MISC: remove reference to deprecated Ward

Author: GaelVaroquaux

benchmarks/bench_plot_ward.py

@@ -8,9 +8,9 @@
 from scipy.cluster import hierarchy
 import pylab as pl
 
-from sklearn.cluster import Ward
+from sklearn.cluster import AgglomerativeClustering
 
-ward = Ward(n_clusters=3)
+ward = AgglomerativeClustering(n_clusters=3, linkage='ward')
 
 n_samples = np.logspace(.5, 3, 9)
 n_features = np.logspace(1, 3.5, 7)

doc/modules/clustering.rst

@@ -589,11 +589,12 @@ enable only merging of neighboring pixels on an image, as in the
 
 .. warning:: **Connectivity constraints with average and complete linkage**
 
-    Connectivity constraints and complete or average linkage enhance the
-    'rich getting richer' aspect of agglomerative clustering. In the
-    limit of a small number of clusters, they tend to give a few
-    macroscopically occupied clusters and almost empty ones. (see the
-    discussion in
+    Connectivity constraints and complete or average linkage can enhance
+    the 'rich getting richer' aspect of agglomerative clustering,
+    particularly so if they are built with
+    :func:`sklearn.neighbors.kneighbors_graph`. In the limit of a small
+    number of clusters, they tend to give a few macroscopically occupied
+    clusters and almost empty ones. (see the discussion in
     :ref:`example_cluster_plot_agglomerative_clustering.py`).
 
 .. image:: ../auto_examples/cluster/images/plot_agglomerative_clustering_1.png

doc/tutorial/statistical_inference/unsupervised_learning.rst

@@ -213,10 +213,10 @@ transposed data.
    >>> X = np.reshape(images, (len(images), -1))
    >>> connectivity = grid_to_graph(*images[0].shape)
 
-   >>> agglo = cluster.WardAgglomeration(connectivity=connectivity,
+   >>> agglo = cluster.FeatureAgglomeration(connectivity=connectivity,
    ...                                   n_clusters=32)
    >>> agglo.fit(X) # doctest: +ELLIPSIS
-   WardAgglomeration(compute_full_tree='auto',...
+   FeatureAgglomeration(compute_full_tree='auto',...
    >>> X_reduced = agglo.transform(X)
 
    >>> X_approx = agglo.inverse_transform(X_reduced)

examples/cluster/plot_cluster_comparison.py

@@ -72,7 +72,7 @@
     # create clustering estimators
     ms = cluster.MeanShift(bandwidth=bandwidth, bin_seeding=True)
     two_means = cluster.MiniBatchKMeans(n_clusters=2)
-    ward_five = cluster.AgglomerativeClustering(n_clusters=2,
+    ward = cluster.AgglomerativeClustering(n_clusters=2,
                     linkage='ward', connectivity=connectivity)
     spectral = cluster.SpectralClustering(n_clusters=2,
                                           eigen_solver='arpack',
@@ -89,7 +89,7 @@
         ('AffinityPropagation', affinity_propagation),
         ('MeanShift', ms),
         ('SpectralClustering', spectral),
-        ('Ward', ward_five),
+        ('Ward', ward),
         ('AgglomerativeClustering', average_linkage),
         ('DBSCAN', dbscan)]:
         # predict cluster memberships

examples/cluster/plot_digits_agglomeration.py

@@ -26,8 +26,8 @@
 X = np.reshape(images, (len(images), -1))
 connectivity = grid_to_graph(*images[0].shape)
 
-agglo = cluster.WardAgglomeration(connectivity=connectivity,
-                                  n_clusters=32)
+agglo = cluster.FeatureAgglomeration(connectivity=connectivity,
+                                     n_clusters=32)
 
 agglo.fit(X)
 X_reduced = agglo.transform(X)

examples/cluster/plot_feature_agglomeration_vs_univariate_selection.py

@@ -27,7 +27,7 @@
 
 from sklearn.feature_extraction.image import grid_to_graph
 from sklearn import feature_selection
-from sklearn.cluster import WardAgglomeration
+from sklearn.cluster import FeatureAgglomeration
 from sklearn.linear_model import BayesianRidge
 from sklearn.pipeline import Pipeline
 from sklearn.grid_search import GridSearchCV
@@ -66,9 +66,9 @@
 mem = Memory(cachedir=cachedir, verbose=1)
 
 # Ward agglomeration followed by BayesianRidge
-A = grid_to_graph(n_x=size, n_y=size)
-ward = WardAgglomeration(n_clusters=10, connectivity=A, memory=mem,
-                         n_components=1)
+connectivity = grid_to_graph(n_x=size, n_y=size)
+ward = FeatureAgglomeration(n_clusters=10, connectivity=connectivity,
+                            memory=mem, n_components=1)
 clf = Pipeline([('ward', ward), ('ridge', ridge)])
 # Select the optimal number of parcels with grid search
 clf = GridSearchCV(clf, {'ward__n_clusters': [10, 20, 30]}, n_jobs=1, cv=cv)

examples/cluster/plot_ward_structured_vs_unstructured.py

@@ -30,7 +30,7 @@
 import numpy as np
 import pylab as pl
 import mpl_toolkits.mplot3d.axes3d as p3
-from sklearn.cluster import Ward
+from sklearn.cluster import AgglomerativeClustering
 from sklearn.datasets.samples_generator import make_swiss_roll
 
 ###############################################################################
@@ -45,7 +45,7 @@
 # Compute clustering
 print("Compute unstructured hierarchical clustering...")
 st = time.time()
-ward = Ward(n_clusters=6).fit(X)
+ward = AgglomerativeClustering(n_clusters=6, linkage='ward').fit(X)
 elapsed_time = time.time() - st
 label = ward.labels_
 print("Elapsed time: %.2fs" % elapsed_time)
@@ -71,7 +71,8 @@
 # Compute clustering
 print("Compute structured hierarchical clustering...")
 st = time.time()
-ward = Ward(n_clusters=6, connectivity=connectivity).fit(X)
+ward = AgglomerativeClustering(n_clusters=6, connectivity=connectivity,
+                               linkage='ward').fit(X)
 elapsed_time = time.time() - st
 label = ward.labels_
 print("Elapsed time: %.2fs" % elapsed_time)

sklearn/cluster/tests/test_hierarchical.py

@@ -204,6 +204,7 @@ def test_ward_agglomeration():
     mask = np.ones([10, 10], dtype=np.bool)
     X = rnd.randn(50, 100)
     connectivity = grid_to_graph(*mask.shape)
+    assert_warns(DeprecationWarning, WardAgglomeration)
     ward = WardAgglomeration(n_clusters=5, connectivity=connectivity)
     ward.fit(X)
     assert_true(np.size(np.unique(ward.labels_)) == 5)