def constructFromFile(self, fileName, **args) :
if 'data' not in args :
raise ValueError, 'missing data object'
self._data = args['data']
patternIDdict = misc.list2dict(self._data.labels.patternID,
range(len(self._data)))
labels = Labels(fileName)
patterns = []
pairs = []
for i in range(len(labels)) :
p1,p2 = labels.patternID[i].split('_')
# add only pairs for which we have kernel data:
if p1 in patternIDdict and p2 in patternIDdict :
pairs.append((patternIDdict[p1],patternIDdict[p2]))
patterns.append(i)
else :
print p1, ' or ', p2, 'not found'
labels = labels.__class__(labels, patterns = patterns)
self.pairs = pairs
first = [pair[0] for pair in pairs]
second = [pair[1] for pair in pairs]
firstVector = arrayWrap.intVector([pair[0] for pair in pairs])
secondVector = arrayWrap.intVector([pair[1] for pair in pairs])
self.callConstructor(firstVector, secondVector)
WrapperDataSet.attachLabels(self, labels)
def constructFromFile(self, fileName):
patternIDdict = misc.list2dict(self._data.labels.patternID,
range(len(self._data)))
labels = Labels(fileName)
patterns = []
pairs = []
for i in range(len(labels)):
p1, p2 = labels.patternID[i].split('_')
# add only pairs for which we have kernel data:
if p1 in patternIDdict and p2 in patternIDdict:
pairs.append((patternIDdict[p1], patternIDdict[p2]))
patterns.append(i)
else:
print p1, ' or ', p2, 'not found'
labels = labels.__class__(labels, patterns=patterns)
self.pairs = pairs
first = [pair[0] for pair in pairs]
second = [pair[1] for pair in pairs]
firstVector = arrayWrap.intVector([pair[0] for pair in pairs])
secondVector = arrayWrap.intVector([pair[1] for pair in pairs])
self.callConstructor(firstVector, secondVector)
WrapperDataSet.attachLabels(self, labels)
def constructFromFile(self, fileName):
patternIDdict = misc.list2dict(self._data.labels.patternID, range(len(self._data)))
labels = Labels(fileName)
patterns = []
pairs = []
for i in range(len(labels)):
p1, p2 = labels.patternID[i].split("_")
# add only pairs for which we have kernel data:
if p1 in patternIDdict and p2 in patternIDdict:
pairs.append((patternIDdict[p1], patternIDdict[p2]))
patterns.append(i)
else:
print p1, " or ", p2, "not found"
labels = labels.__class__(labels, patterns=patterns)
self.pairs = pairs
first = [pair[0] for pair in pairs]
second = [pair[1] for pair in pairs]
firstVector = arrayWrap.intVector([pair[0] for pair in pairs])
secondVector = arrayWrap.intVector([pair[1] for pair in pairs])
self.callConstructor(firstVector, secondVector)
WrapperDataSet.attachLabels(self, labels)
def mean(self, patterns=None):
if patterns is None: patterns = range(len(self))
if min(patterns) < 0 or max(patterns) >= len(self):
raise ValueError, 'Pattern index out of range'
cpatterns = arrayWrap.intVector(patterns)
return self.container.mean(self, cpatterns)
def mean(self, patterns = None) :
if patterns is None : patterns = range(len(self))
if min(patterns) < 0 or max(patterns) >= len(self) :
raise ValueError, 'Pattern index out of range'
cpatterns = arrayWrap.intVector(patterns)
return self.container.mean(self, cpatterns)
def nonzero(self, feature, patterns=None):
if patterns is None: patterns = range(len(self))
if type(patterns) != type([]): patterns = list(patterns)
if min(patterns) < 0 or max(patterns) >= len(self):
raise ValueError, 'Pattern index goes outside of range'
cpatterns = arrayWrap.intVector(patterns)
return self.container.nonzero(self, feature, cpatterns)
def featureCounts(self, patterns=None):
if patterns is None: patterns = range(len(self))
if type(patterns) != type([]): patterns = list(patterns)
if min(patterns) < 0 or max(patterns) >= len(self):
raise ValueError, 'Pattern index out of range'
cpatterns = arrayWrap.intVector(patterns)
return self.container.featureCounts(self, cpatterns)
def nonzero(self, feature, patterns = None) :
if patterns is None : patterns = range(len(self))
if type(patterns) != type([]) : patterns = list(patterns)
if min(patterns) < 0 or max(patterns) >= len(self) :
raise ValueError, 'Pattern index goes outside of range'
cpatterns = arrayWrap.intVector(patterns)
return self.container.nonzero(self, feature, cpatterns)
def featureCounts(self, patterns = None) :
if patterns is None : patterns = range(len(self))
if type(patterns) != type([]) : patterns = list(patterns)
if min(patterns) < 0 or max(patterns) >= len(self) :
raise ValueError, 'Pattern index out of range'
cpatterns = arrayWrap.intVector(patterns)
return self.container.featureCounts(self, cpatterns)
def eliminateFeatures(self, featureList):
"""eliminate a list of features from a dataset
INPUT:
featureList - a list of features to eliminate; these are numbers
between 0 and numFeatures-1 (indices of features, not their IDs)"""
if len(featureList) == 0: return
if type(featureList[0]) == type(''):
featureList = self.featureNames2IDs(featureList)
featureList.sort()
if type(featureList) != list:
featureList = list(featureList)
if max(featureList) >= self.numFeatures or min(featureList) < 0:
raise ValueError, 'Bad feature list'
cfeatureList = arrayWrap.intVector(featureList)
self.container.eliminateFeatures(self, cfeatureList)
self.updateFeatureDict(featureList)
def eliminateFeatures(self, featureList):
"""eliminate a list of features from a dataset
INPUT:
featureList - a list of features to eliminate; these are numbers
between 0 and numFeatures-1 (indices of features, not their IDs)"""
if len(featureList) == 0 : return
if type(featureList[0]) == type('') :
featureList = self.featureNames2IDs(featureList)
featureList.sort()
if type(featureList) != list :
featureList = list(featureList)
if max(featureList) >= self.numFeatures or min(featureList) < 0 :
raise ValueError, 'Bad feature list'
cfeatureList = arrayWrap.intVector(featureList)
self.container.eliminateFeatures(self, cfeatureList)
self.updateFeatureDict(featureList)
