def test_kmeans_when_k_is_3(datasetPath, expected1, expected2, expected3):
random.seed(1)
dataset = read.read_csv(datasetPath)
expected_clustering1 = read.read_csv(expected1)
expected_clustering2 = read.read_csv(expected2)
expected_clustering3 = read.read_csv(expected3)
clustering = kmeans.k_means(dataset=dataset, k=3)
cost = kmeans.cost_function(clustering)
for _ in range(10):
new_clustering = kmeans.k_means(dataset=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, dataset) is True
clustered = []
for assignment in clustering:
clustered.append(clustering[assignment])
assert clustered == [
expected_clustering1, expected_clustering2, expected_clustering3
]
def test_kmeans_when_k_is_1(datasetPath):
dataset = read.read_csv(datasetPath)
expected_clustering = dataset
clustering = kmeans.k_means(dataset=dataset, k=1)
assert len(clustering.keys()) == 1
assert clustered_all_points(clustering, dataset) is True
clustered = []
for assignment in clustering:
clustered.append(clustering[assignment])
assert clustered == [expected_clustering]
def kmeans(self, args):
"""Run the kmeans command
"""
import csv
dataset = read.read_csv(args.dataset_file)
clustering = kmeans.k_means(dataset=dataset, k=int(args.k))
cost = kmeans.cost_function(clustering)
for _ in range(100):
new_clustering = kmeans.k_means(dataset=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()