def target_spearman_correlations(data, vars=None, target_var=None):
import numpy
import statc
if vars is None:
vars = list(data.domain.variables)
if target_var is None:
if is_continuous(data.domain.class_var):
target_var = data.domain.class_var
else:
raise ValueError("A data with continuous class variable expected if 'target_var' is not explicitly declared.")
all_vars = list(data.domain.variables)
indices = [all_vars.index(v) for v in vars]
target_index = all_vars.index(target_var)
(data,) = data.to_numpy_MA("Ac")
averages = numpy.ma.average(data, axis=0)
target_values = data[:, target_index].filled(averages[target_index])
target_values = list(target_values)
correlations = []
for i, var_i in enumerate(indices):
a = data[:,var_i].filled(averages[var_i])
correlations.append(statc.spearmanr(list(a), target_values)[0])
return correlations
def target_spearman_correlations(data, vars=None, target_var=None):
import numpy
import statc
if vars is None:
vars = list(data.domain.variables)
if target_var is None:
if is_continuous(data.domain.class_var):
target_var = data.domain.class_var
else:
raise ValueError(
"A data with continuous class variable expected if 'target_var' is not explicitly declared."
)
all_vars = list(data.domain.variables)
indices = [all_vars.index(v) for v in vars]
target_index = all_vars.index(target_var)
(data, ) = data.to_numpy_MA("Ac")
averages = numpy.ma.average(data, axis=0)
target_values = data[:, target_index].filled(averages[target_index])
target_values = list(target_values)
correlations = []
for i, var_i in enumerate(indices):
a = data[:, var_i].filled(averages[var_i])
correlations.append(statc.spearmanr(list(a), target_values)[0])
return correlations
def distSpearman(x, y):
"""distance corresponding to 1 - spearman's correlation coefficient for arrays x,y
returns distance: 1 - spearman_r
"""
x = MA.asarray(x)
y = MA.asarray(y)
assert MA.rank(x) == MA.rank(y) == 1
cond = MA.logical_not(MA.logical_or(MA.getmaskarray(x),
MA.getmaskarray(y)))
return 1 - statc.spearmanr(
MA.compress(cond, x).tolist(),
MA.compress(cond, y).tolist())[0]
def __call__(self, e1, e2):
X1 = []; X2 = []
for i in self.indxs:
if not(e1[i].isSpecial() or e2[i].isSpecial()):
X1.append(float(e1[i]))
X2.append(float(e2[i]))
if not X1:
return 1.0
try:
return (1.0 - statc.spearmanr(X1, X2)[0]) / 2.
except:
return 1.0
def compute_attr_dist_matrix(data):
import numpy, statc
attrs = data.domain.attributes
matrix = SymMatrix(len(attrs))
# why not just matrix.items = attrs?
matrix.setattr(b"items", attrs)
m = 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(attrs))]
for a1, f1 in enumerate(filleds):
for a2 in range(a1):
matrix[a1, a2] = (1.0 - statc.spearmanr(f1, filleds[a2])[0]) / 2.0
return matrix
def pairwise_spearman_correlations(data, vars=None):
import numpy
import statc
if vars is None:
vars = list(data.domain.variables)
matrix = Orange.core.SymMatrix(len(vars))
all_vars = list(data.domain.variables)
indices = [all_vars.index(v) for v in vars]
(data,) = data.to_numpy_MA("Ac")
averages = numpy.ma.average(data, axis=0)
for i, var_i in enumerate(indices):
for j, var_j in enumerate(indices[i + 1:], i + 1):
a = data[:, var_i].filled(averages[var_i])
b = data[:, var_j].filled(averages[var_j])
matrix[i, j] = statc.spearmanr(list(a), list(b))[0]
return matrix
def pairwise_spearman_correlations(data, vars=None):
import numpy
import statc
if vars is None:
vars = list(data.domain.variables)
matrix = Orange.core.SymMatrix(len(vars))
all_vars = list(data.domain.variables)
indices = [all_vars.index(v) for v in vars]
(data, ) = data.to_numpy_MA("Ac")
averages = numpy.ma.average(data, axis=0)
for i, var_i in enumerate(indices):
for j, var_j in enumerate(indices[i + 1:], i + 1):
a = data[:, var_i].filled(averages[var_i])
b = data[:, var_j].filled(averages[var_j])
matrix[i, j] = statc.spearmanr(list(a), list(b))[0]
return matrix
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):
return {'centroids' : None, 'selected_examples' : None, 'unselected_examples' : None}
class Clustering:
@staticmethod
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)]
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
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):
return {
'centroids': None,
'selected_examples': None,
'unselected_examples': None
}
class Clustering:
@staticmethod
def computeMatrix(self):
self.error(0)
if self.data:
atts = self.data.domain.attributes
if len(atts) < 2:
self.error(0, "Dataset must contain at least two attributes")
return None
matrix = orange.SymMatrix(len(atts))
matrix.setattr('items', atts)
if self.classInteractions < 3:
if self.data.domain.hasContinuousAttributes():
if self.discretizedData is None:
try:
self.discretizedData = orange.Preprocessor_discretize(self.data, method=orange.EquiNDiscretization(numberOfIntervals=4))
except orange.KernelException, ex:
self.error(0, "An error ocured during data discretization: %s" % ex.message)
return None
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(0, "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] = (1.0 - orange.PearsonCorrelation(a1, a2, self.data, 0).r) / 2.0
else:
if len(self.data) < 3:
self.error(0, "The selected distance measure requires a data set with at least 3 instances")
return None
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] = (1.0 - statc.spearmanr(f1, filleds[a2])[0]) / 2.0
return matrix