def test_call_construction(self):
d = orange.ExampleTable("iris")
e1 = d[0]
e2 = d[50]
eud = orange.ExamplesDistanceConstructor_Euclidean(d, ignore_class=True, normalize=False, foo=42)
self.assertEqual(eud(e1, e2), math.sqrt(sum((x-y)**2 for x, y in zip(list(e1)[:-1], e2))))
self.assertEqual(eud.foo, 42)
eud = orange.ExamplesDistanceConstructor_Euclidean(d, ignore_class=False, normalize=False, foo=42)
self.assertEqual(eud(e1, e2), math.sqrt(sum((x-y)**2 for x, y in zip(list(e1), e2))))
self.assertEqual(eud.foo, 42)
def kNNratioInd(train, calSet, measure=None):
"""
Use the fraction of kNN with the same response.
"""
if not measure:
#measure = instances.MahalanobisConstructor(extTrain)
measure = orange.ExamplesDistanceConstructor_Euclidean(train)
alphaList = []
for predEx in calSet:
distList = []
for runIdx in range(len(train)):
dist = measure(predEx, train[runIdx])
distList.append(dist)
# Get the distance of the 10th NN
distList.sort()
thresDist = distList[9]
# Find the labels of the 10 NN
sameCount = 0
for runIdx in range(len(train)):
dist = measure(predEx, train[runIdx])
if dist <= thresDist:
if predEx.get_class().value == train[runIdx].get_class().value:
sameCount = sameCount + 1
alpha = 1.00 - float(sameCount) / 10.0
alphaList.append(alpha)
return alphaList, train
def avgNN(idx, extTrain, measure=None):
"""
Use the ratio between the distance to the kNN of the same and of the other class
"""
attrList = ["SMILES_1"]
extTrain = dataUtilities.attributeDeselectionData(extTrain, attrList)
distListSame = []
distListDiff = []
#measure = Orange.distance.Euclidean(extTrain)
if not measure:
measure = orange.ExamplesDistanceConstructor_Euclidean(extTrain)
for runIdx in range(len(extTrain)):
if runIdx != idx:
dist = measure(extTrain[idx], extTrain[runIdx])
if extTrain[idx].get_class().value == extTrain[runIdx].get_class(
).value:
distListSame.append(dist)
else:
distListDiff.append(dist)
distListSame.sort()
avgSame = sum(distListSame[0:10]) / 10.0
distListDiff.sort()
avgDiff = sum(distListDiff[0:10]) / 10.0
if avgDiff == 0:
alpha = max(distListDiff)
else:
alpha = avgSame / float(avgDiff)
return alpha
def kNNratio(idx, extTrain, measure=None):
"""
Use the fraction of kNN with the same response.
"""
attrList = ["SMILES_1"]
extTrain = dataUtilities.attributeDeselectionData(extTrain, attrList)
distList = []
if not measure:
#measure = instances.MahalanobisConstructor(extTrain)
measure = orange.ExamplesDistanceConstructor_Euclidean(extTrain)
for runIdx in range(len(extTrain)):
if runIdx != idx:
dist = measure(extTrain[idx], extTrain[runIdx])
distList.append(dist)
# Get the distance of the 10th NN
distList.sort()
thresDist = distList[9]
# Find the labels of the 10 NN
sameCount = 0
for runIdx in range(len(extTrain)):
if runIdx != idx:
dist = measure(extTrain[idx], extTrain[runIdx])
if dist <= thresDist:
if extTrain[idx].get_class(
).value == extTrain[runIdx].get_class().value:
sameCount = sameCount + 1
alpha = 1.00 - float(sameCount) / 10.0
return alpha
def getMinDistRatio(train):
"""
Calculate the minDistSame and minDistDiff ratio for all ex in the data set and select the greatest quotient.
Used to scale the minDist ratios in the non-conf score.
