def __init__(self, filename=None):
SupervisedDataSet.__init__(self, 0, 0)
self.nCls = 0
self.nSamples = 0
self.classHist = {}
self.filename = ''
if filename is not None:
self.loadData(filename)
def _setDataFields(self, x, y):
if not len(x): raise Exception("no input data found")
SupervisedDataSet.__init__(self, len(x[0]), 1)
self.setField('input', x)
self.setField('target', y)
flat_labels = list(self.getField('target').flatten())
classes = list(set(flat_labels))
self._classes = classes
self.nClasses = len(classes)
for class_ in classes:
self.classHist[class_] = flat_labels.count(class_)
def __init__(self, inp, target=1, nb_classes=0, class_labels=None):
"""Initialize an empty dataset.
`inp` is used to specify the dimensionality of the input. While the
number of targets is given by implicitly by the training samples, it can
also be set explicity by `nb_classes`. To give the classes names, supply
an iterable of strings as `class_labels`."""
# FIXME: hard to keep nClasses synchronized if appendLinked() etc. is used.
SupervisedDataSet.__init__(self, inp, target)
self.addField('class', 1)
self.nClasses = nb_classes
if len(self) > 0:
# calculate class histogram, if we already have data
self.calculateStatistics()
self.convertField('target', int)
if class_labels is None:
self.class_labels = list(set(self.getField('target').flatten()))
else:
self.class_labels = class_labels
# copy classes (may be changed into other representation)
self.setField('class', self.getField('target'))