def prob0():
arff = Arff('datasets/labor.arff', label_count=1)
# Trim the id column
arff = arff.create_subset_arff(col_idx=slice(1, None))
arff = arff.get_features()
km = KMeans(5)
km.train(arff, verbose=True, centers=arff.data[:5])
def prob2wclass():
iris = Arff('datasets/iris.arff', label_count=0)
# features.normalize()
# Train k means for 2-7
ks = [2, 3, 4, 5, 6, 7]
for k in ks:
km = KMeans(k)
km.train(iris)
hac2 = HAC(simple=False)
hac2.train(iris, printk=ks)
def prob4():
arff = Arff('datasets/abalone.arff', label_count=0)
arff.normalize()
domain = np.arange(2, 8)
ssekmm = []
for k in domain:
km = KMeans(k)
ssek = km.train(arff)
ssekmm.append(ssek)
print(km.calc_silhouette_score())
def prob2():
iris = Arff('datasets/iris.arff')
features = iris.get_features()
# features.normalize()
# Train k means for 2-7
ks = [2, 3, 4, 5, 6, 7]
for k in ks:
km = KMeans(k)
km.train(features)
hac2 = HAC(simple=False)
hac2.train(features, printk=ks)
def prob3():
arff = Arff('datasets/abalone.arff', label_count=0)
domain = np.arange(2, 8)
ssekmm = []
for k in domain:
km = KMeans(k)
ssek = km.train(arff)
ssekmm.append(ssek)
hac = HAC()
hac2 = HAC(simple=False)
ssehac = hac.train(arff, printk=domain)
ssehac2 = hac2.train(arff, printk=domain)
plt.plot(domain, ssekmm, label="K-Means SSE")
plt.plot(domain, ssehac[::-1], label="HAC (Single-Link) SSE")
plt.plot(domain, ssehac2[::-1], label="HAC (Complete-Link) SSE")
plt.title("Abalone SSE vs # of Clusters")
plt.xlabel("# of Clusters")
plt.ylabel('SSE')
plt.legend()
plt.show()
def prob2_v3():
iris = Arff('datasets/iris.arff', label_count=0)
for _ in range(5):
km = KMeans(4)
km.train(iris)
def prob1():
arff = Arff('datasets/sponge.arff')
km = KMeans(4)
print(arff.data[:4])
km.train(arff, verbose=True, centers=arff.data[:4])