Pushing the docs to dev/ for branch: master, commit 94366b83195b2c004e6576268ae7ee0d3b772c18

Author: sklearn-ci

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -117,3 +117,30 @@
 
 titanic = fetch_openml('titanic', version=1, as_frame=True)
 print(titanic.data.head()[['pclass', 'embarked']])
+
+############################################################################
+# Precomputed sparse nearest neighbors graph
+# ------------------------------------------
+# Most estimators based on nearest neighbors graphs now accept precomputed
+# sparse graphs as input, to reuse the same graph for multiple estimator fits.
+# To use this feature in a pipeline, one can use the `memory` parameter, along
+# with one of the two new transformers,
+# :class:`~sklearn.neighbors.KNeighborsTransformer` and
+# :class:`~sklearn.neighbors.RadiusNeighborsTransformer`. The precomputation
+# can also be performed by custom estimators to use alternative
+# implementations, such as approximate nearest neighbors methods.
+# See more details in the :ref:`User Guide <neighbors_transformer>`.
+
+from sklearn.neighbors import KNeighborsTransformer
+from sklearn.manifold import Isomap
+from sklearn.pipeline import make_pipeline
+
+estimator = make_pipeline(
+    KNeighborsTransformer(n_neighbors=10, mode='distance'),
+    Isomap(n_neighbors=10, metric='precomputed'),
+    memory='.')
+estimator.fit(X)
+
+# We can decrease the number of neighbors and the graph will not be recomputed.
+estimator.set_params(isomap__n_neighbors=5)
+estimator.fit(X)

dev/_downloads/7ee55c12f8d3eb1dd8d2005d9dd7b6f1/plot_release_highlights_0_22_0.py

@@ -107,6 +107,24 @@
       "source": [
         "from sklearn.datasets import fetch_openml\n\ntitanic = fetch_openml('titanic', version=1, as_frame=True)\nprint(titanic.data.head()[['pclass', 'embarked']])"
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Precomputed sparse nearest neighbors graph\n------------------------------------------\nMost estimators based on nearest neighbors graphs now accept precomputed\nsparse graphs as input, to reuse the same graph for multiple estimator fits.\nTo use this feature in a pipeline, one can use the `memory` parameter, along\nwith one of the two new transformers,\n:class:`~sklearn.neighbors.KNeighborsTransformer` and\n:class:`~sklearn.neighbors.RadiusNeighborsTransformer`. The precomputation\ncan also be performed by custom estimators to use alternative\nimplementations, such as approximate nearest neighbors methods.\nSee more details in the `User Guide <neighbors_transformer>`.\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "from sklearn.neighbors import KNeighborsTransformer\nfrom sklearn.manifold import Isomap\nfrom sklearn.pipeline import make_pipeline\n\nestimator = make_pipeline(\n    KNeighborsTransformer(n_neighbors=10, mode='distance'),\n    Isomap(n_neighbors=10, metric='precomputed'),\n    memory='.')\nestimator.fit(X)\n\n# We can decrease the number of neighbors and the graph will not be recomputed.\nestimator.set_params(isomap__n_neighbors=5)\nestimator.fit(X)"
+      ]
     }
   ],
   "metadata": {