def perform_orange_clustering(mss_id):
import orange
from task_similarities import TreeNode
import helper
#(dist_full, id_to_name) = compute_task_distances(mss_id)
p = '/fml/ag-raetsch/home/cwidmer'
(dist_full, id_to_name) = helper.load(p + "/dist")
l = []
for i in range(len(dist_full)):
l.append([])
for j in range(i + 1, len(dist_full)):
l[i].append(dist_full[i, j])
l.reverse()
m = orange.SymMatrix(l)
root = orange.HierarchicalClustering(
m, linkage=orange.HierarchicalClustering.Average)
root_node = TreeNode("root")
clusters = [root]
nodes = [root_node]
while len(clusters) > 0:
cluster = clusters.pop(0)
node = nodes.pop(0)
# append nodes if non-empty
if cluster.left:
clusters.append(cluster.left)
name = str(tuple(cluster.left))
if len(tuple(cluster.left)) == 1:
name = id_to_name[tuple(cluster.left)[0]]
print name
# create nodes
left_node = TreeNode(name)
node.add_child(left_node, 1.0)
nodes.append(left_node)
# append nodes if non-empty
if cluster.right:
clusters.append(cluster.right)
name = str(tuple(cluster.right))
if len(tuple(cluster.right)) == 1:
name = id_to_name[tuple(cluster.right)[0]]
print name
# create nodes
right_node = TreeNode(name)
node.add_child(right_node, 1.0)
nodes.append(right_node)
return root_node
def hierarchical_clustering(linkage, distance_matrix):
import orange
linkages = [("Single linkage", orange.HierarchicalClustering.Single),
("Average linkage", orange.HierarchicalClustering.Average),
("Ward's linkage", orange.HierarchicalClustering.Ward),
("Complete linkage",
orange.HierarchicalClustering.Complete)]
return orange.HierarchicalClustering(distance_matrix,
linkage=linkages[linkage][1])
def sortClusteringOrdered(self):
self.rootCluster = orange.HierarchicalClustering(
self.matrix, linkage=orange.HierarchicalClustering.Average)
import orngClustering
self.progressBarInit()
orngClustering.orderLeaves(self.rootCluster, self.matrix,
self.progressBarSet)
self.progressBarFinished()
self.order = list(self.rootCluster.mapping)
def run_clustering(self):
if self.matrix:
self.progressBarInit()
self.root_cluster = orange.HierarchicalClustering(
self.matrix,
linkage=self.linkage[self.Linkage][1],
progressCallback=lambda value, a: self.progressBarSet(value *
100))
self.progressBarFinished()
self.display_tree()
def hierarchicalClustering_attributes(data, distance=None, linkage=orange.HierarchicalClustering.Average, order=False, progressCallback=None):
"""Return hierarhical clustering of attributes in the data set."""
matrix = orange.SymMatrix(len(data.domain.attributes))
for a1 in range(len(data.domain.attributes)):
for a2 in range(a1):
matrix[a1, a2] = orange.PearsonCorrelation(a1, a2, data, 0).p
root = orange.HierarchicalClustering(matrix, linkage=linkage, progressCallback=progressCallback)
if order:
orderLeaves(root, matrix, progressCallback=progressCallback)
return root
def hierarchical_clustering(linkage, distance_matrix):
import Orange, orange, sys
linkages = [("Single linkage", orange.HierarchicalClustering.Single),
("Average linkage", orange.HierarchicalClustering.Average),
("Ward's linkage", orange.HierarchicalClustering.Ward),
("Complete linkage", orange.HierarchicalClustering.Complete)]
try:
return orange.HierarchicalClustering(distance_matrix, linkage=linkages[linkage][1])
except TypeError as e:
print "hierarchical_clustering:", sys.exc_info()[0]
print e
def test_iris(self):
data = orange.ExampleTable("iris")
dss = orange.ExamplesDistanceConstructor_Euclidean(data)
t = orange.HierarchicalClustering.Linkage
for linkage in [t.Single, t.Average, t.Complete, t.Ward]:
dist = orange.SymMatrix(len(data))
for i, e in enumerate(data):
for j in range(i):
dist[i, j] = dss(e, data[j])
root = orange.HierarchicalClustering(dist, linkage=linkage)
self.assertEqual(len(root), len(data))
self.rectestlen(root)
root.mapping.objects = data
self.assertEqual(root[0], data[0])
def hierarchicalClustering(data,
distanceConstructor=orange.ExamplesDistanceConstructor_Euclidean,
linkage=orange.HierarchicalClustering.Average,
order=False,
progressCallback=None):
"""Return a hierarhical clustering of the data set."""