"""
# Get the min dist for all ex in the data set
minSame = []
minDiff = []
minRatio = []
measure = orange.ExamplesDistanceConstructor_Euclidean(extTrain)
for idx in range(len(train)):
distListSame = []
distListDiff = []
for iidx in range(len(train)):
if idx != iidx:
dist = measure(train[idx], train[iidx])
if train[idx].get_class().value == train[iidx].get_class(
).value:
distListSame.append(dist)
else:
distListDiff.append(dist)
minSame.append(min(distListSame))
minDiff.append(min(distListDiff))
if min(distListDiff) == 0:
alpha = max(distListDiff)
else:
minRatio.append(min(distListSame) / float(min(distListDiff)))
# Calculate min, mean and std of all the min distances
meanSame, stdSame = meanStd(minSame)
meanDiff, stdDiff = meanStd(minDiff)
maxDistRatio = max(minRatio)
return maxDistRatio
def getMeanStd(extTrain):
# Get the min dist for all ex in the data set
minSame = []
minDiff = []
measure = orange.ExamplesDistanceConstructor_Euclidean(extTrain)
for idx in range(len(extTrain)):
distListSame = []
distListDiff = []
for iidx in range(len(extTrain)):
if idx != iidx:
dist = measure(extTrain[idx], extTrain[iidx])
if extTrain[idx].get_class().value == extTrain[iidx].get_class(
).value:
distListSame.append(dist)
else:
distListDiff.append(dist)
minSame.append(min(distListSame))
minDiff.append(min(distListDiff))
# Calculate mean and std of all the min distances
meanSame, stdSame = meanStd(minSame)
meanDiff, stdDiff = meanStd(minDiff)
return meanSame, stdSame, meanDiff, stdDiff
def CVByPairs(data, dimensions=None, method=None, **dic):
import orngTree
cv = orange.MakeRandomIndicesCV(data, 10)
meter = orange.ExamplesDistanceConstructor_Euclidean(data)
maxDist = 0
for i in range(100):
maxDist = max(maxDist, meter(data.randomexample(),
data.randomexample()))
weightK = 10.0 / maxDist
acc = amb = unre = 0
for fold in range(10):
train = data.select(cv, fold, negate=1)
test = data.select(cv, fold)
pa, qid, did, cid = pade(train,
dimensions,
method,
originalAsMeta=True,
**dic)
tree = orngTree.TreeLearner(pa, maxDepth=4)
tacc, tamb, tunre = computeDirectionAccuracyForPairs(
tree, data, meter, weightK, -1)
acc += tacc
amb += tamb
unre += tunre
return acc / 10, amb / 10, unre / 10
def distanceMatrix(data):
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])
return matrix
def LLOOprob(idx, extTrain, measure=None):
"""
Use the fraction of kNN correctly predicted by a local model
Hard coded to 20 NN.
Modeling method. RF of Tree?
"""
distList = []
if not measure:
measure = orange.ExamplesDistanceConstructor_Euclidean(extTrain)
for runIdx in range(len(extTrain)):
if runIdx != idx:
dist = measure(extTrain[idx], extTrain[runIdx])
distList.append(dist)
# Get the distance of the 20th NN
distList.sort()
thresDist = distList[
50] # Smaller number of NN does not work with returnDFV
# Find the predEx and the 20 NN
kNN = []
for runIdx in range(len(extTrain)):
dist = measure(extTrain[idx], extTrain[runIdx])
if dist <= thresDist:
kNN.append(extTrain[runIdx])
kNNtrain = dataUtilities.DataTable(kNN)
# Find the fraction of correctly predicted ex in a LOO over kNN
alphaList = []
for iidx in range(len(kNNtrain)):
# Deselect example idx in extTrain
idxList = range(0, iidx)
idxList.extend(range(iidx + 1, len(kNNtrain)))
train = kNNtrain.get_items(idxList)
# Get prediction and pred probability
model = AZorngRF.RFLearner(train)
predList = model(kNNtrain[iidx], returnDFV=True)
pred = predList[0].value
prob = predList[1]
actual = kNNtrain[iidx].get_class().value
# alpha should be greater the less certain the model
try:
if pred != actual:
alpha = 1.0 + abs(prob)
else:
alpha = 1.0 - abs(prob)
alphaList.append(alpha)
except:
pass
alpha = sum(alphaList) / float(len(alphaList))
return alpha
def test_learner_on(self, data):
""" Test custom kernel wrapper
"""
# Need the data for ExamplesDistanceConstructor_Euclidean
self.learner = self.LEARNER(
kernel_type=SVMLearner.Custom,
kernel_func=RBFKernelWrapper(
orange.ExamplesDistanceConstructor_Euclidean(data), gamma=0.5))
testing.LearnerTestCase.test_learner_on(self, data)
def construct_distance_matrix(data):
'''
Constructs a distance matrix using Euclidean distance
'''
euclidean = orange.ExamplesDistanceConstructor_Euclidean(data)
distance = orange.SymMatrix(len(data))
for i in range(len(data)):
for j in range(i + 1):
distance[i, j] = euclidean(data[i], data[j])
return distance
def test_learner_on(self, data):
""" Test custom kernel wrapper
"""
if data.domain.has_continuous_attributes():
dist = orange.ExamplesDistanceConstructor_Euclidean(data)
else:
dist = orange.ExamplesDistanceConstructor_Hamming(data)
self.learner = self.LEARNER(kernel_type=SVMLearner.Custom,
kernel_func=RBFKernelWrapper(dist,
gamma=0.5))
testing.LearnerTestCase.test_learner_on(self, data)
svm_test_binary_classifier(self, data)
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 LLOO(idx, extTrain, measure=None):
"""
Use the fraction of kNN correctly predicted by a local model
Hard coded to 20 NN.
