def setUp(self):
self.dir_ = data_dir + "/space_test_resources/"
self.init_test_cases = [(DenseMatrix(np.array([[1,2],[3,4]])),
["car", "man"],
["feat1", "feat2"],
{"man":1, "car":0},
{"feat1":0, "feat2":1},
[ScalingOperation(EpmiWeighting())]),
(DenseMatrix(np.array([[1,2],[3,4]])),
["car", "man"],
[],
{"man":1, "car":0},
{},
[ScalingOperation(EpmiWeighting())])]
self.m1 = np.array([[1,2,3]])
self.row1 = ["a"]
self.row2 = ["a", "b", "c"]
self.ft1 = ["f1","f2","f3"]
self.space1 = Space(DenseMatrix(self.m1),self.row1, self.ft1)
self.x = np.mat([[1,2,3],[2,4,6],[4,675,43]])
self.us = np.mat([[ 2.19272110e+00, 3.03174768e+00],
[ 4.38544220e+00, 6.06349536e+00],
[ 6.76369708e+02, -4.91431927e-02]])
self.space2 = Space(DenseMatrix(self.x), self.row2, self.ft1)
def test_top_feat_selection(self):
test_cases = [
(self.a, np.mat([[3, 1], [5, 4]]), [2, 0], 2),
(self.a, np.mat([[3], [5]]), [2], 1),
(self.a, np.mat([[3, 1, 2], [5, 4, 0]]), [2, 0, 1], 6),
]
for in_mat, expected_mat, expected_perm, no_cols in test_cases:
fs = TopFeatureSelection(no_cols)
out_mat, perm = fs.apply(DenseMatrix(in_mat))
np.testing.assert_array_equal(out_mat.mat, expected_mat)
self.assertListEqual(perm, expected_perm)
out_mat, perm = fs.apply(SparseMatrix(in_mat))
np.testing.assert_array_equal(out_mat.mat.todense(), expected_mat)
self.assertListEqual(perm, expected_perm)
fs = TopFeatureSelection(no_cols, criterion="length")
out_mat, perm = fs.apply(DenseMatrix(in_mat))
np.testing.assert_array_equal(out_mat.mat, expected_mat)
self.assertListEqual(perm, expected_perm)
out_mat, perm = fs.apply(SparseMatrix(in_mat))
np.testing.assert_array_equal(out_mat.mat.todense(), expected_mat)
self.assertListEqual(perm, expected_perm)
self.assertRaises(ValueError, TopFeatureSelection, 0)
self.assertRaises(ValueError,
TopFeatureSelection,
2,
criterion="something")
def test_trivial_crossvalidation(self):
for i in range(1, 10):
m_a = DenseMatrix(np.mat(np.random.random((i + 1, 4))))
m_b = DenseMatrix(np.mat(np.random.random((i + 1, 4))))
tmp_a = m_a.mat.copy()
tmp_b = m_b.mat.copy()
learner = RidgeRegressionLearner(param_range=[3], intercept=False)
solution = learner.train(m_a, m_b)
learner2 = RidgeRegressionLearner(param=3, intercept=False)
solution2 = learner2.train(m_a, m_b)
np.testing.assert_array_equal(tmp_a, m_a.mat)
np.testing.assert_array_equal(tmp_b, m_b.mat)
np.testing.assert_array_equal(solution.mat, solution2.mat)
learner = RidgeRegressionLearner(param_range=[3], intercept=False)
solution = learner.train(m_a, m_b)
np.testing.assert_array_equal(tmp_a, m_a.mat)
np.testing.assert_array_equal(tmp_b, m_b.mat)
np.testing.assert_array_equal(solution.mat, solution2.mat)
learner = RidgeRegressionLearner(param_range=[0], intercept=False)
solution = learner.train(m_a, m_b)
learner2 = LstsqRegressionLearner(intercept=False)
solution2 = learner2.train(m_a, m_b)
np.testing.assert_array_almost_equal(solution.mat, solution2.mat,
3)
def test_init_svd(self):
test_cases = [(self.space2, self.us, self.us2, self.x, self.row3)]
red1 = Svd(2)
red2 = Svd(1)
for in_s, expected_mat, expected_mat2, data, rows in test_cases:
in_s = in_s.apply(red1)
per_s = PeripheralSpace(in_s, DenseMatrix(data), rows)
np.testing.assert_array_almost_equal(expected_mat,
per_s.cooccurrence_matrix.mat,
2)
self.assertListEqual(per_s.id2row, in_s.id2row)
self.assertListEqual(per_s.id2column, [])
self.assertDictEqual(per_s.row2id, in_s.row2id)
self.assertDictEqual(per_s.column2id, {})
self.assertEqual(1, len(per_s.operations))
in_s = in_s.apply(red2)
per_s = PeripheralSpace(in_s, DenseMatrix(data), rows)
np.testing.assert_array_almost_equal(expected_mat2,
per_s.cooccurrence_matrix.mat,
2)
self.assertListEqual(per_s.id2row, in_s.id2row)
self.assertListEqual(per_s.id2column, [])
self.assertDictEqual(per_s.row2id, in_s.row2id)
self.assertDictEqual(per_s.column2id, {})
self.assertEqual(2, len(per_s.operations))
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 setUp(self):
self.ft = ["f1", "f2"]
self.n_space = Space(DenseMatrix(np.mat([[3, 4], [5, 6]])),
["car", "man"], self.ft)
self.an_space = Space(DenseMatrix(np.mat([[3, 4], [5, 6]])),
["a1_car", "a1_man"], self.ft)
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_train_intercept(self):
a1_mat = DenseMatrix(np.mat([[3,4],[5,6]]))
a2_mat = DenseMatrix(np.mat([[1,2],[3,4]]))
