Python sklearn.cluster.FeatureAgglomeration() Examples

The following are 6 code examples of sklearn.cluster.FeatureAgglomeration(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module sklearn.cluster , or try the search function .
Example #1
Source File: test_hierarchical.py    From Mastering-Elasticsearch-7.0 with MIT License 6 votes vote down vote up 
def test_linkage_misc():
    # Misc tests on linkage
    rng = np.random.RandomState(42)
    X = rng.normal(size=(5, 5))
    assert_raises(ValueError, AgglomerativeClustering(linkage='foo').fit, X)
    assert_raises(ValueError, linkage_tree, X, linkage='foo')
    assert_raises(ValueError, linkage_tree, X, connectivity=np.ones((4, 4)))

    # Smoke test FeatureAgglomeration
    FeatureAgglomeration().fit(X)

    # test hierarchical clustering on a precomputed distances matrix
    dis = cosine_distances(X)

    res = linkage_tree(dis, affinity="precomputed")
    assert_array_equal(res[0], linkage_tree(X, affinity="cosine")[0])

    # test hierarchical clustering on a precomputed distances matrix
    res = linkage_tree(X, affinity=manhattan_distances)
    assert_array_equal(res[0], linkage_tree(X, affinity="manhattan")[0])
Example #2
Source File: test_hierarchical.py    From Mastering-Elasticsearch-7.0 with MIT License 6 votes vote down vote up 
def test_ward_agglomeration():
    # Check that we obtain the correct solution in a simplistic case
    rng = np.random.RandomState(0)
    mask = np.ones([10, 10], dtype=np.bool)
    X = rng.randn(50, 100)
    connectivity = grid_to_graph(*mask.shape)
    agglo = FeatureAgglomeration(n_clusters=5, connectivity=connectivity)
    agglo.fit(X)
    assert np.size(np.unique(agglo.labels_)) == 5

    X_red = agglo.transform(X)
    assert X_red.shape[1] == 5
    X_full = agglo.inverse_transform(X_red)
    assert np.unique(X_full[0]).size == 5
    assert_array_almost_equal(agglo.transform(X_full), X_red)

    # Check that fitting with no samples raises a ValueError
    assert_raises(ValueError, agglo.fit, X[:0])
Example #3
Source File: test_hierarchical.py    From twitter-stock-recommendation with MIT License 6 votes vote down vote up 
def test_linkage_misc():
    # Misc tests on linkage
    rng = np.random.RandomState(42)
    X = rng.normal(size=(5, 5))
    assert_raises(ValueError, AgglomerativeClustering(linkage='foo').fit, X)
    assert_raises(ValueError, linkage_tree, X, linkage='foo')
    assert_raises(ValueError, linkage_tree, X, connectivity=np.ones((4, 4)))

    # Smoke test FeatureAgglomeration
    FeatureAgglomeration().fit(X)

    # test hierarchical clustering on a precomputed distances matrix
    dis = cosine_distances(X)

    res = linkage_tree(dis, affinity="precomputed")
    assert_array_equal(res[0], linkage_tree(X, affinity="cosine")[0])

    # test hierarchical clustering on a precomputed distances matrix
    res = linkage_tree(X, affinity=manhattan_distances)
    assert_array_equal(res[0], linkage_tree(X, affinity="manhattan")[0])
Example #4
Source File: test_hierarchical.py    From twitter-stock-recommendation with MIT License 6 votes vote down vote up 
def test_ward_agglomeration():
    # Check that we obtain the correct solution in a simplistic case
    rng = np.random.RandomState(0)
    mask = np.ones([10, 10], dtype=np.bool)
    X = rng.randn(50, 100)
    connectivity = grid_to_graph(*mask.shape)
    agglo = FeatureAgglomeration(n_clusters=5, connectivity=connectivity)
    agglo.fit(X)
    assert_true(np.size(np.unique(agglo.labels_)) == 5)

    X_red = agglo.transform(X)
    assert_true(X_red.shape[1] == 5)
    X_full = agglo.inverse_transform(X_red)
    assert_true(np.unique(X_full[0]).size == 5)
    assert_array_almost_equal(agglo.transform(X_full), X_red)

    # Check that fitting with no samples raises a ValueError
    assert_raises(ValueError, agglo.fit, X[:0])
Example #5
Source File: test_feature_agglomeration.py    From Mastering-Elasticsearch-7.0 with MIT License 5 votes vote down vote up 
def test_feature_agglomeration():
    n_clusters = 1
    X = np.array([0, 0, 1]).reshape(1, 3)  # (n_samples, n_features)

    agglo_mean = FeatureAgglomeration(n_clusters=n_clusters,
                                      pooling_func=np.mean)
    agglo_median = FeatureAgglomeration(n_clusters=n_clusters,
                                        pooling_func=np.median)
    assert_no_warnings(agglo_mean.fit, X)
    assert_no_warnings(agglo_median.fit, X)
    assert np.size(np.unique(agglo_mean.labels_)) == n_clusters
    assert np.size(np.unique(agglo_median.labels_)) == n_clusters
    assert np.size(agglo_mean.labels_) == X.shape[1]
    assert np.size(agglo_median.labels_) == X.shape[1]

    # Test transform
    Xt_mean = agglo_mean.transform(X)
    Xt_median = agglo_median.transform(X)
    assert Xt_mean.shape[1] == n_clusters
    assert Xt_median.shape[1] == n_clusters
    assert Xt_mean == np.array([1 / 3.])
    assert Xt_median == np.array([0.])

    # Test inverse transform
    X_full_mean = agglo_mean.inverse_transform(Xt_mean)
    X_full_median = agglo_median.inverse_transform(Xt_median)
    assert np.unique(X_full_mean[0]).size == n_clusters
    assert np.unique(X_full_median[0]).size == n_clusters

    assert_array_almost_equal(agglo_mean.transform(X_full_mean),
                              Xt_mean)
    assert_array_almost_equal(agglo_median.transform(X_full_median),
                              Xt_median)
Example #6
Source File: test_cluster.py    From pandas-ml with BSD 3-Clause "New" or "Revised" License 3 votes vote down vote up 
def test_objectmapper(self):
        df = pdml.ModelFrame([])
        self.assertIs(df.cluster.AffinityPropagation, cluster.AffinityPropagation)
        self.assertIs(df.cluster.AgglomerativeClustering, cluster.AgglomerativeClustering)
        self.assertIs(df.cluster.Birch, cluster.Birch)
        self.assertIs(df.cluster.DBSCAN, cluster.DBSCAN)
        self.assertIs(df.cluster.FeatureAgglomeration, cluster.FeatureAgglomeration)
        self.assertIs(df.cluster.KMeans, cluster.KMeans)
        self.assertIs(df.cluster.MiniBatchKMeans, cluster.MiniBatchKMeans)
        self.assertIs(df.cluster.MeanShift, cluster.MeanShift)
        self.assertIs(df.cluster.SpectralClustering, cluster.SpectralClustering)

        self.assertIs(df.cluster.bicluster.SpectralBiclustering,
                      cluster.bicluster.SpectralBiclustering)
        self.assertIs(df.cluster.bicluster.SpectralCoclustering,
                      cluster.bicluster.SpectralCoclustering)