def computeCorrelationInsideClassesBetweenAttributes(data,
attrList,
minCorrelation=0.0,
progressCallback=None):
if not data.domain.classVar or data.domain.classVar.varType == orange.VarTypes.Continuous:
return []
correlations = []
attrListLen = len(attrList)
iterCount = attrListLen * (attrListLen - 1) / 2
iter = 0
milestones = progressBarMilestones(iterCount)
for i in range(len(attrList)):
if data.domain.attributes[i].varType != orange.VarTypes.Continuous:
continue
for j in range(i + 1, len(attrList)):
if data.domain.attributes[j].varType != orange.VarTypes.Continuous:
continue
corr, corrs, lengths = computeCorrelationInsideClasses(
data, attrList[i], attrList[j])
if corr >= minCorrelation:
correlations.append((corr, attrList[i], attrList[j]))
iter += 1
if progressCallback and iter in milestones:
progressCallback(100.0 * iter / iterCount)
return sorted(correlations, reverse=True)
def computeMatrix(self):
if not self.data:
return
data = self.data
dist = self.metrics[self.Metrics][1](data)
self.error(0)
try:
self.matrix = orange.SymMatrix(len(data))
except orange.KernelException as ex:
self.error(0, "Could not create distance matrix! %s" % str(ex))
self.matrix = None
self.send("Distance Matrix", None)
return
self.matrix.setattr('items', data)
pb = OWGUI.ProgressBar(self, 100)
milestones = orngMisc.progressBarMilestones(
len(data) * (len(data) - 1) / 2, 100)
count = 0
for i in range(len(data)):
for j in range(i + 1):
self.matrix[i, j] = dist(data[i], data[j])
if count in milestones:
pb.advance()
count += 1
pb.finish()
self.send("Distance Matrix", self.matrix)
def computeCorrelationBetweenAttributes(data, attrList, minCorrelation = 0.0, progressCallback=None):
correlations = []
attrListLen = len(attrList)
iterCount = attrListLen * (attrListLen - 1) / 2
iter = 0
milestones = progressBarMilestones(iterCount)
for i in range(len(attrList)):
if data.domain.attributes[i].varType != orange.VarTypes.Continuous:
continue
for j in range(i+1, len(attrList)):
if data.domain.attributes[j].varType != orange.VarTypes.Continuous:
continue
val = abs(computeCorrelation(data, attrList[i], attrList[j]))
if val >= minCorrelation:
correlations.append((val, attrList[i], attrList[j]))
iter += 1
if progressCallback and iter in milestones:
progressCallback(100.0 * iter / iterCount)
return sorted(correlations, reverse=True)
def computeCorrelationInsideClassesBetweenAttributes(data, attrList, minCorrelation = 0.0, progressCallback=None):
if not data.domain.classVar or data.domain.classVar.varType == orange.VarTypes.Continuous:
return []
correlations = []
attrListLen = len(attrList)
iterCount = attrListLen * (attrListLen - 1) / 2
iter = 0
milestones = progressBarMilestones(iterCount)
for i in range(len(attrList)):
if data.domain.attributes[i].varType != orange.VarTypes.Continuous:
continue
for j in range(i+1, len(attrList)):
if data.domain.attributes[j].varType != orange.VarTypes.Continuous:
continue
corr, corrs, lengths = computeCorrelationInsideClasses(data, attrList[i], attrList[j])
if corr >= minCorrelation:
correlations.append((corr, attrList[i], attrList[j]))
iter += 1
if progressCallback and iter in milestones:
progressCallback(100.0 * iter / iterCount)
return sorted(correlations, reverse=True)
def computeCorrelationBetweenAttributes(data,
attrList,
minCorrelation=0.0,
progressCallback=None):
correlations = []
attrListLen = len(attrList)
iterCount = attrListLen * (attrListLen - 1) / 2
iter = 0
milestones = progressBarMilestones(iterCount)
for i in range(len(attrList)):
if data.domain.attributes[i].varType != orange.VarTypes.Continuous:
continue
for j in range(i + 1, len(attrList)):
if data.domain.attributes[j].varType != orange.VarTypes.Continuous:
continue
val = abs(computeCorrelation(data, attrList[i], attrList[j]))
if val >= minCorrelation:
correlations.append((val, attrList[i], attrList[j]))
iter += 1
if progressCallback and iter in milestones:
progressCallback(100.0 * iter / iterCount)
return sorted(correlations, reverse=True)
class OWExampleDistance(OWWidget):
settingsList = ["Metrics", "Normalize"]
contextHandlers = {"": DomainContextHandler("", ["Label"])}
def __init__(self, parent=None, signalManager = None):
