def analyze_clustering(cls, separated_decomposed_clusters, distance_matrix,
analysis):
"""
Performs the overlap analysis of a clustering (calculates global measurements).
"""
analysis["total_num_clusters"] = 0
analysis["total_num_elements"] = 0
analysis["overlap"] = OverlapCalculator.calculate_clustering_overlap(
mergeSeparatedClusters(separated_decomposed_clusters),
distance_matrix)
analysis[
"mixed_overlap"] = OverlapCalculator.calculate_clustering_overlap(
mergeSeparatedClusters(
{"mixed": separated_decomposed_clusters["mixed"]}),
distance_matrix)
for cluster_type in separated_decomposed_clusters:
analysis["num_" + cluster_type] = len(
separated_decomposed_clusters[cluster_type])
analysis["total_num_clusters"] += analysis["num_" + cluster_type]
analysis["num_" + cluster_type + "_elements"] = numpy.sum([
len(
getAllElements(
separated_decomposed_clusters[cluster_type][dc_id]))
for dc_id in separated_decomposed_clusters[cluster_type]
])
analysis["total_num_elements"] += analysis["num_" + cluster_type +
"_elements"]
def test_get_cluster_min_max_distances(self):
# First test
distance_matrix = CondensedMatrix([1., 0.7,
0.3])
decomposed_cluster = {"traj_0":[0],"traj_1":[1],"traj_2":[2]}
expected_min_d, expected_max_d = [ 0.7, 0.3, 0.3], [ 1., 1., 0.7]
min_d, max_d = OverlapCalculator.get_cluster_min_max_distances(decomposed_cluster, distance_matrix)
numpy.testing.assert_array_almost_equal(min_d, expected_min_d, 8)
numpy.testing.assert_array_almost_equal(max_d, expected_max_d, 8)
#Second test
distance_matrix = CondensedMatrix([1., 0.7, 2.,
0.3, 1.,
0.7])
decomposed_cluster = {"traj_0":[0,3],"traj_1":[1],"traj_2":[2]}
expected_min_d, expected_max_d = [ 0.7, 0.7, 0.3, 0.3], [ 1., 1., 1., 0.7]
min_d, max_d = OverlapCalculator.get_cluster_min_max_distances(decomposed_cluster, distance_matrix)
numpy.testing.assert_array_almost_equal(min_d, expected_min_d, 8)
numpy.testing.assert_array_almost_equal(max_d, expected_max_d, 8)
def test_calculate_global_overlap(self):
distance_matrix = CondensedMatrix([1., 0.7, 2.,
0.3, 1.,
0.7])
decomposed_clusters = [{"traj_0":[0],"traj_1":[1]},{"traj_0":[2],"traj_1":[3]}]
self.assertEqual(0., OverlapCalculator.calculate_global_overlap(decomposed_clusters, distance_matrix, 1, 1))
decomposed_clusters = [{"traj_0":[0],"traj_1":[1]}, {"traj_0":[2]}, {"traj_1":[3]}]
self.assertEqual(0., OverlapCalculator.calculate_global_overlap(decomposed_clusters, distance_matrix, 1, 1))
def test_calculate_cluster_overlap(self):
distance_matrix = CondensedMatrix([1., 0.7,
0.3])
decomposed_cluster = {"traj_0":[0],"traj_1":[1],"traj_2":[2]}
self.assertAlmostEqual(0.481481488022, OverlapCalculator.calculate_cluster_overlap(1, decomposed_cluster, distance_matrix),12)
self.assertAlmostEqual(0.4761904843, OverlapCalculator.calculate_cluster_overlap(2, decomposed_cluster, distance_matrix), 12)
decomposed_cluster = {"traj_0":[0],"traj_1":[1]}
self.assertAlmostEqual(1., OverlapCalculator.calculate_cluster_overlap(1, decomposed_cluster, distance_matrix), 12)
self.assertAlmostEqual(1., OverlapCalculator.calculate_cluster_overlap(2, decomposed_cluster, distance_matrix), 12)
def analyze_clustering(cls, separated_decomposed_clusters, distance_matrix, analysis):
"""
Performs the overlap analysis of a clustering (calculates global measurements).