distance = distanceConstructor(data)
matrix = orange.SymMatrix(len(data))
for i in range(len(data)):
for j in range(i+1):
matrix[i, j] = distance(data[i], data[j])
root = orange.HierarchicalClustering(matrix, linkage=linkage, progressCallback=(lambda value, obj=None: progressCallback(value*100.0/(2 if order else 1))) if progressCallback else None)
if order:
orderLeaves(root, matrix, progressCallback=(lambda value: progressCallback(50.0 + value/2)) if progressCallback else None)
return root
print int(round(100 * f)),
repTime("Loading data")
data = orange.ExampleTable("iris")
repTime("Computing distances")
matrix = orange.SymMatrix(len(data))
matrix.setattr("objects", data)
distance = orange.ExamplesDistanceConstructor_Euclidean(data)
for i1, ex1 in enumerate(data):
for i2 in range(i1 + 1, len(data)):
matrix[i1, i2] = distance(ex1, data[i2])
repTime("Hierarchical clustering (single linkage)")
clustering = orange.HierarchicalClustering()
clustering.linkage = clustering.Average
clustering.overwriteMatrix = 1
root = clustering(matrix)
repTime("Done.")
def prune(cluster, togo):
if cluster.branches:
if togo < 0:
cluster.branches = None
else:
for branch in cluster.branches:
prune(branch, togo - cluster.height)
import orange
from orngClustering import *
# data = orange.ExampleTable("doc//datasets//brown-selected.tab")
data = orange.ExampleTable("iris")
# data = orange.ExampleTable("doc//datasets//zoo.tab")
# data = orange.ExampleTable("doc//datasets//titanic.tab")
# m = [[], [ 3], [ 2, 4], [17, 5, 4], [ 2, 8, 3, 8], [ 7, 5, 10, 11, 2], [ 8, 4, 1, 5, 11, 13], [ 4, 7, 12, 8, 10, 1, 5], [13, 9, 14, 15, 7, 8, 4, 6], [12, 10, 11, 15, 2, 5, 7, 3, 1]]
# matrix = orange.SymMatrix(m)
dist = orange.ExamplesDistanceConstructor_Euclidean(data)
matrix = orange.SymMatrix(len(data))
# matrix.setattr('items', data)
for i in range(len(data)):
for j in range(i + 1):
matrix[i, j] = dist(data[i], data[j])
root = orange.HierarchicalClustering(
matrix, linkage=orange.HierarchicalClustering.Average)
# root.mapping.objects = [str(ex.getclass()) for ex in data]
d = DendrogramPlot(root,
data=data,
labels=[str(ex.getclass()) for ex in data],
width=500,
height=2000)
d.set_matrix_color_schema([(0, 255, 0), (255, 0, 0)], 0.0, 1.0)
# d.setClusterColors({root.left:(0,255,0), root.right:(0,0,255)})
d.plot("graph.png")
print "Sum:", sum([
matrix[root.mapping[i], root.mapping[i + 1]]
for i in range(len(root.mapping) - 1)
])
orderLeaves(root, matrix)
print "Sum:", sum([
def sortClustering(self):
self.rootCluster = orange.HierarchicalClustering(
self.matrix, linkage=orange.HierarchicalClustering.Average)
self.order = list(self.rootCluster.mapping)