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_read(dataset, expected):
actual_data = read.read_csv(dataset)
expected_data = expected
assert len(actual_data) == len(expected_data)
for i in range(len(actual_data)):
assert actual_data[i] == expected_data[i]
def test_kmeans_when_k_is_2(datasetPath, expected1, expected2):
dataset = read.read_csv(datasetPath)
expected_clustering1 = read.read_csv(expected1)
expected_clustering2 = read.read_csv(expected2)
clustering = kmeans.k_means_pp(dataset=dataset, k=2)
cost = kmeans.cost_function(clustering)
for _ in range(10):
new_clustering = kmeans.k_means_pp(dataset=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, dataset) is True
clustered = []
for assignment in clustering:
clustered.append(clustering[assignment])
assert clustered.sort() == [expected_clustering1,
expected_clustering2].sort()
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 test_read(dataset):
actual_data = read.read_csv(dataset)
expected_data = [[138, 143], [93, 104], [61, 69], [179, 260], [48, 75],
[37, 63], [29, 50], [23, 48], [30, 111], [2, 50],
[38, 52], [46, 53], [71, 79], [25, 57], [298, 317],
[74, 93], [50, 58], [76, 80], [381, 464], [387, 459],
[78, 106], [60, 57], [507, 634], [50, 64], [77, 89],
[64, 77], [40, 60], [136, 139], [243, 291], [256, 288],
[94, 85], [36, 46], [45, 53], [67, 67], [120, 115],
[172, 183], [66, 86], [46, 65], [121, 113], [44, 58],
[64, 63], [56, 142], [40, 64], [116, 130], [87, 105],
[43, 61], [43, 50], [161, 232], [36, 54]]
assert len(actual_data) == len(expected_data)
for i in range(len(actual_data)):
assert actual_data[i] == expected_data[i]
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()
while assignments != old_assignments:
new_centers = update_centers(dataset, assignments)
old_assignments = assignments
assignments = assign_points(dataset, new_centers)
clustering = defaultdict(list)
for assignment, point in zip(assignments, dataset):
clustering[assignment].append(point)
return clustering
def k_means(dataset, k):
if k not in range(1, len(dataset)+1):
raise ValueError("lengths must be in [1, len(dataset)]")
k_points = generate_k(dataset, k)
return _do_lloyds_algo(dataset, k_points)
def k_means_pp(dataset, k):
if k not in range(1, len(dataset)+1):
raise ValueError("lengths must be in [1, len(dataset)]")
k_points = generate_k_pp(dataset, k)
return _do_lloyds_algo(dataset, k_points)
if __name__ =='__main__':
from cs506 import read
data = read.read_csv('D:/OneDrive/College Notebook/Boston University/Fall Senior Year/CS 506/CS506-Fall2020/02-library/tests/test_files/dataset_1.csv')
res = (k_means(data, 4))
print(res[0])