def testLoadData(self):
testPoints = [[0.307143, 0.130137, 0.050000],
[0.365584, 0.105479, 0.050000],
[0.178571, 0.201027, 0.050000],
[0.272078, 0.145548, 0.050000],
[0.318831, 0.065411, 0.050000],
[0.190260, 0.086986, 0.050000],
[0.190260, 0.062329, 0.072500],
[0.120130, 0.068493, 0.072500],
[0.225325, 0.056164, 0.072500],
[0.213636, 0.050000, 0.072500]]
testValues = [
-1.000000, 1.000000, 1.000000, 1.000000, 1.000000, 1.000000,
-1.000000, -1.000000, -1.000000, -1.000000
]
filename = pathlocal + '/datasets/liver-disorders_normalized.arff.gz'
adapter = ARFFAdapter(filename)
container = adapter.loadData()
points = container.getPoints()
values = container.getValues()
size = len(testPoints)
dim = len(testPoints[0])
testVector = DataVector(dim)
for rowIdx in xrange(size):
points.getRow(rowIdx, testVector)
for colIdx in xrange(dim):
if cvar.USING_DOUBLE_PRECISION:
self.assertEqual(testVector[colIdx],
testPoints[rowIdx][colIdx])
else:
self.assertAlmostEqual(testVector[colIdx],
testPoints[rowIdx][colIdx])
self.assertEqual(values[rowIdx], testValues[rowIdx])
def testLoadData(self):
testPoints = [[0.307143,0.130137,0.050000],
[0.365584,0.105479,0.050000],
[0.178571,0.201027,0.050000],
[0.272078,0.145548,0.050000],
[0.318831,0.065411,0.050000],
[0.190260,0.086986,0.050000],
[0.190260,0.062329,0.072500],
[0.120130,0.068493,0.072500],
[0.225325,0.056164,0.072500],
[0.213636,0.050000,0.072500]
]
testValues = [-1.000000, 1.000000, 1.000000, 1.000000, 1.000000, 1.000000, -1.000000, -1.000000, -1.000000, -1.000000]
filename = pathlocal + '/datasets/liver-disorders_normalized.arff.gz'
adapter = ARFFAdapter(filename)
container = adapter.loadData()
points = container.getPoints()
values = container.getValues()
size = len(testPoints)
dim = len(testPoints[0])
testVector = DataVector(dim)
for rowIdx in xrange(size):
points.getRow(rowIdx, testVector)
for colIdx in xrange(dim):
if cvar.USING_DOUBLE_PRECISION:
self.assertEqual(testVector[colIdx], testPoints[rowIdx][colIdx])
else:
self.assertAlmostEqual(testVector[colIdx], testPoints[rowIdx][colIdx])
self.assertEqual(values[rowIdx], testValues[rowIdx])
def testSave(self):
filename = pathlocal + '/datasets/saving.arff.gz'
testPoints = [[0.307143, 0.130137, 0.050000],
[0.365584, 0.105479, 0.050000],
[0.178571, 0.201027, 0.050000],
[0.272078, 0.145548, 0.050000],
[0.318831, 0.065411, 0.050000],
[0.190260, 0.086986, 0.050000],
[0.190260, 0.062329, 0.072500],
[0.120130, 0.068493, 0.072500],
[0.225325, 0.056164, 0.072500],
[0.213636, 0.050000, 0.072500]]
testValues = [
-1.000000, 1.000000, 1.000000, 1.000000, 1.000000, 1.000000,
-1.000000, -1.000000, -1.000000, -1.000000
]
attributes = {
"x0": "NUMERIC",
"x1": "NUMERIC",
"x2": "NUMERIC",
"class": "NUMERIC",
}
size = len(testPoints)
dim = len(testPoints[0])
point = DataVector(dim)
points = DataMatrix(size, dim)
for row in xrange(size):
for col in xrange(dim):
point[col] = testPoints[row][col]
points.setRow(row, point)
adapter = ARFFAdapter(filename)
adapter.save(points, testValues, attributes)
(points, values) = adapter.loadData().getPointsValues()
size = len(testPoints)
dim = len(testPoints[0])
testVector = DataVector(dim)
for rowIdx in xrange(size):
points.getRow(rowIdx, testVector)
for colIdx in xrange(dim):
if cvar.USING_DOUBLE_PRECISION:
self.assertEqual(testVector[colIdx],
testPoints[rowIdx][colIdx])
else:
self.assertAlmostEqual(testVector[colIdx],
testPoints[rowIdx][colIdx])
self.assertEqual(values[rowIdx], testValues[rowIdx])
os.remove(filename)
def withTestingDataFromARFFFile(self, filename):
"""
Signals to use data from ARFF file for testing dataset
@param filename: Filename where to read the data from
@return: LearnerBuilder object itself
"""
adapter = ARFFAdapter(filename)
dataContainer = adapter.loadData(DataContainer.TEST_CATEGORY)
if self._learner.dataContainer is not None:
dataContainer = self._learner.dataContainer.combine(dataContainer)
self._learner.setDataContainer(dataContainer)
else:
self._learner.setDataContainer(dataContainer)
return self
def withTestingDataFromARFFFile(self, filename):
"""
Signals to use data from ARFF file for testing dataset
@param filename: Filename where to read the data from
@return: LearnerBuilder object itself
"""
adapter = ARFFAdapter(filename)
dataContainer = adapter.loadData(DataContainer.TEST_CATEGORY)
if self._learner.dataContainer is not None:
dataContainer = self._learner.dataContainer.combine(dataContainer)
self._learner.setDataContainer(dataContainer)
else:
self._learner.setDataContainer(dataContainer)
return self
def testSave(self):
filename = pathlocal + '/datasets/saving.arff.gz'
testPoints = [[0.307143,0.130137,0.050000],
[0.365584,0.105479,0.050000],
[0.178571,0.201027,0.050000],
[0.272078,0.145548,0.050000],
[0.318831,0.065411,0.050000],
[0.190260,0.086986,0.050000],
[0.190260,0.062329,0.072500],
[0.120130,0.068493,0.072500],
[0.225325,0.056164,0.072500],
[0.213636,0.050000,0.072500]
]
testValues = [-1.000000, 1.000000, 1.000000, 1.000000, 1.000000, 1.000000, -1.000000, -1.000000, -1.000000, -1.000000]
attributes = {
"x0":"NUMERIC",
"x1":"NUMERIC",
"x2":"NUMERIC",
"class":"NUMERIC",
}
size = len(testPoints)
dim = len(testPoints[0])
point = DataVector(dim)
points = DataMatrix(size, dim)
for row in xrange(size):
for col in xrange(dim):
point[col] = testPoints[row][col]
points.setRow(row, point)
adapter = ARFFAdapter(filename)
adapter.save(points, testValues, attributes)
(points, values) = adapter.loadData().getPointsValues()
size = len(testPoints)
dim = len(testPoints[0])
testVector = DataVector(dim)
for rowIdx in xrange(size):
points.getRow(rowIdx, testVector)
for colIdx in xrange(dim):
if cvar.USING_DOUBLE_PRECISION:
self.assertEqual(testVector[colIdx], testPoints[rowIdx][colIdx])
else:
self.assertAlmostEqual(testVector[colIdx], testPoints[rowIdx][colIdx])
self.assertEqual(values[rowIdx], testValues[rowIdx])
os.remove(filename)