train_data = [("a1", "man", "a1_man"),
("a2", "car", "a2_car"),
("a1", "boy", "a1_boy"),
("a2", "boy", "a2_boy")
]
n_mat = DenseMatrix(np.mat([[13,21],[3,4],[5,6]]))
n_space = Space(n_mat, ["man", "car", "boy"], self.ft)
an1_mat = (a1_mat * n_mat.transpose()).transpose()
an2_mat = (a2_mat * n_mat.transpose()).transpose()
an_mat = an1_mat.vstack(an2_mat)
an_space = Space(an_mat, ["a1_man","a1_car","a1_boy","a2_man","a2_car","a2_boy"], self.ft)
#test train
model = LexicalFunction(learner=LstsqRegressionLearner(intercept=True))
model._MIN_SAMPLES = 1
model.train(train_data, n_space, an_space)
a_space = model.function_space
a1_mat.reshape((1,4))
#np.testing.assert_array_almost_equal(a1_mat.mat,
# a_space.cooccurrence_matrix.mat[0])
a2_mat.reshape((1,4))
#np.testing.assert_array_almost_equal(a2_mat.mat,
# a_space.cooccurrence_matrix.mat[1])
self.assertListEqual(a_space.id2row, ["a1", "a2"])
self.assertTupleEqual(a_space.element_shape, (2,3))
#test compose
a1_mat = DenseMatrix(np.mat([[3,4,5,6]]))
a2_mat = DenseMatrix(np.mat([[1,2,3,4]]))
a_mat = a_space.cooccurrence_matrix
a_space = Space(a_mat, ["a1", "a2"], [], element_shape=(2,3))
model = LexicalFunction(function_space=a_space, intercept=True)
model._MIN_SAMPLES = 1
comp_space = model.compose(train_data, n_space)
self.assertListEqual(comp_space.id2row, ["a1_man", "a2_car", "a1_boy", "a2_boy"])
self.assertListEqual(comp_space.id2column, [])
self.assertEqual(comp_space.element_shape, (2,))
np.testing.assert_array_almost_equal(comp_space.cooccurrence_matrix.mat,
an_mat[[0,4,2,5]].mat, 8)
def test_dilation(self):
self.m12 = DenseMatrix(np.mat([[3, 1], [9, 2]]))
self.m22 = DenseMatrix(np.mat([[4, 3], [2, 1]]))
self.ph2 = DenseMatrix(np.mat([[18, 11], [24, 7]]))
self.row = ["a", "b"]
self.ft = ["f1", "f2"]
self.space1 = Space(DenseMatrix(self.m12), self.row, self.ft)
self.space2 = Space(DenseMatrix(self.ph2), ["a_a", "a_b"], self.ft)
m = Dilation()
m.export(self.prefix + ".dil1")
m.train([("a", "b", "a_b")], self.space1, self.space2)
m.export(self.prefix + ".dil2")
def test_weighted_additive(self):
self.m12 = DenseMatrix(np.mat([[3, 1], [9, 2]]))
self.m22 = DenseMatrix(np.mat([[4, 3], [2, 1]]))
self.ph2 = DenseMatrix(np.mat([[18, 11], [24, 7]]))
self.row = ["a", "b"]
self.ft = ["f1", "f2"]
self.space1 = Space(DenseMatrix(self.m12), self.row, self.ft)
self.space2 = Space(DenseMatrix(self.ph2), ["a_a", "a_b"], self.ft)
m = WeightedAdditive()
m.export(self.prefix + ".add1")
m.train([("a", "a", "a_a")], self.space1, self.space2)
m.export(self.prefix + ".add2")
def test_init(self):
test_cases = [(self.space1, self.m2, self.row2, np.array([[2, 0.5,
1]]),
np.array([[0.69314718, 0, 0]]))]
w1 = EpmiWeighting()
w2 = PlogWeighting()
for core_s, per_mat, per_row, per_mat_out1, per_mat_out2 in test_cases:
tmp_mat = per_mat.copy()
tmp_core_mat = core_s.cooccurrence_matrix.mat
per_s1 = PeripheralSpace(core_s, DenseMatrix(per_mat), per_row)
np.testing.assert_array_equal(per_s1.cooccurrence_matrix.mat,
tmp_mat)
self.assert_column_identical(per_s1, core_s)
self.assertListEqual(per_s1.id2row, per_row)
self.assertListEqual(per_s1.operations, core_s.operations)
core_s1 = core_s.apply(w1)
per_s2 = PeripheralSpace(core_s1, DenseMatrix(per_mat), per_row)
np.testing.assert_array_almost_equal(
per_s2.cooccurrence_matrix.mat, per_mat_out1)
self.assert_column_identical(per_s2, core_s1)
self.assertListEqual(per_s2.id2row, per_row)
self.assertListEqual(per_s2.operations, core_s1.operations)
self.assertEqual(len(per_s2.operations), 1)
core_s2 = core_s1.apply(w2)
per_s3 = PeripheralSpace(core_s2, DenseMatrix(per_mat), per_row)
np.testing.assert_array_almost_equal(
per_s3.cooccurrence_matrix.mat, per_mat_out2)
self.assert_column_identical(per_s3, core_s2)
self.assertListEqual(per_s3.id2row, per_row)
self.assertListEqual(per_s3.operations, core_s2.operations)
self.assertEqual(len(per_s3.operations), 2)
np.testing.assert_array_equal(tmp_core_mat,
core_s.cooccurrence_matrix.mat)
core_s3 = core_s2
per_s4 = PeripheralSpace(core_s3, DenseMatrix(per_mat), per_row)
np.testing.assert_array_almost_equal(
per_s4.cooccurrence_matrix.mat, per_mat_out2)
self.assert_column_identical(per_s4, core_s2)
self.assertListEqual(per_s4.id2row, per_row)
self.assertListEqual(per_s4.operations, core_s3.operations)
self.assertEqual(len(per_s4.operations), 2)
