def compare(first_data_set: DataSet, second_data_set: DataSet) -> tuple:
"""
Compare given data sets by computing the
number of metadata entries present in first
but not in second data set and vice versa.
Return both values as a tuple of integers.
Intuitively, both numbers are 0 in case
of strictly identical metadata structures.
:param first_data_set: DataSet - Data points
and corresponding metadata structures.
:param second_data_set: DataSet - Data points
and corresponding metadata structures.
:return: (int, int) - Number of metadata
elements present in first but not
in second data set (and vice versa).
:raise ValueError: In case one
DataSet instance is missing.
"""
# Check if first data structure is
# actually not a DataSet instance.
if not isinstance(first_data_set, DataSet):
raise ValueError
# Check if second data structure is
# actually not a DataSet instance.
if not isinstance(second_data_set, DataSet):
raise ValueError
# Collect metadata entries of first
# data set in a single set structure.
first_metadata = set()
for i in range(len(first_data_set)):
metadata = first_data_set.get_metadata_at_index(i)
first_metadata.update(metadata)
# Collect metadata entries of second
# data set in a single set structure.
second_metadata = set()
for i in range(len(second_data_set)):
metadata = second_data_set.get_metadata_at_index(i)
second_metadata.update(metadata)
num_unique_elements_in_first_metadata = len(
first_metadata.difference(second_metadata))
num_unique_elements_in_second_metadata = len(
second_metadata.difference(first_metadata))
return num_unique_elements_in_first_metadata, num_unique_elements_in_second_metadata
def _get_clustered_data_set(data_set: DataSet, clusters: list) -> DataSet:
"""
Combine vectors within each cluster to a single
data point and corresponding metadata structure.
Use mean vector as the cluster's representative
and all metadata structures excluding duplicates.
:param data_set: DataSet - Data points
and corresponding metadata structures.
:param clusters: list(list) - Data point
indices contained in each cluster.
:return: DataSet - Clustered data points
and corresponding metadata structures.
"""
# Create lists to store compressed vectors
# and corresponding metadata structures.
new_data_points = list()
new_metadata = list()
for index_list in clusters:
# Compress data points in current cluster
# by computing corresponding mean vector.
current_data_points = [
data_set.get_vector_at_index(i) for i in index_list
]
mean_vector = calculation.get_mean(current_data_points)
new_data_points.append(mean_vector)
# Compress metadata structures in current
# cluster by using corresponding merge function.
current_metadata_structure = set()
for i in index_list:
current_metadata_structure = DataSet.merge_metadata(
current_metadata_structure, data_set.get_metadata_at_index(i))
new_metadata.append(current_metadata_structure)
# Return compressed data.
return DataSet(new_data_points, new_metadata)