Modeling method. RF of Tree?
"""
attrList = ["SMILES_1"]
extTrain = dataUtilities.attributeDeselectionData(extTrain, attrList)
distList = []
if not measure:
measure = orange.ExamplesDistanceConstructor_Euclidean(extTrain)
for runIdx in range(len(extTrain)):
if runIdx != idx:
dist = measure(extTrain[idx], extTrain[runIdx])
distList.append(dist)
# Get the distance of the 20th NN
distList.sort()
thresDist = distList[19]
# Find the labels of the 20 NN
kNN = []
for runIdx in range(len(extTrain)):
dist = measure(extTrain[idx], extTrain[runIdx])
if dist <= thresDist:
kNN.append(extTrain[runIdx])
kNNtrain = dataUtilities.DataTable(kNN)
# Find the fraction of correctly predicted ex in a LOO over kNN
corrPred = 0
for idx in range(len(kNNtrain)):
# Deselect example idx in extTrain
idxList = range(0, idx)
idxList.extend(range(idx + 1, len(kNNtrain)))
train = kNNtrain.get_items(idxList)
# Train a model
model = AZorngRF.RFLearner(train)
#model = Orange.classification.tree.TreeLearner(train)
pred = model(kNNtrain[idx]).value
actual = kNNtrain[idx].get_class().value
if pred == actual:
corrPred = corrPred + 1
alpha = 1.0 - float(corrPred) / len(kNNtrain)
return alpha
def analysis(self):
markers = [d.marker for d in self.data]
if len(filter(lambda x: x is not None, markers)) < 3:
self.sbox.setDisabled(True)
for item in self.scene.items():
self.scene.removeItem(item)
# i.setCanvas(None)
# self.canvas.update()
return
self.sbox.setEnabled(True)
pa, pb, pab = [self.data[markers.index(x)] for x in range(3)]
pb = orange.ExampleTable(pa.domain, pb)
pab = orange.ExampleTable(pa.domain, pab)
dist = orange.ExamplesDistanceConstructor_Euclidean(pa,
normalize=False)
ave = [0] * 3
vote = [0] * 3
genevote = []
for g in range(len(pa)):
d = [dist(pb[g], pab[g]), dist(pa[g], pab[g]), dist(pa[g], pb[g])]
voteindx = d.index(min(d))
vote[voteindx] += 1
genevote.append(voteindx)
if self.distype == 1:
for i in range(3):
d[i] = d[i] * d[i]
for i in range(3):
ave[i] += d[i]
if self.distype == 1:
ave = [math.sqrt(x) / len(pa) for x in ave]
else:
ave = [x / len(pa) for x in ave]
# compute Chi^2 statistics,
# update the interface (report on results)
for i in range(3):
self.selChkbox[i].setText(self.cbinfo[i][1] +
" (%d genes)" % vote[i])
p = statc.chisquare([len(pa) / 3.] * 3, vote)[1]
self.infochi.setText('Chi Square: ' +
['p = %6.4f' % p, 'p < 0.0001'][p < 0.0001])
self.setAnalysisPlot(ave)
self.senddata(genevote)
def test():
app = QApplication(sys.argv)
w = OWHierarchicalClustering()
w.show()
data = orange.ExampleTable("../../doc/datasets/iris.tab")
id = orange.newmetaid()
data.domain.addmeta(id, orange.FloatVariable("a"))
data.addMetaAttribute(id)
matrix = orange.SymMatrix(len(data))
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])
w.set_matrix(matrix)
app.exec_()
def minNN(idx, extTrain, maxDistRatio=None, measure=None):
"""
Use the ratio between the distance to the nearest neighbor of the same and of the other class
Two versions exist, with and without scaling with the max distance ratio within the train set.
