def divide_by_cmd(filename1, filename2, position):
X, label = weeklydataset(filename1, [])
X2, label2 = weeklydataset(filename2, [])
x = X + X2
f = operator.itemgetter(position)
commands = map(f, x)
print commands[0:20]
unique_cmd_set = set(commands)
print unique_cmd_set
unique_cmd = []
while len(unique_cmd_set) > 0:
unique_cmd.append(unique_cmd_set.pop())
print unique_cmd
files = []
for i in range(len(unique_cmd)):
files.append(csv.writer(open(unique_cmd[i]+"_cmd.csv", "wb"), delimiter=";"))
for elem in x:
index = unique_cmd.index(elem[position])
files[index].writerow(elem)
def test():
# data = [["claudio","Di Cosmo"], ["claudino", "Cosimino"], ["fabio", "Melillo"], ["fabietto", "Mellillo"], ["angelo", "Furno"], ["angioletto", "Furnetto"], ["antonio", "Cuomo"], ["antoniuccio", "Cuomuccio"], ["marcangelo", "Frunillo"]]
X, label = weeklydataset("/home/claudio/Workloads/WmProxyWL/nlog.csv", [])
start_time = time()
centroids, clusters = kmeans(X, 4)
end_time = time()
print end_time - start_time
print centroids
print len(clusters[0])
print len(clusters[1])
print len(clusters[2])
print len(clusters[3])
results = csv.writer(open("/home/claudio/Workloads/WmProxyWL/cluster0.csv", "wb"), delimiter=";")
results.writerow(["Cluster 0", len(clusters[0])])
results.writerows(clusters[0])
results = csv.writer(open("/home/claudio/Workloads/WmProxyWL/cluster1.csv", "wb"), delimiter=";")
results.writerow(["Cluster 1", len(clusters[1])])
results.writerows(clusters[1])
results = csv.writer(open("/home/claudio/Workloads/WmProxyWL/cluster2.csv", "wb"), delimiter=";")
results.writerow(["Cluster 2", len(clusters[2])])
results.writerows(clusters[2])
results = csv.writer(open("/home/claudio/Workloads/WmProxyWL/cluster3.csv", "wb"), delimiter=";")
results.writerow(["Cluster 3", len(clusters[3])])
results.writerows(clusters[3])
def clusterize():
X, label = weeklydataset('/home/work/Workloads/WmProxyWL/train.csv', [])
X2, label2 = weeklydataset('/home/claudio/Workloads/WmProxyWL/test.csv', [])
x = X + X2
start_time = time()
centroids, clusters = kmeans(x, 4)
end_time = time()
print end_time - start_time
print centroids
print len(clusters[0])
print len(clusters[1])
print len(clusters[2])
print len(clusters[3])
results = csv.writer(open("/home/claudio/Workloads/WmProxyWL/cluster0.csv", "wb"), delimiter=";")
results.writerow(["Cluster 0", len(clusters[0])])
results.writerows(clusters[0])
results = csv.writer(open("/home/claudio/Workloads/WmProxyWL/cluster1.csv", "wb"), delimiter=";")
results.writerow(["Cluster 1", len(clusters[1])])
results.writerows(clusters[1])
results = csv.writer(open("/home/claudio/Workloads/WmProxyWL/cluster2.csv", "wb"), delimiter=";")
results.writerow(["Cluster 2", len(clusters[2])])
results.writerows(clusters[2])
results = csv.writer(open("/home/claudio/Workloads/WmProxyWL/cluster3.csv", "wb"), delimiter=";")
results.writerow(["Cluster 3", len(clusters[3])])
results.writerows(clusters[3])
'''
Created on Jul 18, 2011
@author: work
'''
#from Pycluster import clustercentroids, kcluster
from kmeans import kmeans
from numpy import matrix, float64
from thesis.scripts.dataset.dataset import weeklydataset
import matplotlib.pyplot as plt
#[X, label] = weeklydataset_shogun('/home/work/Projects/EclipseProjects/thesis/Scripts/cpu_mod.csv', [0])
X, label = weeklydataset('/media/DATA/Thesis/Workloads/GenericWorkloadModeler/workloads/WMproxy/wmpcommon_cmd.csv', [])
#X = open('/home/work/Projects/EclipseProjects/thesis/Scripts/cpu.csv',)
K = range(2,3)
labels = list()
error = list()
nfound = list()
cdata = list()
cmask = list()
#param = X[5:8]
#parameters = matrix(X)
for k in K:
# tmplabels, tmperror, tmpnfound = kcluster(parameters, nclusters=k, mask=None, weight=None, transpose=1, npass=1, method='a', dist='e', initialid=None)
# tmpcdata, tmpcmask = clustercentroids(parameters, None, tmplabels, 'a', 1)
tmperror, tmp_cluster = kmeans(X, k)
# labels.append(tmplabels)
error.append(tmperror)