np.testing.assert_array_equal(tmp_core_mat,
core_s.cooccurrence_matrix.mat)
def test_train_random(self):
test_cases = [1.0, 2.0, 3.0]
rows = 4
cols = 3
m1 = np.random.rand(rows, cols)
m2 = np.random.rand(rows, cols)
for lambda_ in test_cases:
m = Dilation(lambda_)
result_p = m._compose(DenseMatrix(m1), DenseMatrix(m2))
m = Dilation()
m._solve(DenseMatrix(m1), DenseMatrix(m2), result_p)
self.assertAlmostEqual(lambda_, m._lambda)
def test_dense_svd(self):
test_cases = self.svd_test_cases
for x, u_expected, s_expected, v_expected in test_cases:
for dim in [2, 3, 6]:
u, s, v = Linalg.svd(DenseMatrix(x), dim)
np.testing.assert_array_almost_equal(u.mat, u_expected, 2)
np.testing.assert_array_almost_equal(s, s_expected, 2)
np.testing.assert_array_almost_equal(v.mat, v_expected, 2)
u, s, v = Linalg.svd(DenseMatrix(x), 1)
np.testing.assert_array_almost_equal(u.mat, u_expected[:, 0:1], 2)
np.testing.assert_array_almost_equal(s, s_expected[0:1], 2)
np.testing.assert_array_almost_equal(v.mat, v_expected[:, 0:1], 2)
def test_intercept_lstsq_regression(self):
a = DenseMatrix(np.matrix([[1, 1],[2, 3],[4, 6]]))
b = DenseMatrix(np.matrix([[12, 15, 18],[21, 27, 33],[35, 46, 57]]))
res = DenseMatrix(np.matrix([[1, 2, 3],[4, 5, 6],[7, 8, 9]]))
res1 = Linalg.lstsq_regression(a, b)
res2 = Linalg.lstsq_regression(a, b, intercept=True)
np.testing.assert_array_almost_equal(res2.mat[:-1,:], res[0:2,:].mat, 6)
np.testing.assert_array_almost_equal(res2.mat[-1,:], res[2:3,:].mat, 6)
new_a = a.hstack(DenseMatrix(np.ones((a.shape[0], 1))))
self.assertGreater(((a * res1) - b).norm(), ((new_a * res2) - b).norm())
def setUp(self):
self.a = np.array([[1,2,3],[4,0,5]])
self.b = np.array([[0,0,0],[0,0,0]])
self.c = np.array([[0,0],[0,0],[0,0]])
self.d = np.array([[1,0],[0,1]])
self.e = np.array([1,10])
self.f = np.array([1,10,100])
self.matrix_a = DenseMatrix(self.a)
self.matrix_b = DenseMatrix(self.b)
self.matrix_c = DenseMatrix(self.c)
self.matrix_d = DenseMatrix(self.d)
def test_vstack_raises(self):
space3 = Space(DenseMatrix(self.x[0:2,0:1]), ["e","f"], self.ft1[0:1])
space4 = Space(DenseMatrix(self.x[0:2,:]), ["a","f"], self.ft1)
space5 = Space(DenseMatrix(self.x[0:2,:]), ["e","f"], [])
space6 = Space(DenseMatrix(self.x[0:2,:]), ["e","f"], ["f1","f2","f4"])
test_cases = [(self.space2, space3),
(self.space2, space4),
(self.space2, space5),
(self.space2, space6)
]
for space1, space2 in test_cases:
self.assertRaises(ValueError, space1.vstack, space1, space2)
def test_lexical_function(self):
self.m12 = DenseMatrix(np.mat([[3, 1], [9, 2]]))
self.m22 = DenseMatrix(np.mat([[4, 3], [2, 1]]))
self.ph2 = DenseMatrix(np.mat([[18, 11], [24, 7]]))
self.row = ["a", "b"]
self.ft = ["f1", "f2"]
self.space1 = Space(DenseMatrix(self.m12), self.row, self.ft)
self.space2 = Space(DenseMatrix(self.ph2), ["a_a", "a_b"], self.ft)
m = LexicalFunction()
m._MIN_SAMPLES = 1
self.assertRaises(IllegalStateError, m.export, self.prefix + ".lf1")
m.train([("a", "b", "a_b"), ("a", "a", "a_a")], self.space1,
self.space2)
m.export(self.prefix + ".lf2")
def test_full_additive(self):
self.m12 = DenseMatrix(np.mat([[3, 1], [9, 2]]))
self.m22 = DenseMatrix(np.mat([[4, 3], [2, 1]]))
self.ph2 = DenseMatrix(np.mat([[18, 11], [24, 7]]))
self.row = ["a", "b"]
self.ft = ["f1", "f2"]
self.space1 = Space(DenseMatrix(self.m12), self.row, self.ft)
self.space2 = Space(DenseMatrix(self.ph2), ["a_a", "a_b"], self.ft)
m = FullAdditive()
self.assertRaises(IllegalStateError, m.export, self.prefix + ".full1")
m.train([("a", "b", "a_b"), ("a", "a", "a_a")], self.space1,
self.space2)
m.export(self.prefix + ".full2")
def _export(self, filename):
if self._mat_a_t is None or self._mat_b_t is None:
raise IllegalStateError("cannot export an untrained FullAdditive model.")
with open(filename, "w") as output_stream:
output_stream.write("A\n")
output_stream.write(str(DenseMatrix(self._mat_a_t).mat.T))
output_stream.write("\nB\n")
if self._has_intercept:
output_stream.write(str(DenseMatrix(self._mat_b_t[:-1,]).mat.T))
output_stream.write("\nIntercept\n")
output_stream.write(str(DenseMatrix(self._mat_b_t[-1,]).mat.T))
else:
output_stream.write(str(DenseMatrix(self._mat_b_t).mat.T))
def main():
"""
Convert temporal referencing matrix to regular (binned) matrix.
"""
# Get the arguments
args = docopt(
"""Convert temporal referencing matrix to regular (binned) matrix.