"""
analysis["total_num_clusters"] = 0
analysis["total_num_elements"] = 0
analysis["overlap"] = OverlapCalculator.calculate_clustering_overlap(mergeSeparatedClusters(separated_decomposed_clusters), distance_matrix)
analysis["mixed_overlap"] = OverlapCalculator.calculate_clustering_overlap(mergeSeparatedClusters({"mixed":separated_decomposed_clusters["mixed"]}), distance_matrix)
for cluster_type in separated_decomposed_clusters:
analysis["num_" + cluster_type] = len(separated_decomposed_clusters[cluster_type])
analysis["total_num_clusters"] += analysis["num_" + cluster_type]
analysis["num_" + cluster_type + "_elements"] = numpy.sum([len(getAllElements(separated_decomposed_clusters[cluster_type][dc_id])) for dc_id in separated_decomposed_clusters[cluster_type]])
analysis["total_num_elements"] += analysis["num_" + cluster_type + "_elements"]
def analyze_clustering(cls, separated_decomposed_clusters, distance_matrix, analysis):
analysis["total_num_clusters"] = 0
analysis["total_num_elements"] = 0
analysis["overlap"] = OverlapCalculator.calculate_global_overlap(mergeSeparatedClusters(separated_decomposed_clusters), distance_matrix, 2, 1)
for cluster_type in separated_decomposed_clusters:
analysis["num_" + cluster_type] = len(separated_decomposed_clusters[cluster_type])
analysis["total_num_clusters"] += analysis["num_" + cluster_type]
analysis["num_" + cluster_type + "_elements"] = numpy.sum([len(getAllElements(separated_decomposed_clusters[cluster_type][dc_id])) for dc_id in separated_decomposed_clusters[cluster_type]])
analysis["total_num_elements"] += analysis["num_" + cluster_type + "_elements"]
return cluster_type
def analyze_clusters(cls, separated_decomposed_clusters, distance_matrix, analysis):
for cluster_type in separated_decomposed_clusters:
for cluster_id in separated_decomposed_clusters[cluster_type]:
decomposed_cluster = separated_decomposed_clusters[cluster_type][cluster_id]
analysis[cluster_id] = {"components":decomposed_cluster.keys(),"global":{}}
analysis[cluster_id]["global"]["mean"], analysis[cluster_id]["global"]["std"], analysis[cluster_id]["global"]["max"] = calculate_distance_stats(getAllElements(decomposed_cluster), distance_matrix)
analysis[cluster_id]["global"]["num_elements"] = len(getAllElements(decomposed_cluster))
for traj_id in decomposed_cluster:
analysis[cluster_id]["global"][traj_id] = {}
analysis[cluster_id]["global"][traj_id]["mean"], analysis[cluster_id]["global"][traj_id]["std"], analysis[cluster_id]["global"][traj_id]["max"] = calculate_distance_stats(decomposed_cluster[traj_id], distance_matrix)
analysis[cluster_id]["global"][traj_id]["num_elements"] = len(decomposed_cluster[traj_id])
if cluster_type == "mixed":
analysis[cluster_id]["centers_mean_diff"] = calculate_mean_center_differences(decomposed_cluster, distance_matrix)
analysis[cluster_id]["global"]["overlap"] = OverlapCalculator.calculate_cluster_overlap(2, decomposed_cluster, distance_matrix)
def analyze_clustering(cls, separated_decomposed_clusters, distance_matrix,
analysis):
analysis["total_num_clusters"] = 0
analysis["total_num_elements"] = 0
analysis["overlap"] = OverlapCalculator.calculate_global_overlap(
mergeSeparatedClusters(separated_decomposed_clusters),
distance_matrix, 2, 1)
for cluster_type in separated_decomposed_clusters:
analysis["num_" + cluster_type] = len(
separated_decomposed_clusters[cluster_type])
analysis["total_num_clusters"] += analysis["num_" + cluster_type]
analysis["num_" + cluster_type + "_elements"] = numpy.sum([
len(
getAllElements(
separated_decomposed_clusters[cluster_type][dc_id]))
for dc_id in separated_decomposed_clusters[cluster_type]
])
analysis["total_num_elements"] += analysis["num_" + cluster_type +
"_elements"]
return cluster_type
def analyze_clusters(cls, separated_decomposed_clusters, distance_matrix,
analysis):
"""
Performs the overlap analysis of separated clusters.
