def test_row_distance(self):
hc = HierarchicalClustering(self.data)
available_answers = [175.803, 453.0] # euclidean, Manhattan
dist = hc.row_distance("Polona", "Rajko")
equal = np.isclose(dist, available_answers, atol=1e-2)
self.assertTrue(equal.any())
def test_run(self):
hc = HierarchicalClustering(self.data)
hc.row_distance = lambda a, b: distance.euclidean(
self.data[a], self.data[b])
hc.run()
self.assertTrue(
compare_trees(hc.clusters, CLUSTER_AVG_MAX)
or compare_trees(hc.clusters, CLUSTER_MIN))
def test_cluster_distance(self):
hc = HierarchicalClustering(self.data)
ca = [["Albert"], [["Branka"], ["Cene"]]]
cb = [["Nika"], ["Polona"]]
available_dists = [124.99, 165.86, 75.94]
hc.row_distance = lambda a, b: distance.euclidean(
self.data[a], self.data[b])
equal = np.isclose(hc.cluster_distance(ca, cb),
available_dists,
atol=1e-2)
self.assertTrue(equal.any())
import matplotlib.pyplot as plt
# Analysis of the results of hierarchical clustering
########################
# Author: Jernej Vivod #
########################
DATA_FILE = "eurovision-final.csv" # Read data.
labels = get_labels(
DATA_FILE
) # Get labels (2xn matrix) that maps each country in first column to its region
# in the second column
hc = HierarchicalClustering(
read_file(DATA_FILE)
) # Create a HierarchicalClustering instance initialized with parsed data.
# Get groups and create a dictionary where index of groups maps to its members
hc.get_groups(11)
hc.extract_group_members()
## (1) ## For each group in hc.groups compute how many points it gave to every country. ##
points_to_countries = dict()
# Go over group indices.
for group_index in hc.groups.keys():
sum_points = np.zeros(
47, dtype=int
) # Create empty vector for computing the cummulative sums of points for each country.