Usage:
tr2bin.py (-w | -s) <spacePrefix> <ref> <outPath>
<spacePrefix> = path to pickled space without suffix
<ref> = reference string
<outPath> = output path for result file
Options:
-w, --w2v save in w2v format
-s, --sps save in sparse matrix format
""")
is_w2v = args['--w2v']
is_sps = args['--sps']
spacePrefix = args['<spacePrefix>']
ref = args['<ref>']
outPath = args['<outPath>']
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',
level=logging.INFO)
logging.info(__file__.upper())
start_time = time.time()
# Load spaces
space = load_pkl_files(spacePrefix)
matrix = space.get_cooccurrence_matrix().get_mat()
id2row = space.get_id2row()
id2column = space.get_id2column()
ti = [(spl[0], i) for i, w in enumerate(id2row) for spl in [w.split('_')]
if len(spl) == 1 or (len(spl) == 2 and spl[1] == ref)]
targets, indices = zip(*ti)
new_matrix = matrix[list(indices), :]
# Save the Space objects
if is_w2v:
new_space = Space(DenseMatrix(new_matrix), list(targets), id2column)
save_pkl_files(new_space,
outPath,
save_in_one_file=True,
save_as_w2v=True)
if is_sps:
new_space = Space(SparseMatrix(new_matrix), list(targets), id2column)
save_pkl_files(new_space,
outPath,
save_in_one_file=True,
save_as_w2v=False)
logging.info("--- %s seconds ---" % (time.time() - start_time))
def main():
parser = argparse.ArgumentParser(
description="Converts a vecf file to dissect pkl format.")
parser.add_argument('--input',
'-i',
type=argparse.FileType('r'),
help='Input file')
parser.add_argument('--output',
'-o',
type=argparse.FileType('w'),
help='Output file')
args = parser.parse_args()
header = args.input.readline().rstrip()
vocab_s, dims = map(int, header.split(" "))
vocab = []
# init matrix
matrix = np.zeros((vocab_s, dims), dtype=np.float)
for i, line in enumerate(args.input):
data = line.split()
vector = np.array(map(float, data[1:]))
word = data[0]
vocab.append(word)
matrix[i] = vector
dm = DenseMatrix(matrix)
sp = Space(dm, vocab, [])
pickle.dump(sp, args.output)
args.output.close()
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_mul_raises(self):
test_cases = [(self.matrix_a, self.a),
(self.matrix_a, DenseMatrix(self.a)),
(self.matrix_a, "3")]
for (term1, term2) in test_cases:
self.assertRaises(TypeError, term1.__mul__, term2)
def main():
parser = argparse.ArgumentParser(
'Converts a VW topic output to a COMPOSES pkl file.')
parser.add_argument('--input',
'-i',
type=argparse.FileType('r'),
help='Input file')
parser.add_argument('--docnames',
'-d',
type=argparse.FileType('r'),
help='Docnames file')
parser.add_argument('--output',
'-o',
type=argparse.FileType('w'),
default=sys.stdout,
help='Output file')
args = parser.parse_args()
docnames = [l for l in (l.strip() for l in args.docnames) if l]
matrix = None
for i, line in enumerate(args.input):
line = line.strip()
weights = map(float, line.split(" "))
if matrix is None:
matrix = np.zeros((len(docnames), len(weights)), dtype=np.float)
weights = np.array(weights)
matrix[i] = weights
dm = DenseMatrix(matrix)
sp = Space(dm, docnames, [])
pickle.dump(sp, args.output)
args.output.close()
def setUp(self):
self.a = np.array([[1, 2, 3], [4, 0, 5]])
self.space_s = Space(SparseMatrix(np.mat(self.a)), ["a", "b"],
["f1", "f2", "f3"])
self.space_d = Space(DenseMatrix(np.mat(self.a)), ["a", "b"],
["f1", "f2", "f3"])
def test_nmf(self):
test_cases = [np.mat([[1,2,3],[2,4,6],[4,17,13]], dtype = np.double),
np.mat([[1,0,0]], dtype = np.double)]
for in_mat in test_cases:
red = Nmf(2)
d_mat = DenseMatrix(in_mat)
#wd_init, hd_init = red.random_init(d_mat)
wd_init, hd_init = red.v_col_init(d_mat)
s_mat = SparseMatrix(in_mat)
ws_init = SparseMatrix(wd_init)
hs_init = SparseMatrix(hd_init)
wd_mat, hd_mat = Linalg.nmf(d_mat, wd_init, hd_init)
ws_mat, hs_mat = Linalg.nmf(s_mat, ws_init, hs_init)
#TESTED IT AGAINST MATLAB IMPLEMENTATION - ALL GOOD
#print wd_mat.mat
#print hd_mat.mat
#print ws_mat.mat.todense()
#print hs_mat.mat.todense()
print "V:", in_mat
print "WH:", (ws_mat*hs_mat).mat.todense()
np.testing.assert_array_almost_equal(wd_mat.mat,
ws_mat.mat.todense(), 2)
np.testing.assert_array_almost_equal(hd_mat.mat,
hs_mat.mat.todense(), 2)
def read_mikolov(spacefile):
header = spacefile.readline().rstrip()
vocab_s, dims = map(int, header.split(" "))
vocab = []
# init matrix
matrix = np.zeros((vocab_s, dims), dtype=np.float)
i = 0
while True:
line = spacefile.readline()
if not line:
break
sep = line.find(" ")
if sep == -1:
raise ValueError(
"Couldn't find the vocab/data separation character! Space file corruption?"
)
word = line[:sep]
data = line[sep + 1:]
if len(data) < FLOAT_SIZE * dims + 1:
data += spacefile.read(FLOAT_SIZE * dims + 1 - len(data))
data = data[:-1]
vocab.append(word)
vector = (struct.unpack("%df" % dims, data))
matrix[i] = vector
i += 1
dm = DenseMatrix(matrix)
sp = Space(dm, vocab, [])
return sp
def project(self, matrix_):
"""
Projects a dim. reduction operation.