"""
attrList = ["SMILES_1"]
extTrain = dataUtilities.attributeDeselectionData(extTrain, attrList)
distListSame = []
distListDiff = []
#measure = Orange.distance.Euclidean(extTrain)
if not measure:
measure = orange.ExamplesDistanceConstructor_Euclidean(extTrain)
for runIdx in range(len(extTrain)):
if runIdx != idx:
dist = measure(extTrain[idx], extTrain[runIdx])
if extTrain[idx].get_class().value == extTrain[runIdx].get_class(
).value:
distListSame.append(dist)
else:
distListDiff.append(dist)
minDistSame = min(distListSame)
minDistDiff = min(distListDiff)
if minDistDiff == 0:
if maxDistRatio:
alpha = 1.0
else:
alpha = max(distListDiff)
else:
if maxDistRatio:
alpha = minDistSame / (float(minDistDiff) * maxDistRatio)
else:
alpha = minDistSame / float(minDistDiff)
#fid = open("tempFile.txt", "a")
#fid.write(str(minDistSame)+"\t"+str(minDistDiff)+"\t"+str(maxDistRatio)+"\t"+str(alpha)+"\n")
#fid.close()
return alpha
def test_euclidean(self):
d = orange.ExampleTable("iris")
e1 = d[0]
e2 = d[50]
euc = orange.ExamplesDistanceConstructor_Euclidean()
euc.normalize = False
euc.ignoreClass = True
eud = euc(d)
self.assertEqual(eud(e1, e2), math.sqrt(sum((x-y)**2 for x, y in zip(list(e1)[:-1], e2))))
euc.ignoreClass = False
eud = euc(d)
self.assertEqual(eud(e1, e2), math.sqrt(sum((x-y)**2 for x, y in zip(e1, e2))))
euc.normalize = True
eud = euc(d)
eud(e1, e2) # Returns whatever
d2 = orange.ExampleTable("zoo")
self.assertRaises(ValueError, eud, d2[0], d2[1])
self.assertRaises(ValueError, eud, d2[0], d[0])
eud = euc(d2)
self.assertEqual(eud(d2[0], d2[0]), 0)
eud(d2[0], d2[1]) # Returns whatever
def repTime(msg):
#print "%s: %s" % (time.asctime(), msg)
pass
def callback(f, o):
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:
import orange, orngSVM
data = orange.ExampleTable("iris.tab")
l1 = orngSVM.SVMLearner()
l1.kernelFunc = orngSVM.RBFKernelWrapper(
orange.ExamplesDistanceConstructor_Euclidean(data), gamma=0.5)
l1.kernel_type = orange.SVMLearner.Custom
l1.probability = True
c1 = l1(data)
l1.name = "SVM - RBF(Euclidean)"
l2 = orngSVM.SVMLearner()
l2.kernelFunc = orngSVM.RBFKernelWrapper(
orange.ExamplesDistanceConstructor_Hamming(data), gamma=0.5)
l2.kernel_type = orange.SVMLearner.Custom
l2.probability = True
c2 = l2(data)
l2.name = "SVM - RBF(Hamming)"
l3 = orngSVM.SVMLearner()
l3.kernelFunc = orngSVM.CompositeKernelWrapper(
orngSVM.RBFKernelWrapper(
orange.ExamplesDistanceConstructor_Euclidean(data), gamma=0.5),
orngSVM.RBFKernelWrapper(orange.ExamplesDistanceConstructor_Hamming(data),
gamma=0.5),
l=0.5)
l3.kernel_type = orange.SVMLearner.Custom
l3.probability = True
c3 = l1(data)
l3.name = "SVM - Composite"
import orngTest, orngStat
def tubedRegression(cache, dimensions, progressCallback=None, **args):
if not cache.findNearest:
cache.findNearest = orange.FindNearestConstructor_BruteForce(
cache.data,
distanceConstructor=orange.ExamplesDistanceConstructor_Euclidean(),
includeSame=True)
if not cache.attrStat:
cache.attrStat = orange.DomainBasicAttrStat(cache.data)
normalizers = cache.findNearest.distance.normalizers
if progressCallback:
nExamples = len(cache.data)
nPoints = 100.0 / nExamples / len(dimensions)
effNeighbours = len(cache.contAttributes) > 1 and cache.nNeighbours or len(
cache.deltas)
for di, d in enumerate(dimensions):
contIdx = cache.contIndices[d]
minV, maxV = cache.attrStat[contIdx].min, cache.attrStat[contIdx].max
if minV == maxV:
continue
oldNormalizer = normalizers[cache.contIndices[d]]
normalizers[cache.contIndices[d]] = 0
for exi, ref_example in enumerate(cache.data):
if ref_example[contIdx].isSpecial():
cache.deltas[exi][d] = "?"