"""
for cluster_type in separated_decomposed_clusters:
for cluster_id in separated_decomposed_clusters[cluster_type]:
decomposed_cluster = separated_decomposed_clusters[
cluster_type][cluster_id]
analysis[cluster_id] = {
"components": decomposed_cluster.keys(),
"global": {}
}
analysis[cluster_id]["global"]["mean"], analysis[cluster_id][
"global"]["std"], analysis[cluster_id]["global"][
"max"] = calculate_distance_stats(
getAllElements(decomposed_cluster),
distance_matrix)
analysis[cluster_id]["global"]["num_elements"] = len(
getAllElements(decomposed_cluster))
for traj_id in decomposed_cluster:
analysis[cluster_id]["global"][traj_id] = {}
analysis[cluster_id]["global"][traj_id]["mean"], analysis[
cluster_id]["global"][traj_id]["std"], analysis[
cluster_id]["global"][traj_id][
"max"] = calculate_distance_stats(
decomposed_cluster[traj_id],
distance_matrix)
analysis[cluster_id]["global"][traj_id][
"num_elements"] = len(decomposed_cluster[traj_id])
if cluster_type == "mixed":
analysis[cluster_id][
"centers_mean_diff"] = calculate_mean_center_differences(
decomposed_cluster, distance_matrix)
# The overlap ranges between 0 and 1, being 0 the best value. We invert it in order to
# to get a more understandable range (1 is the best value and 0 the worst).
analysis[cluster_id]["global"][
"overlap"] = 1 - OverlapCalculator.calculate_cluster_overlap(
decomposed_cluster, distance_matrix)
def analyze_clusters(cls, separated_decomposed_clusters, distance_matrix, analysis):
"""
Performs the overlap analysis of separated clusters.
"""
for cluster_type in separated_decomposed_clusters:
for cluster_id in separated_decomposed_clusters[cluster_type]:
decomposed_cluster = separated_decomposed_clusters[cluster_type][cluster_id]
analysis[cluster_id] = {"components":decomposed_cluster.keys(),"global":{}}
analysis[cluster_id]["global"]["mean"], analysis[cluster_id]["global"]["std"], analysis[cluster_id]["global"]["max"] = calculate_distance_stats(getAllElements(decomposed_cluster), distance_matrix)
analysis[cluster_id]["global"]["num_elements"] = len(getAllElements(decomposed_cluster))
for traj_id in decomposed_cluster:
analysis[cluster_id]["global"][traj_id] = {}
analysis[cluster_id]["global"][traj_id]["mean"], analysis[cluster_id]["global"][traj_id]["std"], analysis[cluster_id]["global"][traj_id]["max"] = calculate_distance_stats(decomposed_cluster[traj_id], distance_matrix)
analysis[cluster_id]["global"][traj_id]["num_elements"] = len(decomposed_cluster[traj_id])
if cluster_type == "mixed":
analysis[cluster_id]["centers_mean_diff"] = calculate_mean_center_differences(decomposed_cluster, distance_matrix)
# The overlap ranges between 0 and 1, being 0 the best value. We invert it in order to
# to get a more understandable range (1 is the best value and 0 the worst).
analysis[cluster_id]["global"]["overlap"] = 1 - OverlapCalculator.calculate_cluster_overlap( decomposed_cluster, distance_matrix)
def analyze_clusters(cls, separated_decomposed_clusters, distance_matrix,
analysis):
for cluster_type in separated_decomposed_clusters:
for cluster_id in separated_decomposed_clusters[cluster_type]:
decomposed_cluster = separated_decomposed_clusters[
cluster_type][cluster_id]
analysis[cluster_id] = {
"components": decomposed_cluster.keys(),
"global": {}
}
analysis[cluster_id]["global"]["mean"], analysis[cluster_id][
"global"]["std"], analysis[cluster_id]["global"][
"max"] = calculate_distance_stats(
getAllElements(decomposed_cluster),
distance_matrix)
analysis[cluster_id]["global"]["num_elements"] = len(
getAllElements(decomposed_cluster))
for traj_id in decomposed_cluster:
analysis[cluster_id]["global"][traj_id] = {}
analysis[cluster_id]["global"][traj_id]["mean"], analysis[
cluster_id]["global"][traj_id]["std"], analysis[
cluster_id]["global"][traj_id][
"max"] = calculate_distance_stats(
decomposed_cluster[traj_id],
distance_matrix)
analysis[cluster_id]["global"][traj_id][
"num_elements"] = len(decomposed_cluster[traj_id])
if cluster_type == "mixed":
analysis[cluster_id][
"centers_mean_diff"] = calculate_mean_center_differences(
decomposed_cluster, distance_matrix)
analysis[cluster_id]["global"][
"overlap"] = OverlapCalculator.calculate_cluster_overlap(
2, decomposed_cluster, distance_matrix)