Args:
matrix_: matrix on which the reduction is projected, of type Matrix
Returns:
the reduced matrix
Uses the transformation matrix stored in the operation object to project
the dimensionality reduction method on a new space, peripheral to the
original one.
"""
if self.__transmat is None:
self._raise_projection_error(self.__dim_reduction)
if self.__dim_reduction.name == "nmf":
matrix_.assert_positive()
if not isinstance(matrix_, type(self.__transmat)):
warn(
"WARNING: peripheral matrix type (dense/sparse) should be the same as the core space matrix type!!"
)
[matrix_, transmat] = resolve_type_conflict([matrix_, self.__transmat],
type(matrix_))
result_mat = matrix_ * transmat
if self.__dim_reduction.name == "nmf":
result_mat.to_non_negative()
return DenseMatrix(result_mat)
def print_cooc_mat_dense_format(matrix_, id2row, file_prefix):
matrix_file = "%s.%s" % (file_prefix, "dm")
with open(matrix_file, 'w') as f:
for i, row in enumerate(id2row):
v = DenseMatrix(matrix_[i]).mat.flat
line = "\t".join([row] + [repr(v[j]) for j in range(len(v))])
f.write("%s\n" % (line))
def to_matrix(matrix_):
"""
Converts an array-like structure to a DenseMatrix/SparseMatrix
"""
if issparse(matrix_):
return SparseMatrix(matrix_)
else:
return DenseMatrix(matrix_)
def test_init_raise(self):
test_cases = [(DenseMatrix(np.array([[1,2],[3,4],[5,6]])),
["car", "man"], ["feat1", "feat2"],
{"man":1, "car":0}, {"feat1":0, "feat2":1}),
(DenseMatrix(np.array([[1,2],[3,4]])),
[], ["feat1", "feat2"],
{"man":1, "car":0}, {"feat1":0, "feat2":1}),
(DenseMatrix(np.array([[1,2],[3,4]])),
["car", "man"], ["feat1", "feat2"],
{}, {"feat1":0, "feat2":1}),
(DenseMatrix(np.array([[1,2],[3,4]])),
["car", "man"], ["feat1"],
{"man":1, "car":0}, {"feat1":0, "feat2":1}),
(DenseMatrix(np.array([[1,2],[3,4]])),
["car", "man"], ["feat1"],
{"man":1, "car":0}, {"feat1":0, "feat2":1}),
(DenseMatrix(np.array([[1,2],[3,4]])),
["car", "man"], ["feat1","feat2"],
{"man":1, "car":0}, {"feat1":0}),
(DenseMatrix(np.array([[1,2],[3,4]])),
["car", "man"], ["feat1","feat2"],
{"man":1, "car":0}, {"feat1":1,"feat2":0})
]
for (m, id2row, id2col, row2id, col2id) in test_cases:
self.assertRaises(ValueError, Space, m, id2row, id2col,
row2id, col2id)
def _dense_svd(matrix_, reduced_dimension):
print "Running dense svd"
u, s, vt = np.linalg.svd(matrix_.mat, False, True)
rank = len(s[s > Linalg._SVD_TOL])
no_cols = min(u.shape[1], reduced_dimension, rank)
u = DenseMatrix(u[:,0:no_cols])
s = s[0:no_cols]
v = DenseMatrix(vt[0:no_cols,:].transpose())
Linalg._check_reduced_dim(matrix_.shape[1], u.shape[1], reduced_dimension)
if not u.is_mostly_positive():
u = -u
v = -v
return u, s, v
def setUp(self):
self.m1 = np.array([[1, 2, 3]])
self.row1 = ["a"]
self.ft1 = ["f1", "f2", "f3"]
self.space1 = Space(DenseMatrix(self.m1), self.row1, self.ft1)
self.m2 = np.array([[4, 2, 6]])
self.row2 = ["b"]
self.row3 = ["a", "b", "c"]
self.x = np.mat([[1, 2, 3], [2, 4, 6], [4, 675, 43]])
self.us = np.mat([[2.19272110e+00, 3.03174768e+00],
[4.38544220e+00, 6.06349536e+00],
[6.76369708e+02, -4.91431927e-02]])
self.us2 = np.mat([[2.19272110e+00], [4.38544220e+00],
[6.76369708e+02]])
self.space2 = Space(DenseMatrix(self.x), self.row3, self.ft1)
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 setUp(self):
self.a = np.array([[1, 2, 3], [4, 0, 5]])
self.b = np.array([[0, 0, 0], [0, 0, 0]])
self.c = np.array([[0, 0], [0, 0], [0, 0]])
self.d = np.array([[1, 0], [0, 1]])
self.e = np.array([1, 10])
self.f = np.array([1, 10, 100])
self.matrix_a = DenseMatrix(self.a)
self.matrix_b = DenseMatrix(self.b)
self.matrix_c = DenseMatrix(self.c)
self.matrix_d = DenseMatrix(self.d)
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 compute_matreps(self,vecspace,matspace,multiply_matrices=False):
'''
This method computes symbolic and numeric matrix representations od a
papfunc node, taking as input a vector space, a matrix space. An optional Boolean argument, if set to True, makes matrices to be multiplied rather than summed when both subconstituents have arity greater than 0.
'''
# for terminal nodes do lexical insertions by calling
#insert_terminal_node_representation
if self.is_terminal():
matrep,temp_numrep=self.insert_terminal_node_representation(vecspace,matspace)
self._matrep = matrep
if temp_numrep[0] == "empty":
numrep = [] #default semantic representation for syntactic elements we ignore
else:
numrep = [temp_numrep[0].transpose()]
dimensionality=(temp_numrep[0].shape[1])
if len(temp_numrep)>1:
# Matrices are "flattened", stored as vectors.
# We reshape each matrix to a normal shape (usually square)
for x in range(1, (len(temp_numrep))):
y = DenseMatrix(temp_numrep[x])
y.reshape((dimensionality,(y.shape[1]/dimensionality)))
numrep.append(y)
self._numrep = numrep
#raise an exception for a non-terminal node without children
elif len(self._children) == 0:
raise ValueError("Non-terminal non-branching node!")
