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
diss,labels = im.exportChi2Matrix()
off = 0
elif classInteractions == 1:
(diss,labels) = im.depExportDissimilarityMatrix(jaccard=1) # 2-interactions
else:
(diss,labels) = im.exportDissimilarityMatrix(jaccard=1) # 3-interactions
for i in range(len(atts)-off):
for j in range(i+1):
matrix[i+off, j] = diss[i][j]
else:
if classInteractions == 3:
for a1 in range(len(atts)):
for a2 in range(a1):
matrix[a1, a2] = (1.0 - orange.PearsonCorrelation(a1, a2, inputdata, 0).r) / 2.0
else:
if len(inputdata) < 3:
return None
import numpy, statc
m = inputdata.toNumpyMA("A")[0]
averages = numpy.ma.average(m, axis=0)
filleds = [list(numpy.ma.filled(m[:,i], averages[i])) for i in range(len(atts))]
for a1, f1 in enumerate(filleds):
for a2 in range(a1):
matrix[a1, a2] = (1.0 - statc.spearmanr(f1, filleds[a2])[0]) / 2.0
output_dict = {}
output_dict['dm']=matrix
return output_dict
def cforange_hierarchical_clustering(input_dict):
def computeMatrix(self):
self.error()
if self.data:
atts = self.data.domain.attributes
matrix = orange.SymMatrix(len(atts))
matrix.setattr('items', atts)
if self.classInteractions < 3:
if self.data.domain.hasContinuousAttributes():
if self.discretizedData is None:
self.discretizedData = orange.Preprocessor_discretize(
self.data,
method=orange.EquiNDiscretization(
numberOfIntervals=4))
data = self.discretizedData
else:
data = self.data
# This is ugly, but: Aleks' code which computes Chi2 requires the class attribute because it prepares
# some common stuff for all measures. If we want to use his code, we need the class variable, so we
# prepare a fake one
if not data.domain.classVar:
if self.classInteractions == 0:
classedDomain = orange.Domain(
data.domain.attributes,
orange.EnumVariable("foo", values=["0", "1"]))
data = orange.ExampleTable(classedDomain, data)
else:
self.error(
"The selected distance measure requires a data set with a class attribute"
)
return None
im = orngInteract.InteractionMatrix(data, dependencies_too=1)
off = 1
if self.classInteractions == 0:
diss, labels = im.exportChi2Matrix()
off = 0
elif self.classInteractions == 1:
(diss, labels) = im.depExportDissimilarityMatrix(
jaccard=1) # 2-interactions
else:
(diss, labels) = im.exportDissimilarityMatrix(
jaccard=1) # 3-interactions
for i in range(len(atts) - off):
for j in range(i + 1):
matrix[i + off, j] = diss[i][j]
else:
if self.classInteractions == 3:
for a1 in range(len(atts)):
for a2 in range(a1):
matrix[a1, a2] = orange.PearsonCorrelation(
a1, a2, self.data, 0).p
else:
import numpy, statc
m = self.data.toNumpyMA("A")[0]
averages = numpy.ma.average(m, axis=0)
filleds = [
list(numpy.ma.filled(m[:, i], averages[i]))
for i in range(len(atts))
]
for a1, f1 in enumerate(filleds):
for a2 in range(a1):
matrix[a1, a2] = statc.spearmanr(f1,
filleds[a2])[1]
return matrix
else:
return None