return sum(s)/len(s)
#-----------------------------------------------------------
def get_s1():
file_name = 'datasets/s1.txt'
with open(file_name) as f:
#header = f.readline()
points = []
for line in f:
items = line.strip().split(' ')
r = [
float(items[0]),
float(items[1]),
]
points.append( Point(r) )
#random.shuffle(points)
return points
#-----------------------------------------------------------
points = get_s1()
#print(points)
Point.set_features(0,1)
for k in range(3, 4):
model = KMeans(points, 15, 0.01)
model.cluster()
# model.show()
print("Done")
print('k = ', k, 'silhouette = ', silhouette(model.points, model.clusters))
# Md Lutfar Rahman # [email protected] # DataMining Assingment 4 from kmeans import Point, Cluster, KMeans import random from UserMatrix import UserMatrix userMat = UserMatrix() points = userMat.userpoints fet = list(range(len(userMat.movieIds))) k=3 #print(fet) Point.set_features(*fet) model = KMeans(points, k, 0.001) model.cluster() #print("clustring>>ended") print('') model.getIntraCentriodDensity() print('') model.getInterCentroidDensity()
#-----------------------------------------------------------
def get_iris_data():
file_name = 'datasets/iris.csv'
with open(file_name) as f:
header = f.readline()
points = []
for line in f:
items = line.strip().split(',')
r = [
float(items[0]),
float(items[1]),
float(items[2]),
float(items[3]), items[4]
]
points.append(Point(r))
random.shuffle(points)
return points
#-----------------------------------------------------------
points = get_iris_data()
Point.set_features(0, 1, 2, 3)
for k in range(2, 10):
model = KMeans(points, k, 0.01)
model.cluster()
# model.show()
print('k = ', k, 'silhouette = ', silhouette(model.points, model.clusters))