def test_space_compose_dense(self):
test_cases = [
([("a", "b", "a_b")], self.space4, self.space5,
DenseMatrix.identity(2), DenseMatrix.identity(2)),
([("a", "b", "a_b")], self.space4, self.space6,
np.mat([[0, 0], [0, 0]]), np.mat([[0, 0], [0, 0]])),
([("a", "b", "a_b"), ("a", "b", "a_a")], self.space4, self.space7,
DenseMatrix.identity(2), DenseMatrix.identity(2)),
]
for in_data, arg_space, phrase_space, mat_a, mat_b in test_cases:
comp_model = FullAdditive(A=mat_a, B=mat_b)
comp_space = comp_model.compose(in_data, arg_space)
np.testing.assert_array_almost_equal(
comp_space.cooccurrence_matrix.mat,
phrase_space.cooccurrence_matrix.mat, 10)
self.assertListEqual(comp_space.id2column, [])
self.assertDictEqual(comp_space.column2id, {})
self.assertListEqual(comp_space.id2row, phrase_space.id2row)
self.assertDictEqual(comp_space.row2id, phrase_space.row2id)
self.assertFalse(comp_model._has_intercept)
def test_space_compose_sparse(self):
#WHAT TO DO HERE???
#PARAMETERS ARE GIVEN AS DENSE MATRICES, INPUT DATA AS SPARSE??
test_cases = [([("a", "b", "a_b")], self.space1, self.space2,
DenseMatrix.identity(2), DenseMatrix.identity(2)),
([("a", "b", "a_b")], self.space1, self.space3,
np.mat([[0, 0], [0, 0]]), np.mat([[0, 0], [0, 0]]))]
for in_data, arg_space, phrase_space, mat_a, mat_b in test_cases:
comp_model = FullAdditive(A=mat_a, B=mat_b)
comp_space = comp_model.compose(in_data, arg_space)
np.testing.assert_array_almost_equal(
comp_space.cooccurrence_matrix.mat.todense(),
phrase_space.cooccurrence_matrix.mat.todense(), 10)
def test_dense_lstsq_regression(self):
test_cases = self.pinv_test_cases
for m, m_inv in test_cases:
m1 = DenseMatrix(m)
id_ = DenseMatrix.identity(m1.shape[0])
res = Linalg.lstsq_regression(m1, id_)
np.testing.assert_array_almost_equal(res.mat, m_inv, 7)
def test_dense_lstsq_regression(self):
test_cases = self.pinv_test_cases
for m, m_inv in test_cases:
m1 = DenseMatrix(m)
id_ = DenseMatrix.identity(m1.shape[0])
res = Linalg.lstsq_regression(m1, id_)
np.testing.assert_array_almost_equal(res.mat, m_inv, 7)
def test_space_compose_dense(self):
test_cases = [([("a","b","a_b")], self.space4, self.space5, DenseMatrix.identity(2), DenseMatrix.identity(2)),
([("a","b","a_b")], self.space4, self.space6, np.mat([[0,0],[0,0]]), np.mat([[0,0],[0,0]])),
([("a","b","a_b"),("a","b","a_a")], self.space4, self.space7, DenseMatrix.identity(2), DenseMatrix.identity(2)),
]
for in_data, arg_space, phrase_space, mat_a, mat_b in test_cases:
comp_model = FullAdditive(A=mat_a, B=mat_b)
comp_space = comp_model.compose(in_data, arg_space)
np.testing.assert_array_almost_equal(comp_space.cooccurrence_matrix.mat,
phrase_space.cooccurrence_matrix.mat, 10)
self.assertListEqual(comp_space.id2column, [])
self.assertDictEqual(comp_space.column2id, {})
self.assertListEqual(comp_space.id2row, phrase_space.id2row)
self.assertDictEqual(comp_space.row2id, phrase_space.row2id)
self.assertFalse(comp_model._has_intercept)
def test_space_compose_sparse(self):
#WHAT TO DO HERE???
#PARAMTERS ARE GIVEN AS DENSE MATRICES, INPUT DATA AS SPARSE??
test_cases = [([("a","b","a_b")], self.space1, self.space2, DenseMatrix.identity(2), DenseMatrix.identity(2)),
([("a","b","a_b")], self.space1, self.space3, np.mat([[0,0],[0,0]]), np.mat([[0,0],[0,0]]))
]
for in_data, arg_space, phrase_space, mat_a, mat_b in test_cases:
comp_model = FullAdditive(A=mat_a, B=mat_b)
comp_space = comp_model.compose(in_data, arg_space)
np.testing.assert_array_almost_equal(comp_space.cooccurrence_matrix.mat.todense(),
phrase_space.cooccurrence_matrix.mat.todense(), 10)
def test_dense_ridge_regression(self):
test_cases = self.pinv_test_cases
for m, m_inv in test_cases:
m1 = DenseMatrix(m)
id_ = DenseMatrix.identity(m1.shape[0])
res1 = Linalg.lstsq_regression(m1, id_)
np.testing.assert_array_almost_equal(res1.mat, m_inv, 7)
res2 = Linalg.ridge_regression(m1, id_, 1)[0]
error1 = (m1 * res1 - DenseMatrix(m_inv)).norm()
error2 = (m1 * res2 - DenseMatrix(m_inv)).norm()
#print "err", error1, error2
norm1 = error1 + res1.norm()
norm2 = error2 + res2.norm()
#print "norm", norm1, norm2
#THIS SHOULD HOLD, BUT DOES NOT, MAYBE ROUNDING ERROR?
#self.assertGreaterEqual(error2, error1)
self.assertGreaterEqual(norm1, norm2)
def test_dense_ridge_regression(self):
test_cases = self.pinv_test_cases
for m, m_inv in test_cases:
m1 = DenseMatrix(m)
id_ = DenseMatrix.identity(m1.shape[0])
res1 = Linalg.lstsq_regression(m1, id_)
np.testing.assert_array_almost_equal(res1.mat, m_inv, 7)
res2 = Linalg.ridge_regression(m1, id_, 1)[0]
error1 = (m1 * res1 - DenseMatrix(m_inv)).norm()
error2 = (m1 * res2 - DenseMatrix(m_inv)).norm()
#print "err", error1, error2
norm1 = error1 + res1.norm()
norm2 = error2 + res2.norm()
#print "norm", norm1, norm2
#THIS SHOULD HOLD, BUT DOES NOT, MAYBE ROUNDING ERROR?
#self.assertGreaterEqual(error2, error1)
self.assertGreaterEqual(norm1, norm2)
def train(self, matrix_a, matrix_b=None):
"""
matrix_b is ignored
"""
W = DenseMatrix.identity(matrix_a.shape[1])
return W
