def train(self, matrix_a, matrix_b):
"""
If cross validation is set to True, it performs generalized
cross validation. (Hastie, Tibshirani and Friedman, Second edition,
page 244).
"""
if not self._crossvalidation:
return Linalg.ridge_regression(matrix_a, matrix_b, self._param,
self._intercept)[0]
else:
min_err_param = 0
min_err = np.Inf
gcv_err = np.Inf
N = matrix_a.shape[0]
for param in self._param_range:
mat_x, S_trace, err1 = Linalg.ridge_regression(matrix_a, matrix_b, param,
self._intercept)
nom = pow(1 - S_trace / N, 2) * N
if nom != 0:
gcv_err = (err1 * err1) / nom
if gcv_err < min_err:
min_err = gcv_err
min_err_param = param
#print "lambda:", min_err_param
return Linalg.ridge_regression(matrix_a, matrix_b, min_err_param,
self._intercept)[0]
def train(self, matrix_a, matrix_b):
"""
If cross validation is set to True, it performs generalized
cross validation. (Hastie, Tibshirani and Friedman, Second edition,
page 244).
"""
if not self._crossvalidation:
return Linalg.ridge_regression(matrix_a, matrix_b, self._param,
self._intercept)[0]
else:
min_err_param = 0
min_err = np.Inf
gcv_err = np.Inf
N = matrix_a.shape[0]
for param in self._param_range:
mat_x, S_trace, err1 = Linalg.ridge_regression(matrix_a, matrix_b, param,
self._intercept)
nom = pow(1 - S_trace / N, 2) * N
if nom != 0:
gcv_err = (err1 * err1) / nom
if gcv_err < min_err:
min_err = gcv_err
min_err_param = param
#print "lambda:", min_err_param
return Linalg.ridge_regression(matrix_a, matrix_b, min_err_param,
self._intercept)[0]
def train(self, matrix_a, matrix_b=None):
"""
If cross validation is set to True, it performs generalized
cross validation. (Hastie, Tibshirani and Friedman, Second edition,
page 244).
TODO: not yet!
"""
pid = str(getpid())
logdir = 'convergence/'+pid
call(['mkdir', '-p', logdir])
# mkdir -p convergence/pid
self._trainId += 1 # For logging purposes
if not self._crossvalidation:
if self._projector:
matrix_b = matrix_a
W, costs = Linalg.tracenorm_regression(matrix_a, matrix_b, self._param, self._iterations, self._intercept)
print_tuple_list(costs, logdir+'/'+str(self._trainId)+'-lmbd-'+str(self._param))
return W
elif matrix_b == None:
raise ValueError("Unable to perform cross-validation without a phrase space")
else:
min_err_param = 0
min_err = np.Inf
gcv_err = np.Inf
N = matrix_a.shape[0]
for param in self._param_range:
mat_x, S_trace, err1 = Linalg.ridge_regression(matrix_a, matrix_b, param,
self._intercept)
nom = pow(1 - S_trace / N, 2) * N
if nom != 0:
gcv_err = (err1 * err1) / nom
if gcv_err < min_err:
min_err = gcv_err
min_err_param = param
#print "lambda:", min_err_param
return Linalg.ridge_regression(matrix_a, matrix_b, min_err_param,
self._intercept)[0]
def test_sparse_ridge_regression(self):
test_cases = self.pinv_test_cases
for m, m_inv in test_cases:
m1 = SparseMatrix(m)
id_ = SparseMatrix.identity(m1.shape[0])
res1 = Linalg.lstsq_regression(m1, id_)
np.testing.assert_array_almost_equal(res1.mat.todense(), m_inv, 7)
res2 = Linalg.ridge_regression(m1, id_, 1)[0]
error1 = (m1 * res1 - SparseMatrix(m_inv)).norm()
error2 = (m1 * res2 - SparseMatrix(m_inv)).norm()
#print "err", error1, error2
norm1 = error1 + res1.norm()
norm2 = error2 + res2.norm()
#print "norm", norm1, norm2
#THIS SHOULD HOLD, MAYBE ROUNDIGN ERROR?
#self.assertGreaterEqual(error2, error1)
self.assertGreaterEqual(norm1, norm2)
def test_sparse_ridge_regression(self):
test_cases = self.pinv_test_cases
for m, m_inv in test_cases:
m1 = SparseMatrix(m)
id_ = SparseMatrix.identity(m1.shape[0])
res1 = Linalg.lstsq_regression(m1, id_)
np.testing.assert_array_almost_equal(res1.mat.todense(), m_inv, 7)
res2 = Linalg.ridge_regression(m1, id_, 1)[0]
error1 = (m1 * res1 - SparseMatrix(m_inv)).norm()
error2 = (m1 * res2 - SparseMatrix(m_inv)).norm()
#print "err", error1, error2
norm1 = error1 + res1.norm()
norm2 = error2 + res2.norm()
#print "norm", norm1, norm2
#THIS SHOULD HOLD, MAYBE ROUNDIGN ERROR?
#self.assertGreaterEqual(error2, error1)
self.assertGreaterEqual(norm1, norm2)
