def testWeightedModelMatrix(self):
linearModel = LinearModel(
self.regressorList, self.regressorNames, self.covMatrixObserv2, regressorsAreWeighted=True
)
self.assertTrue(np.alltrue(linearModel.designMatrix() == self.unweightedDesignMatrix))
linearModel = LinearModel(
self.regressorList, self.regressorNames, self.covMatrixObserv2, regressorsAreWeighted=False
)
self.assertFalse(np.alltrue(linearModel.designMatrix() == self.unweightedDesignMatrix))
expectedWeightedDesignMatrix = np.array(
[
[3.16227766e00, 4.73643073e-15],
[4.23376727e-01, 2.79508497e00],
[-2.67843095e-01, 3.79299210e00],
[-5.45288776e-01, 4.39760881e00],
[-6.78144517e-01, 4.84809047e00],
[-7.46997591e-01, 5.21965041e00],
[-7.83412990e-01, 5.54374745e00],
[-8.01896636e-01, 5.83605564e00],
[-8.09868157e-01, 6.10538773e00],
[-8.11425366e-01, 6.35716086e00],
]
)
self.assertTrue(
np.allclose(linearModel.designMatrix(), expectedWeightedDesignMatrix, rtol=1.0e-6, atol=1.0e-08)
)
def testCopyLinearModel(self):
linearModel = LinearModel(self.regressorList, self.regressorNames)
linearModel2 = linearModel.copy()
self.assertTrue(linearModel2.nParameters() == self.nParameters)
self.assertTrue(np.alltrue(linearModel2.designMatrix() == self.designMatrix))
self.assertTrue(linearModel2.regressorNames() == self.regressorNames)
self.assertTrue(id(linearModel2.designMatrix()) != id(linearModel.designMatrix()))
self.assertTrue(id(linearModel2.regressorNames()) != id(linearModel.regressorNames()))
def testCopyLinearModel(self):
linearModel = LinearModel(self.regressorList, self.regressorNames)
linearModel2 = linearModel.copy()
self.assertTrue(linearModel2.nParameters() == self.nParameters)
self.assertTrue(np.alltrue(linearModel2.designMatrix() == self.designMatrix))
self.assertTrue(linearModel2.regressorNames() == self.regressorNames)
self.assertTrue(id(linearModel2.designMatrix()) != id(linearModel.designMatrix()))
self.assertTrue(id(linearModel2.regressorNames()) != id(linearModel.regressorNames()))
def testWeightedModelMatrix(self):
linearModel = LinearModel(self.regressorList, self.regressorNames, self.covMatrixObserv2, regressorsAreWeighted=True)
self.assertTrue(np.alltrue(linearModel.designMatrix() == self.unweightedDesignMatrix))
linearModel = LinearModel(self.regressorList, self.regressorNames, self.covMatrixObserv2, regressorsAreWeighted=False)
self.assertFalse(np.alltrue(linearModel.designMatrix() == self.unweightedDesignMatrix))
expectedWeightedDesignMatrix = np.array([[ 3.16227766e+00, 4.73643073e-15],
[ 4.23376727e-01, 2.79508497e+00],
[-2.67843095e-01, 3.79299210e+00],
[-5.45288776e-01, 4.39760881e+00],
[-6.78144517e-01, 4.84809047e+00],
[-7.46997591e-01, 5.21965041e+00],
[-7.83412990e-01, 5.54374745e+00],
[-8.01896636e-01, 5.83605564e+00],
[-8.09868157e-01, 6.10538773e+00],
[-8.11425366e-01, 6.35716086e+00]])
self.assertTrue(np.allclose(linearModel.designMatrix(), expectedWeightedDesignMatrix, rtol=1.0e-6, atol=1.e-08))
def testAddLinearModel(self):
linearModel = LinearModel(self.regressorList, self.regressorNames)
linearModel2 = LinearModel(self.RegressorList2, self.RegressorNames2)
linearModel = linearModel + linearModel2
self.assertTrue(linearModel.nParameters() == self.newnParameters)
self.assertTrue(np.alltrue(linearModel.designMatrix() == self.newModelMatrix))
self.assertTrue(linearModel.regressorNames() == self.regressorNames + self.RegressorNames2)
self.assertTrue(linearModel._covMatrixObserv == None)
self.assertRaises(TypeError, lambda lm : lm + 1.0, linearModel)
self.assertRaises(ValueError, lambda x,y : LinearModel(x,y) + LinearModel(x[:-1,:],y),
self.designMatrix, self.regressorNames)
def testAddLinearModel(self):
linearModel = LinearModel(self.regressorList, self.regressorNames)
linearModel2 = LinearModel(self.RegressorList2, self.RegressorNames2)
linearModel = linearModel + linearModel2
self.assertTrue(linearModel.nParameters() == self.newnParameters)
self.assertTrue(np.alltrue(linearModel.designMatrix() == self.newModelMatrix))
self.assertTrue(linearModel.regressorNames() == self.regressorNames + self.RegressorNames2)
self.assertTrue(linearModel._covMatrixObserv == None)
self.assertRaises(TypeError, lambda lm: lm + 1.0, linearModel)
self.assertRaises(
ValueError,
lambda x, y: LinearModel(x, y) + LinearModel(x[:-1, :], y),
self.designMatrix,
self.regressorNames,
)
def testModelMatrix(self):
# With a list of regressor arrays as input
linearModel = LinearModel(self.regressorList, self.regressorNames)
self.assertTrue(isinstance(linearModel.designMatrix(), np.ndarray))
self.assertTrue(linearModel.designMatrix().dtype == np.double)
self.assertTrue(linearModel.designMatrix().shape == (self.nObservations, self.nParameters))
self.assertTrue(np.alltrue(linearModel.designMatrix() == self.designMatrix))
# With a design matrix as input
linearModel = LinearModel(self.designMatrix, self.regressorNames)
self.assertTrue(isinstance(linearModel.designMatrix(), np.ndarray))
self.assertTrue(linearModel.designMatrix().dtype == np.double)
self.assertTrue(linearModel.designMatrix().shape == (self.nObservations, self.nParameters))
self.assertTrue(np.alltrue(linearModel.designMatrix() == self.designMatrix))
def testModelMatrix(self):
# With a list of regressor arrays as input
linearModel = LinearModel(self.regressorList, self.regressorNames)
self.assertTrue(isinstance(linearModel.designMatrix(), np.ndarray))
self.assertTrue(linearModel.designMatrix().dtype == np.double)
self.assertTrue(linearModel.designMatrix().shape == (self.nObservations, self.nParameters))
self.assertTrue(np.alltrue(linearModel.designMatrix() == self.designMatrix))
# With a design matrix as input
linearModel = LinearModel(self.designMatrix, self.regressorNames)
self.assertTrue(isinstance(linearModel.designMatrix(), np.ndarray))
self.assertTrue(linearModel.designMatrix().dtype == np.double)
self.assertTrue(linearModel.designMatrix().shape == (self.nObservations, self.nParameters))
self.assertTrue(np.alltrue(linearModel.designMatrix() == self.designMatrix))