# inherit the value of the single daughter in case of unary branching
if len(self._children) == 1:
self._matrep = self.get_child(0)._matrep
self._numrep = self.get_child(0)._numrep
#apply composition for binary branching nodes
if len(self._children) == 2 and self._matrep == []:
matrep1=self.get_child(0)._matrep
if not matrep1:
raise ValueError("Empty matrix representation for node %s!" %self.get_child(0))
matrep2=self.get_child(1)._matrep
if not matrep2:
raise ValueError("Empty matrix representation for node %s!" %self.get_child(1))
#get the arity of two daughter nodes in order to determine which of
#them is the function and which is the argument
arity1=len(matrep1)-1
arity2=len(matrep2)-1
# first, compute symbolic matrix representation
if arity1-arity2 == 0:
for x in range(0, arity1+1):
self._matrep.append('(' + matrep1[x] + '+' + matrep2[x] + ')')
#left application
if arity1 < arity2 and not re.search('empty$',matrep2[0]) and not re.search('empty$',matrep1[0]):
for x in range(0, arity2):
if x == 0: # compute vector of the mother node
self._matrep.append('(' + matrep2[x] + '+' + matrep2[arity2] + '*' + matrep1[x] + ')')
elif x < len(matrep1): # compute matrices of the mother node
if multiply_matrices: self._matrep.append('(' + matrep2[x] + '*' + matrep1[x] + ')')
else: self._matrep.append('(' + matrep2[x] + '+' + matrep1[x] + ')')
else:
self._matrep.append(matrep2[x])
#right application
if arity1 > arity2 and not re.search('empty$',matrep2[0]) and not re.search('empty$',matrep1[0]):
for x in range(0, arity1):
if x == 0:
self._matrep.append('(' + matrep1[x] + '+' + matrep1[arity1] + '*' + matrep2[x] + ')')
elif x < len(matrep2):
if multiply_matrices: self._matrep.append('(' + matrep1[x] + '*' + matrep2[x] + ')')
else: self._matrep.append('(' + matrep1[x] + '+' + matrep2[x] + ')')
else:
self._matrep.append(matrep1[x])
#if one of the daughters is 'empty' (marked to be ignored), ignore it
if re.search('empty$',matrep1[0]):
self._matrep = matrep2
if re.search('empty$',matrep2[0]):
self._matrep = matrep1
# computing numeric matrix representation of a node from those of
# its two daughters.
# First, get arity of the daughters to establish the directionality
# of function application
numrep1=self.get_child(0)._numrep
numrep2=self.get_child(1)._numrep
if arity1-arity2 == 0 and numrep1 and numrep2:
for x in range(0, arity1+1):
self._numrep.append(numrep1[x].__add__(numrep2[x]))
#left application
if arity1 < arity2 and not numrep1==[] and not numrep2==[]:
for x in range(0, arity2):
# compute the vector
if x == 0:
self._numrep.append(numrep2[x].__add__(numrep2[arity2] * numrep1[x]))
# compute a matrix
elif x < len(numrep1):
if multiply_matrices:
self._numrep.append(numrep2[x] * numrep1[x])
else:
self._numrep.append(numrep1[x].__add__(numrep2[x]))
else:
self._numrep.append(numrep2[x])
#right aplication
if arity1 > arity2 and not numrep1==[] and not numrep2==[]:
for x in range(0, arity1):
if x == 0:
self._numrep.append(numrep1[x].__add__(numrep1[arity1]*numrep2[x]))
elif x < len(numrep2):
if multiply_matrices:
self._numrep.append(numrep2[x] * numrep1[x])
else:
self._numrep.append(numrep1[x].__add__(numrep2[x]))
else:
self._numrep.append(numrep1[x])
# ignore 'empty' elements in composition
if (numrep1 == []):
self._numrep = numrep2
if (numrep2 == []):
self._numrep = numrep1
# end of numrep computation
# Raise an exception for non-binary branching - we don't want to handle those structures
if len(self._children)>2:
raise ValueError("Matrix representations are not defined for trees with more than binary branching")
def train(self, matrix_a, matrix_b=None):
"""
matrix_b is ignored
"""
W = DenseMatrix.identity(matrix_a.shape[1])
return W
class TestDenseMatrix(unittest.TestCase):
def setUp(self):
self.a = np.array([[1, 2, 3], [4, 0, 5]])
self.b = np.array([[0, 0, 0], [0, 0, 0]])
self.c = np.array([[0, 0], [0, 0], [0, 0]])
self.d = np.array([[1, 0], [0, 1]])
self.e = np.array([1, 10])
self.f = np.array([1, 10, 100])
self.matrix_a = DenseMatrix(self.a)
self.matrix_b = DenseMatrix(self.b)
self.matrix_c = DenseMatrix(self.c)
self.matrix_d = DenseMatrix(self.d)
def tearDown(self):
pass
def test_init(self):
nparr = self.a
test_cases = [nparr, np.mat(nparr), csr_matrix(nparr), csc_matrix(nparr), SparseMatrix(nparr)]
for inmat in test_cases:
outmat = DenseMatrix(inmat)
self.assertIsInstance(outmat.mat, np.matrix)
numpy.testing.assert_array_equal(nparr, np.array(outmat.mat))
def test_add(self):
test_cases = [
(self.matrix_a, self.matrix_a, np.mat([[2, 4, 6], [8, 0, 10]])),
