery(title, images, n_col=n_col, n_row=n_row, cmap=plt.cm.gray):
     batch_size=20,
     max_iter=50,
     random_state=rng,
+    n_init="auto",
 )
 kmeans_estimator.fit(faces_centered)
 plot_gallery(

dev/_downloads/4825fc8223d1af0f3b61080c3dea3a62/plot_faces_decomposition.py

@@ -36,7 +36,7 @@
 # Anisotropicly distributed data
 transformation = [[0.60834549, -0.63667341], [-0.40887718, 0.85253229]]
 X_aniso = np.dot(X, transformation)
-y_pred = KMeans(n_clusters=3, n_init=10, random_state=random_state).fit_predict(
+y_pred = KMeans(n_clusters=3, n_init="auto", random_state=random_state).fit_predict(
     X_aniso
 )
 

dev/_downloads/5d2d581a4569eb0718dbdb8abf7cbbdf/plot_kmeans_assumptions.py

@@ -134,7 +134,9 @@ def plot_embedding(X, title):
     "LTSA LLE embedding": LocallyLinearEmbedding(
         n_neighbors=n_neighbors, n_components=2, method="ltsa"
     ),
-    "MDS embedding": MDS(n_components=2, n_init=1, max_iter=120, n_jobs=2),
+    "MDS embedding": MDS(
+        n_components=2, n_init=1, max_iter=120, n_jobs=2, normalized_stress="auto"
+    ),
     "Random Trees embedding": make_pipeline(
         RandomTreesEmbedding(n_estimators=200, max_depth=5, random_state=0),
         TruncatedSVD(n_components=2),

dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -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, 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()"
+        "# 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=\"auto\", 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()"
       ]
     }
   ],

dev/_downloads/9d97cc4ed755b7f2c7f9311bccc89a00/plot_lle_digits.py

@@ -72,11 +72,11 @@ def load_ames_housing():
         "MoSold",
     ]
 
-    X = X[features]
+    X = X.loc[:,features]
     X, y = shuffle(X, y, random_state=0)
 
-    X = X[:600]
-    y = y[:600]
+    X = X.iloc[:600]
+    y = y.iloc[:600]
     return X, np.log(y)
 
 

dev/_downloads/b05e6cdf6d51481f37bf29b0bb92995e/plot_kmeans_assumptions.ipynb

@@ -184,7 +184,7 @@
       },
       "outputs": [],
       "source": [
-        "kmeans_estimator = cluster.MiniBatchKMeans(\n    n_clusters=n_components,\n    tol=1e-3,\n    batch_size=20,\n    max_iter=50,\n    random_state=rng,\n)\nkmeans_estimator.fit(faces_centered)\nplot_gallery(\n    \"Cluster centers - MiniBatchKMeans\",\n    kmeans_estimator.cluster_centers_[:n_components],\n)"
+        "kmeans_estimator = cluster.MiniBatchKMeans(\n    n_clusters=n_components,\n    tol=1e-3,\n    batch_size=20,\n    max_iter=50,\n    random_state=rng,\n    n_init=\"auto\",\n)\nkmeans_estimator.fit(faces_centered)\nplot_gallery(\n    \"Cluster centers - MiniBatchKMeans\",\n    kmeans_estimator.cluster_centers_[:n_components],\n)"
       ]
     },
     {