continue
ref_x = float(ref_example[contIdx])
Sx = Sy = Sxx = Syy = Sxy = n = 0.0
nn = cache.findNearest(ref_example, 0, True)
nn = [ex for ex in nn
if not ex[contIdx].isSpecial()][:effNeighbours]
mx = [abs(ex[contIdx] - ref_x) for ex in nn]
if not mx:
cache.deltas[exi][d] = "?"
continue
if max(mx) < 1e-10:
kw = math.log(.001)
else:
kw = math.log(.001) / max(mx)**2
for ex in nn[:effNeighbours]:
ex_x = float(ex[contIdx])
ex_y = float(ex.getclass())
w = math.exp(kw * (ex_x - ref_x)**2)
Sx += w * ex_x
Sy += w * ex_y
Sxx += w * ex_x**2
Syy += w * ex_y**2
Sxy += w * ex_x * ex_y
n += w
div = n * Sxx - Sx**2
if div: # and i<40:
b = (Sxy * n - Sx * Sy) / div
# div = Sx*Sy/n - Sxy
# if abs(div) < 1e-10:
# cache.errors[exi][d] = 1
# else:
# B = ((Syy - Sy**2/n) - (Sxx - Sx**2/n)) / 2 / div
#
# b_p = -B + math.sqrt(B**2+1)
# a = Sy/n - b_p * Sx/n
# error1 = 1/(1+b_p**2) * (Syy + a**2 + b_p**2*Sxx - 2*a*Sy + 2*a*b_p*Sx - 2*b_p*Sxy)
#
# b_2 = -B - math.sqrt(B**2+1)
# a = Sy/n - b_p * Sx/n
# error2 = 1/(1+b_p**2) * (Syy + a**2 + b_p**2*Sxx - 2*a*Sy + 2*a*b_p*Sx - 2*b_p*Sxy)
#
# if error1 < error2 and error1 >= 0:
# cache.errors[exi][d] = error1
# elif error2 >= 0:
# cache.errors[exi][d] = error2
# else:
# cache.errors[exi][d] = 42
# print error1, error2
a = (Sy - b * Sx) / n
err = (n * a**2 + b**2 * Sxx + Syy + 2 * a * b * Sx -
2 * a * Sy - 2 * b * Sxy)
tot = Syy - Sy**2 / n
mod = tot - err
merr = err / (n - 2)
if merr < 1e-10:
F = 0
Fprob = 1
else:
F = mod / merr
Fprob = statc.fprob(F, 1, int(n - 2))
cache.errors[exi][d] = Fprob
# print "%.4f" % Fprob,
#print ("%.3f\t" + "%.0f\t"*6 + "%f\t%f") % (w, ref_x, ex_x, n, a, b, merr, F, Fprob)
cache.deltas[exi][d] = b
else:
cache.deltas[exi][d] = "?"
