def RunKMeansShogun(q):
totalTimer = Timer()
# Load input dataset.
# If the dataset contains two files then the second file is the centroids
# file.
Log.Info("Loading dataset", self.verbose)
if len(self.dataset) == 2:
data = np.genfromtxt(self.dataset[0], delimiter=',')
centroids = np.genfromtxt(self.dataset[1], delimiter=',')
else:
data = np.genfromtxt(self.dataset[0], delimiter=',')
# Gather parameters.
clusters = re.search("-c (\d+)", options)
maxIterations = re.search("-m (\d+)", options)
seed = re.search("-s (\d+)", options)
# Now do validation of options.
if not clusters and len(self.dataset) != 2:
Log.Fatal("Required option: Number of clusters or cluster locations.")
q.put(-1)
return -1
elif (not clusters or int(clusters.group(1)) < 1) and len(self.dataset) != 2:
Log.Fatal("Invalid number of clusters requested! Must be greater than"
+ " or equal to 1.")
q.put(-1)
return -1
m = 1000 if not maxIterations else int(maxIterations.group(1))
if seed:
Math_init_random(seed.group(1))
try:
dataFeat = RealFeatures(data.T)
distance = EuclideanDistance(dataFeat, dataFeat)
# Create the K-Means object and perform K-Means clustering.
with totalTimer:
if len(self.dataset) == 2:
model = KMeans(int(clusters.group(1)), distance, RealFeatures(centroids))
else:
model = KMeans(int(clusters.group(1)), distance)
model.set_mbKMeans_iter(m)
model.train()
labels = model.apply().get_labels()
centers = model.get_cluster_centers()
except Exception as e:
print(e)
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