(self.matrix_a, self.matrix_b, self.matrix_a.mat),
]
for (term1, term2, expected) in test_cases:
sum_ = term1 + term2
numpy.testing.assert_array_equal(sum_.mat, expected)
self.assertIsInstance(sum_, type(term1))
def test_add_raises(self):
test_cases = [(self.matrix_a, self.a), (self.matrix_a, SparseMatrix(self.a))]
for (term1, term2) in test_cases:
self.assertRaises(TypeError, term1.__add__, term2)
def test_div(self):
test_cases = [
(self.matrix_a, 2, np.mat([[0.5, 1.0, 1.5], [2.0, 0.0, 2.5]])),
(self.matrix_c, 2, np.mat(self.c)),
]
for (term1, term2, expected) in test_cases:
sum_ = term1 / term2
numpy.testing.assert_array_equal(sum_.mat, expected)
self.assertIsInstance(sum_, DenseMatrix)
def test_div_raises(self):
test_cases = [
(self.matrix_a, self.a, TypeError),
(self.matrix_a, SparseMatrix(self.a), TypeError),
(self.matrix_a, "3", TypeError),
(self.matrix_a, 0, ZeroDivisionError),
]
for (term1, term2, error_type) in test_cases:
self.assertRaises(error_type, term1.__div__, term2)
def test_mul(self):
test_cases = [
(self.matrix_a, self.matrix_c, np.mat([[0, 0], [0, 0]])),
(self.matrix_d, self.matrix_a, self.matrix_a.mat),
(self.matrix_a, 2, np.mat([[2, 4, 6], [8, 0, 10]])),
(2, self.matrix_a, np.mat([[2, 4, 6], [8, 0, 10]])),
(self.matrix_a, np.int64(2), np.mat([[2, 4, 6], [8, 0, 10]])),
(np.int64(2), self.matrix_a, np.mat([[2, 4, 6], [8, 0, 10]])),
]
for (term1, term2, expected) in test_cases:
sum_ = term1 * term2
numpy.testing.assert_array_equal(sum_.mat, expected)
self.assertIsInstance(sum_, DenseMatrix)
def test_mul_raises(self):
test_cases = [
(self.matrix_a, self.a),
(self.matrix_a, SparseMatrix(self.a)),
(self.matrix_a, "3"),
("3", self.matrix_a),
]
for (term1, term2) in test_cases:
self.assertRaises(TypeError, term1.__mul__, term2)
def test_multiply(self):
test_cases = [
(self.matrix_a, self.matrix_a, np.mat([[1, 4, 9], [16, 0, 25]])),
(self.matrix_a, self.matrix_b, np.mat(self.b)),
]
for (term1, term2, expected) in test_cases:
mult1 = term1.multiply(term2)
mult2 = term2.multiply(term1)
numpy.testing.assert_array_equal(mult1.mat, expected)
numpy.testing.assert_array_equal(mult2.mat, expected)
self.assertIsInstance(mult1, DenseMatrix)
self.assertIsInstance(mult2, DenseMatrix)
def test_multiply_raises(self):
test_cases = [
(self.matrix_a, self.matrix_d, ValueError),
(self.matrix_a, self.a, TypeError),
(self.matrix_a, SparseMatrix(self.a), TypeError),
]
for (term1, term2, error_type) in test_cases:
self.assertRaises(error_type, term1.multiply, term2)
def test_scale_rows(self):
outcome = np.mat([[1, 2, 3], [40, 0, 50]])
test_cases = [(self.matrix_a, self.e, outcome), (self.matrix_a, np.mat(self.e).T, outcome)]
for (term1, term2, expected) in test_cases:
term1 = term1.scale_rows(term2)
numpy.testing.assert_array_equal(term1.mat, expected)
def test_scale_columns(self):
test_cases = [(self.matrix_a, self.f, np.mat([[1, 20, 300], [4, 0, 500]]))]
for (term1, term2, expected) in test_cases:
term1 = term1.scale_columns(term2)
numpy.testing.assert_array_equal(term1.mat, expected)
def test_scale_raises(self):
test_cases = [
(self.matrix_a, self.f, ValueError, self.matrix_a.scale_rows),
(self.matrix_a, self.e, ValueError, self.matrix_a.scale_columns),
(self.matrix_a, self.b, ValueError, self.matrix_a.scale_rows),
(self.matrix_a, self.b, ValueError, self.matrix_a.scale_columns),
(self.matrix_a, "3", TypeError, self.matrix_a.scale_rows),
]
for (term1, term2, error_type, function) in test_cases:
self.assertRaises(error_type, function, term2)
def test_plog(self):
m = DenseMatrix(np.mat([[0.5, 1.0, 1.5], [2.0, 0.0, 2.5]]))
m_expected = np.mat([[0.0, 0.0, 0.4054], [0.6931, 0.0, 0.9162]])
a_expected = np.mat([[0.0, 0.6931, 1.0986], [1.3862, 0.0, 1.6094]])
test_cases = [(self.matrix_a.copy(), a_expected), (m, m_expected)]
for (term, expected) in test_cases:
term.plog()
numpy.testing.assert_array_almost_equal(term.mat, expected, 3)
def test_3d(self):
# setting up
v_mat = DenseMatrix(np.mat([[0,0,1,1,2,2,3,3],#hate
[0,1,2,4,5,6,8,9]])) #love
vo11_mat = DenseMatrix(np.mat([[0,11],[22,33]])) #hate boy
vo12_mat = DenseMatrix(np.mat([[0,7],[14,21]])) #hate man
vo21_mat = DenseMatrix(np.mat([[6,34],[61,94]])) #love boy
vo22_mat = DenseMatrix(np.mat([[2,10],[17,26]])) #love car
train_vo_data = [("hate_boy", "man", "man_hate_boy"),
("hate_man", "man", "man_hate_man"),
("hate_boy", "boy", "boy_hate_boy"),
("hate_man", "boy", "boy_hate_man"),
("love_car", "boy", "boy_love_car"),
("love_boy", "man", "man_love_boy"),
("love_boy", "boy", "boy_love_boy"),
("love_car", "man", "man_love_car")
]