if progressCallback:
progressCallback((nExamples * di + exi) * nPoints)
normalizers[cache.contIndices[d]] = oldNormalizer
import orange, orngSVM
data=orange.ExampleTable("iris.tab")
l1=orngSVM.SVMLearner()
l1.kernelFunc=orngSVM.RBFKernelWrapper(orange.ExamplesDistanceConstructor_Euclidean(data), gamma=0.5)
l1.kernel_type=orange.SVMLearner.Custom
l1.probability=True
c1=l1(data)
l1.name="SVM - RBF(Euclidean)"
l2=orngSVM.SVMLearner()
l2.kernelFunc=orngSVM.RBFKernelWrapper(orange.ExamplesDistanceConstructor_Hamming(data), gamma=0.5)
l2.kernel_type=orange.SVMLearner.Custom
l2.probability=True
c2=l2(data)
l2.name="SVM - RBF(Hamming)"
l3=orngSVM.SVMLearner()
l3.kernelFunc=orngSVM.CompositeKernelWrapper(orngSVM.RBFKernelWrapper(orange.ExamplesDistanceConstructor_Euclidean(data), gamma=0.5),orngSVM.RBFKernelWrapper(orange.ExamplesDistanceConstructor_Hamming(data), gamma=0.5), l=0.5)
l3.kernel_type=orange.SVMLearner.Custom
l3.probability=True
c3=l1(data)
l3.name="SVM - Composite"
import orngTest, orngStat
tests=orngTest.crossValidation([l1, l2, l3], data, folds=5)
[ca1, ca2, ca3]=orngStat.CA(tests)
print l1.name, "CA: %.2f" % ca1
print l2.name, "CA: %.2f" % ca2
print l3.name, "CA: %.2f" % ca3
def showWidget(self):
self.information()
if self.ow is not None:
self.ow.topWidgetPart.hide()
self.ow.setLayout(self.layout())
elif self.layout() is not None:
sip.delete(self.layout())
self.ow = None
if self.data is None:
self.information("No learning data given.")
return
if self.model is None: return
if "model" not in self.model.domain: return
if "label" in self.model.domain:
attr = self.model["label"].value.split(', ')
modelType = self.model["model"].value.upper()
projWidget = None
if modelType == "SCATTERPLOT" or modelType == "SCATTTERPLOT":
projWidget = self.setWidget(OWScatterPlot.OWScatterPlot)
if modelType == "RADVIZ":
projWidget = self.setWidget(OWRadviz.OWRadviz)
if modelType == "POLYVIZ":
projWidget = self.setWidget(OWPolyviz.OWPolyviz)
if projWidget is not None:
self.ow.setData(self.data)
self.ow.setShownAttributes(attr)
self.ow.handleNewSignals()
################################
### add new model types here ###
################################
if modelType == "SPCA" or modelType == "LINPROJ":
self.setWidget(OWLinProj.OWLinProj)
self.ow.setData(self.data)
self.ow.setShownAttributes(attr)
self.ow.handleNewSignals()
xAnchors, yAnchors = self.model["anchors"].value
self.ow.updateGraph(None, setAnchors=1, XAnchors=xAnchors, YAnchors=yAnchors)
if modelType == "TREE":
self.setWidget(OWClassificationTreeGraph.OWClassificationTreeGraph)
classifier = self.model["classifier"].value
self.ow.ctree(classifier)
if modelType == "BAYES":
self.setWidget(OWNomogram.OWNomogram)
classifier = self.model["classifier"].value
self.ow.classifier(classifier)
if modelType == "KNN":
exclude = [att for att in self.data.domain if att.name not in attr + [self.data.domain.classVar.name]]
data2 = orange.Preprocessor_ignore(self.data, attributes = exclude)
dist = orange.ExamplesDistanceConstructor_Euclidean(data2)
smx = orange.SymMatrix(len(data2))
smx.setattr('items', data2)
pb = OWGUI.ProgressBar(self, 100)
milestones = orngMisc.progressBarMilestones(len(data2)*(len(data2)-1)/2, 100)
count = 0
for i in range(len(data2)):
for j in range(i+1):
smx[i, j] = dist(data2[i], data2[j])
if count in milestones:
pb.advance()
count += 1
pb.finish()
self.setWidget(OWMDS.OWMDS)
self.ow.cmatrix(smx)
if self.ow is not None:
self.ow.send = self.send
if self.layout() is not None: sip.delete(self.layout())
self.setLayout(self.ow.layout())
self.ow.topWidgetPart.show()
self.update()
# Description: Shows how to find the nearest neighbours of the given example
# Category: basic classes, distances
# Classes: FindNearest, FindNearestConstructor, FindNearest_BruteForce, FindNearestConstructor_BruteForce
# Uses: lenses
# Referenced: FindNearest.htm
import orange
data = orange.ExampleTable("lenses")
nnc = orange.FindNearestConstructor_BruteForce()
nnc.distanceConstructor = orange.ExamplesDistanceConstructor_Euclidean()
did = -42
# Note that this is wrong: id should be assigned by
# did = orange.newmetaid()
# We only do this so that the script gives the same output each time it's run
nn = nnc(data, 0, did)
print "*** Reference example: ", data[0]
for ex in sorted(nn(data[0], 5)):
print ex
