def test_get_maximum_for_dataset2(self):
keywords_dont_matter_here = ['']
kwc1 = KeywordCoordinate(0, 0, keywords_dont_matter_here)
kwc2 = KeywordCoordinate(1, 1, keywords_dont_matter_here)
kwc3 = KeywordCoordinate(2, 2, keywords_dont_matter_here)
kwc4 = KeywordCoordinate(3, 3, keywords_dont_matter_here)
kwc5 = KeywordCoordinate(4, 4, keywords_dont_matter_here)
kwc6 = KeywordCoordinate(5, 5, keywords_dont_matter_here)
dataset: dataset_type = [kwc1, kwc2, kwc3, kwc4, kwc5, kwc6]
cf = CostFunction(manhattan_distance, separated_cosine_similarity, 0.3,
0.3, 0.4)
result = cf.get_maximum_for_dataset(dataset)
self.assertAlmostEqual(result, 10.0, delta=0.01)
def test_get_maximum_for_dataset4(self):
keywords_dont_matter_here = ['']
kwc1 = KeywordCoordinate(6, 6, keywords_dont_matter_here)
kwc2 = KeywordCoordinate(8, 8, keywords_dont_matter_here)
kwc3 = KeywordCoordinate(9, 9, keywords_dont_matter_here)
kwc4 = KeywordCoordinate(13, 13, keywords_dont_matter_here)
kwc5 = KeywordCoordinate(24, 24, keywords_dont_matter_here)
kwc6 = KeywordCoordinate(35, 35, keywords_dont_matter_here)
dataset: dataset_type = [kwc1, kwc2, kwc3, kwc4, kwc5, kwc6]
cf = CostFunction(manhattan_distance, separated_cosine_similarity, 0.3,
0.3, 0.4)
result = cf.get_maximum_for_dataset(dataset)
self.assertAlmostEqual(result, 58.0, delta=0.01)
def get_max_inter_dataset_distances(costfunction: CostFunction, subsets):
"""
This function gets executed inside every maximum inter-dataset distance process.
:param costfunction: The CostFunction
:param subsets: The subsets for the process
:return: A list with tuples of the costs and their corresponding subset
"""
results = []
# count = 1
for subset in subsets:
# print('Subset: ', count)
# count = count + 1
# print('*** ', subset)
current_cost = costfunction.get_maximum_for_dataset(subset)
results.append((current_cost, subset))
return results