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 test_kmeans_when_k_is_1(dataset):
expected_clustering = kmeans.get_list_from_dataset_file(dataset)
clustering = kmeans.k_means(dataset_file=dataset, k=1)
assert len(clustering.keys()) == 1
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_clustering]
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)
def generateSeparator(length):
result = ""
for i in range(length):
result += "-"
result += "\n"
return result
startTime = current_milli_time()
result = head
for i in range(1, 6, 1):
result += generateSeparator(120)
dataset = "inputs/graph.txt"
result += "Dataset: " + dataset + "\t\t count centroids: " + str(i) + "\n"
centroids = k_means(dataset, i)
centroids.sort()
for centroid in centroids:
for coordinate in centroid:
result += str(coordinate) + "\t"
result += "\n"
result += "\n"
for i in range(1, 6, 1):
result += generateSeparator(120)
dataset = "inputs/iris.data.txt"
result += "Dataset: " + dataset + "\t\t count centroids: " + str(i) + "\n"
centroids = k_means(dataset, i)
centroids.sort()
for centroid in centroids:
for coordinate in centroid:
NC = list(range(3, 4)) #numOfModels+1)) # list of numbers of clusters
accuracies = np.zeros((numOfEPS, len(NC)))
clusteringResult = {}
for numOfClusters in NC:
clusteringResult[numOfClusters] = []
with open("clustering_result.txt", "w") as fp:
for numOfClusters in NC:
# clustering into c groups
print("Clustering: {} clusters".format(numOfClusters))
# kmeans = KMeans(n_clusters=numOfClusters, random_state=0).fit(predVec)
# for c in range(numOfClusters):
# clusteringResult[numOfClusters].append(np.where(kmeans.labels_ == c)[0])
# print(np.where(kmeans.labels_ == c)[0])
assignments = k_means(predVec, numOfClusters, "L2", "ZerosFarAway")
fp.write("## number of clusters: " + str(numOfClusters) + "\n")
for c in range(numOfClusters):
cluster = np.where(assignments == c)[0]
clusteringResult[numOfClusters].append(cluster)
print(cluster)
fp.write("\t" + str(cluster) + "\n")
fp.write("\n")
def vote1(participants):
'''
Input:
participants: a list of opinions. Each element in the list is a numpy array, N X 2.
N is the number of events. The second dimension contains (opinion/label, confidence)
Output:
current_milli_time = lambda: int(round(time.time() * 1000))
def generateSeparator(length):
result = ""
for i in range(length):
result += "-"
result += "\n"
return result
startTime = current_milli_time()
result = head
for i in range(1, 6, 1):
result += generateSeparator(120)
dataset = "inputs/graph.txt"
result += "Dataset: " + dataset + "\t\t count centroids: " + str(i) + "\n"
centroids = k_means(dataset, i)
centroids.sort()
for centroid in centroids:
for coordinate in centroid:
result += str(coordinate) + "\t"
result+="\n"
result += "\n"
for i in range(1, 6, 1):
result += generateSeparator(120)
dataset = "inputs/iris.data.txt"
result += "Dataset: " + dataset + "\t\t count centroids: " + str(i) + "\n"
centroids = k_means(dataset, i)
centroids.sort()
for centroid in centroids:
for coordinate in centroid: