def test_partial_fit():
"""Test partial_fit."""
blocks = (y <= 1)
clusterer1 = BlockClustering(blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer1.partial_fit(X[y <= 1], blocks=blocks[y <= 1])
assert_equal(len(clusterer1.clusterers_), 1)
clusterer1.partial_fit(X[y > 1], blocks=blocks[y > 1])
assert_equal(len(clusterer1.clusterers_), 2)
clusterer2 = BlockClustering(blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer2.fit(X, blocks=blocks)
c1 = clusterer1.predict(X, blocks=blocks)
c2 = clusterer2.labels_
assert_equal(paired_f_score(c1, c2), 1.0)
def test_partial_fit():
"""Test partial_fit."""
blocks = (y <= 1)
clusterer1 = BlockClustering(blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer1.partial_fit(X[y <= 1], blocks=blocks[y <= 1])
assert_equal(len(clusterer1.clusterers_), 1)
clusterer1.partial_fit(X[y > 1], blocks=blocks[y > 1])
assert_equal(len(clusterer1.clusterers_), 2)
clusterer2 = BlockClustering(blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer2.fit(X, blocks=blocks)
c1 = clusterer1.predict(X, blocks=blocks)
c2 = clusterer2.labels_
assert_equal(paired_f_score(c1, c2), 1.0)
truth = data["y"]
print("hello")
# Block clustering with fixed threshold
block_clusterer = BlockClustering(
blocking=block_last_name_first_initial,
base_estimator=ScipyHierarchicalClustering(threshold=0.5,
affinity=affinity,
method="complete"),
verbose=3,
n_jobs=-1)
block_clusterer.fit(X)
labels = block_clusterer.labels_
# Print clusters
for cluster in np.unique(labels):
entries = set()
for name, affiliation in X[labels == cluster]:
entries.add((name, affiliation))
print("Cluster #%d = %s" % (cluster, entries))
print()
# Statistics
print("Number of blocks =", len(block_clusterer.clusterers_))
print("True number of clusters", len(np.unique(truth)))
print("Number of computed clusters", len(np.unique(labels)))
print("Paired F-score =", paired_f_score(truth, labels))
X = data["X"]
truth = data["y"]
# Block clustering with fixed threshold
block_clusterer = BlockClustering(
blocking=block_last_name_first_initial,
base_estimator=ScipyHierarchicalClustering(
threshold=0.5,
affinity=affinity,
method="complete"),
verbose=3,
n_jobs=-1)
block_clusterer.fit(X)
labels = block_clusterer.labels_
# Print clusters
for cluster in np.unique(labels):
entries = set()
for name, affiliation in X[labels == cluster]:
entries.add((name, affiliation))
print("Cluster #%d = %s" % (cluster, entries))
print()
# Statistics
print("Number of blocks =", len(block_clusterer.clusterers_))
print("True number of clusters", len(np.unique(truth)))
print("Number of computed clusters", len(np.unique(labels)))
print("Paired F-score =", paired_f_score(truth, labels))