OWWidget.__init__(self, parent, signalManager, 'ExampleDistance', wantMainArea = 0, resizingEnabled = 0)
self.inputs = [("Data", ExampleTable, self.dataset)]
self.outputs = [("Distances", orange.SymMatrix)]
self.Metrics = 0
self.Normalize = True
self.Label = ""
self.loadSettings()
self.data = None
self.matrix = None
self.metrics = [
("Euclidean", orange.ExamplesDistanceConstructor_Euclidean),
("Pearson Correlation", orngClustering.ExamplesDistanceConstructor_PearsonR),
("Spearman Rank Correlation", orngClustering.ExamplesDistanceConstructor_SpearmanR),
("Manhattan", orange.ExamplesDistanceConstructor_Manhattan),
("Hamming", orange.ExamplesDistanceConstructor_Hamming),
("Relief", orange.ExamplesDistanceConstructor_Relief),
]
cb = OWGUI.comboBox(self.controlArea, self, "Metrics", box="Distance Metrics",
items=[x[0] for x in self.metrics],
tooltip="Choose metrics to measure pairwise distance between examples.",
callback=self.distMetricChanged, valueType=str)
cb.setMinimumWidth(170)
OWGUI.separator(self.controlArea)
box = OWGUI.widgetBox(self.controlArea, "Normalization",
addSpace=True)
self.normalizeCB = OWGUI.checkBox(box, self, "Normalize", "Normalize data",
callback=self.computeMatrix)
self.normalizeCB.setEnabled(self.Metrics in [0, 3])
self.labelCombo = OWGUI.comboBox(self.controlArea, self, "Label", box="Example Label",
items=[],
tooltip="Attribute used for example labels",
callback=self.setLabel, sendSelectedValue = 1)
self.labelCombo.setDisabled(1)
OWGUI.rubber(self.controlArea)
def sendReport(self):
self.reportSettings("Settings",
[("Metrics", self.metrics[self.Metrics][0]),
("Label", self.Label)])
self.reportData(self.data)
def distMetricChanged(self):
self.normalizeCB.setEnabled(self.Metrics in [0, 3])
self.computeMatrix()
def computeMatrix(self):
if not self.data:
return
data = self.data
constructor = self.metrics[self.Metrics][1]()
constructor.normalize = self.Normalize
dist = constructor(data)
self.error(0)
try:
self.matrix = orange.SymMatrix(len(data))
except orange.KernelException, ex:
self.error(0, "Could not create distance matrix! %s" % str(ex))
self.matrix = None
self.send("Distances", None)
return
self.matrix.setattr('items', data)
pb = OWGUI.ProgressBar(self, 100)
milestones = orngMisc.progressBarMilestones(len(data)*(len(data)-1)/2, 100)
count = 0
for i in range(len(data)):
for j in range(i+1):
self.matrix[i, j] = dist(data[i], data[j])
if count in milestones:
pb.advance()
count += 1
pb.finish()
self.send("Distances", self.matrix)
def readMatrix(fn, progress=None):
msg = None
matrix = labels = data = None
if type(fn) != file and (os.path.splitext(fn)[1] == '.pkl' or os.path.splitext(fn)[1] == '.sym'):
pkl_file = open(fn, 'rb')
matrix = pickle.load(pkl_file)
data = None
if hasattr(matrix, 'items'):
items = matrix.items
if isinstance(items, orange.ExampleTable):
data = items
elif isinstance(items, list) or hasattr(item, "__iter__"):
labels = items
pkl_file.close()
elif type(fn) != file and os.path.splitext(fn)[1] == '.npy':
import numpy
nmatrix = numpy.load(fn)
matrix = orange.SymMatrix(len(nmatrix))
milestones = orngMisc.progressBarMilestones(matrix.dim, 100)
for i in range(len(nmatrix)):
for j in range(i+1):
matrix[j,i] = nmatrix[i,j]
if progress and i in milestones:
progress.advance()
#labels = [""] * len(nmatrix)
else:
if type(fn) == file:
fle = fn
else:
fle = open(fn)
while 1:
lne = fle.readline().strip()
if lne:
break
spl = lne.split()
try:
dim = int(spl[0])
except IndexError:
raise ValueError("Matrix dimension expected in the first line.")
#print dim
labeled = len(spl) > 1 and spl[1] in ["labelled", "labeled"]
matrix = orange.SymMatrix(dim)
data = None
milestones = orngMisc.progressBarMilestones(dim, 100)
if labeled:
labels = []
else:
labels = [""] * dim
for li, lne in enumerate(fle):
if li > dim:
if not li.strip():
continue
raise ValueError("File to long")
spl = lne.split("\t")
if labeled:
labels.append(spl[0].strip())
spl = spl[1:]
if len(spl) > dim:
raise ValueError("Line %i too long" % li+2)
for lj, s in enumerate(spl):
if s:
try:
matrix[li, lj] = float(s)
except ValueError:
raise ValueError("Invalid number in line %i, column %i" % (li+2, lj))
if li in milestones:
if progress:
progress.advance()
if progress:
progress.finish()
return matrix, labels, data
