def test_kmeans_when_k_is_2(dataset, expected1, expected2):
expected_clustering1 = kmeans.get_list_from_dataset_file(expected1)
expected_clustering2 = kmeans.get_list_from_dataset_file(expected2)
clustering = kmeans.k_means(dataset_file=dataset, k=2)
cost = kmeans.cost_function(clustering)
for _ in range(10):
new_clustering = kmeans.k_means(dataset_file=dataset, k=2)
new_cost = kmeans.cost_function(clustering)
if new_cost < cost:
clustering = new_clustering
cost = new_cost
assert len(clustering.keys()) == 2
assert clustered_all_points(clustering, kmeans.get_list_from_dataset_file(dataset)) is True
clustered = []
for assignment in clustering:
clustered.append(clustering[assignment])
assert clustered == [expected_clustering1, expected_clustering2]
def kmeans(self, args):
"""Run the kmeans command
"""
import csv
clustering = kmeans.k_means(dataset_file=args.dataset, k=int(args.k))
cost = kmeans.cost_function(clustering)
for _ in range(100):
new_clustering = kmeans.k_means(dataset_file=args.dataset, k=int(args.k))
new_cost = kmeans.cost_function(clustering)
if new_cost < cost:
clustering = new_clustering
cost = new_cost
for assignment in clustering.keys():
file_name = str(args.dataset).split(".")[0]+"_k_is_"+args.k+"_"+str(assignment)+".csv"
with open(file_name, "w") as f:
writer = csv.writer(f)
print("assignement ", assignment, " is: ", clustering[assignment])
writer.writerows(clustering[assignment])
f.close()
def test_kmeans_when_k_is_3(dataset, expected1, expected2, expected3):
expected_clustering1 = kmeans.get_list_from_dataset_file(expected1)
expected_clustering2 = kmeans.get_list_from_dataset_file(expected2)
expected_clustering3 = kmeans.get_list_from_dataset_file(expected3)
clustering = kmeans.k_means(dataset_file=dataset, k=3)
cost = kmeans.cost_function(clustering)
for _ in range(3000):
new_clustering = kmeans.k_means(dataset_file=dataset, k=3)
new_cost = kmeans.cost_function(clustering)
if new_cost < cost:
clustering = new_clustering
cost = new_cost
assert len(clustering.keys()) == 3
assert clustered_all_points(
clustering, kmeans.get_list_from_dataset_file(dataset)) is True
clustered = []
for assignment in clustering:
clustered.append(clustering[assignment])
assert clustered == [
expected_clustering1, expected_clustering2, expected_clustering3
]
#return clustered == [expected_clustering1, expected_clustering2, expected_clustering3]
# a = "/Users/AaronLee/clustering/tests/test_files/dataset_1.csv"
# b = "/Users/AaronLee/clustering/tests/test_files/dataset_1_k_is_3_0.csv"
# c = "/Users/AaronLee/clustering/tests/test_files/dataset_1_k_is_3_1.csv"
# d = "/Users/AaronLee/clustering/tests/test_files/dataset_1_k_is_3_2.csv"
# x = test_kmeans_when_k_is_3(a,b,c,d)
#
# a1 = "/Users/AaronLee/clustering/tests/test_files/dataset_1.csv"
# b1 = "/Users/AaronLee/clustering/tests/test_files/dataset_1_k_is_2_0.csv"
# c1 = "/Users/AaronLee/clustering/tests/test_files/dataset_1_k_is_2_1.csv"
# x1 = test_kmeans_when_k_is_2(a1,b1,c1)
#
# a2 = "/Users/AaronLee/clustering/tests/test_files/dataset_1.csv"
# x2 = test_kmeans_when_k_is_1(a2)