def test_shc_semi_supervised_scoring_data_affinity():
"""Test semi-supervised learning for SHC when scoring_data='affinity'."""
# Passing feature matrix
X1, y1 = generate_data(supervised=True, affinity=False)
def _scoring1(X_affinity, labels_true, labels_pred):
assert X_affinity.shape[0] == X_affinity.shape[1]
assert X_affinity.shape != X1.shape
score = b3_f_score(labels_true, labels_pred)
return score
clusterer = ScipyHierarchicalClustering(scoring=_scoring1,
scoring_data="affinity",
affinity=euclidean_distances)
clusterer.fit(X1, y1)
labels = clusterer.labels_
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
# Passing affinity matrix
X2, y2 = generate_data(supervised=True, affinity=True)
def _scoring2(X_affinity, labels_true, labels_pred):
assert X_affinity.shape[0] == X_affinity.shape[1]
assert X_affinity.shape == X2.shape
score = b3_f_score(labels_true, labels_pred)
return score
clusterer = ScipyHierarchicalClustering(scoring=_scoring2,
scoring_data="affinity",
affinity="precomputed")
clusterer.fit(X2, y2)
labels = clusterer.labels_
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
def hcluster(X, attrs):
"""
Hierarchical Clustering.
Return Example:
{'children': [
{'children': [], 'name': 2, 'value': 150.0039243544126},
{'children': [
{'children': [], 'name': 1, 'value': 2.509279181210386},
{'children': [
{'children': [], 'name': 0, 'value': 2.4987419269136737},
{'children': [], 'name': 3, 'value': 2.4987419269136737}
], 'name': 4,'value': 4.997483853827347}
], 'name': 5, 'value': 5.018558362420772}
], 'name': 6, 'value': 300.0078487088252}
"""
n_clusters = int(attrs['kNumber'])
hcluster = ScipyHierarchicalClustering(method=attrs['distance'],
affinity=attrs['affinity'],
n_clusters=n_clusters)
hcluster.fit(X)
labels = hcluster.labels_
# Z = hcluster.linkage_
# return HClusterTree(Z).to_dict()
save_clusterer(hcluster)
return scatterplot(X, labels, n_clusters)
def hcluster(X, attrs):
"""
Hierarchical Clustering.
Return Example:
{'children': [
{'children': [], 'name': 2, 'value': 150.0039243544126},
{'children': [
{'children': [], 'name': 1, 'value': 2.509279181210386},
{'children': [
{'children': [], 'name': 0, 'value': 2.4987419269136737},
{'children': [], 'name': 3, 'value': 2.4987419269136737}
], 'name': 4,'value': 4.997483853827347}
], 'name': 5, 'value': 5.018558362420772}
], 'name': 6, 'value': 300.0078487088252}
"""
n_clusters = int(attrs['kNumber'])
hcluster = ScipyHierarchicalClustering(method=attrs['distance'],
affinity=attrs['affinity'],
n_clusters=n_clusters)
hcluster.fit(X)
labels = hcluster.labels_
# Z = hcluster.linkage_
# return HClusterTree(Z).to_dict()
# save_clusterer(hcluster)
return scatterplot(X, labels, n_clusters)
def test_shc_semi_supervised_scoring_data_none():
"""Test semi-supervised learning for SHC when scoring_data is None."""
X, y = generate_data(supervised=True, affinity=False)
def _scoring(labels_true, labels_pred):
score = b3_f_score(labels_true, labels_pred)
return score
# We should find all 4 clusters
clusterer = ScipyHierarchicalClustering(scoring=_scoring)
clusterer.fit(X, y)
labels = clusterer.labels_
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
def test_shc_semi_supervised_scoring_data_raw():
"""Test semi-supervised learning for SHC when scoring_data='raw'."""
X, y = generate_data(supervised=True, affinity=False)
def _scoring(X_raw, labels_true, labels_pred):
assert X_raw.shape == X.shape
score = b3_f_score(labels_true, labels_pred)
return score
clusterer = ScipyHierarchicalClustering(scoring=_scoring,
scoring_data="raw")
clusterer.fit(X, y)
labels = clusterer.labels_
assert_array_equal([25, 25, 25, 25], np.bincount(labels))