# if do not find a phrase
# what to do?
train_v_data = [("love", "boy", "love_boy"),
("hate", "man", "hate_man"),
("hate", "boy", "hate_boy"),
("love", "car", "love_car")]
sentences = ["man_hate_boy", "car_hate_boy", "boy_hate_boy",
"man_hate_man", "car_hate_man", "boy_hate_man",
"man_love_boy", "car_love_boy", "boy_love_boy",
"man_love_car", "car_love_car", "boy_love_car" ]
n_mat = DenseMatrix(np.mat([[3,4],[1,2],[5,6]]))
n_space = Space(n_mat, ["man", "car", "boy"], self.ft)
s1_mat = (vo11_mat * n_mat.transpose()).transpose()
s2_mat = (vo12_mat * n_mat.transpose()).transpose()
s3_mat = (vo21_mat * n_mat.transpose()).transpose()
s4_mat = (vo22_mat * n_mat.transpose()).transpose()
s_mat = vo11_mat.nary_vstack([s1_mat,s2_mat,s3_mat,s4_mat])
s_space = Space(s_mat, sentences, self.ft)
#test train 2d
model = LexicalFunction(learner=LstsqRegressionLearner(intercept=False))
model._MIN_SAMPLES = 1
model.train(train_vo_data, n_space, s_space)
vo_space = model.function_space
self.assertListEqual(vo_space.id2row, ["hate_boy", "hate_man","love_boy", "love_car"])
self.assertTupleEqual(vo_space.element_shape, (2,2))
vo11_mat.reshape((1,4))
np.testing.assert_array_almost_equal(vo11_mat.mat,
vo_space.cooccurrence_matrix.mat[0])
vo12_mat.reshape((1,4))
np.testing.assert_array_almost_equal(vo12_mat.mat,
vo_space.cooccurrence_matrix.mat[1])
vo21_mat.reshape((1,4))
np.testing.assert_array_almost_equal(vo21_mat.mat,
vo_space.cooccurrence_matrix.mat[2])
vo22_mat.reshape((1,4))
np.testing.assert_array_almost_equal(vo22_mat.mat,
vo_space.cooccurrence_matrix.mat[3])
# test train 3d
model2 = LexicalFunction(learner=LstsqRegressionLearner(intercept=False))
model2._MIN_SAMPLES = 1
model2.train(train_v_data, n_space, vo_space)
v_space = model2.function_space
np.testing.assert_array_almost_equal(v_mat.mat,
v_space.cooccurrence_matrix.mat)
self.assertListEqual(v_space.id2row, ["hate","love"])
self.assertTupleEqual(v_space.element_shape, (2,2,2))
# test compose 3d
vo_space2 = model2.compose(train_v_data, n_space)
id2row1 = list(vo_space.id2row)
id2row2 = list(vo_space2.id2row)
id2row2.sort()
self.assertListEqual(id2row1, id2row2)
row_list = vo_space.id2row
vo_rows1 = vo_space.get_rows(row_list)
vo_rows2 = vo_space2.get_rows(row_list)
np.testing.assert_array_almost_equal(vo_rows1.mat, vo_rows2.mat,7)
self.assertTupleEqual(vo_space.element_shape, vo_space2.element_shape)
def compute_matreps(self,vecspace,matspace,multiply_matrices=False):
'''
This method computes symbolic and numeric matrix representations od a
papfunc node, taking as input a vector space, a matrix space. An optional Boolean argument, if set to True, makes matrices to be multiplied rather than summed when both subconstituents have arity greater than 0.
'''
# for terminal nodes call insert_terminal_node_representation
if self.is_terminal():
matrep,temp_numrep=self.insert_terminal_node_representation(vecspace,matspace)
self._matrep = matrep
if temp_numrep[0] == "empty":
numrep = []
else:
numrep = [temp_numrep[0].transpose()]
dimensionality=(temp_numrep[0].shape[1])
if len(temp_numrep)>1:
# all matrices are stored flattened, as long vectors. We need to
# reshape them before we use them in computations
for x in range(1, (len(temp_numrep))):
y = DenseMatrix(temp_numrep[x])
y.reshape((dimensionality,(y.shape[1]/dimensionality)))
numrep.append(y)
self._numrep = numrep
#raise an exception for a non-terminal node without children
elif len(self._children) == 0:
raise ValueError("Non-terminal non-branching node!")
# inherit the value of the single daughter in case of unary branching
if len(self._children) == 1:
self._matrep = self.get_child(0)._matrep
self._numrep = self.get_child(0)._numrep
#apply composition for binary branching nodes
if len(self._children) == 2 and self._matrep == []:
matrep1=self.get_child(0)._matrep
#ignore 'empty' nodes
if not matrep1:
raise ValueError("Empty matrix representation for node %s!" %self.get_child(0))
matrep2=self.get_child(1)._matrep
if not matrep2:
raise ValueError("Empty matrix representation for node %s!" %self.get_child(1))
arity1=len(matrep1)-1
arity2=len(matrep2)-1
# first, compute symbolic matrix representation
# default to componentwise addition for daughters of equal arity
if arity1-arity2 == 0:
for x in range(0, arity1+1):
self._matrep.append('(' + matrep1[x] + '+' + matrep2[x] + ')')
# left function application
if arity1 < arity2 and not re.search('empty$',matrep2[0]) and not re.search('empty$',matrep1[0]):
for x in range(0, arity2):
if x == 0: #compute the vector
self._matrep.append('(' + matrep2[x] + '+' + matrep2[arity2] + '*' + matrep1[x] + ')')
# compute a matrix
# If both daughters have matrices in the xth position in
# their vector-matrix structures, add or multiply those
# matrices according to the multiply_matrices parameter
elif x < len(matrep1):
if multiply_matrices: self._matrep.append('(' + matrep2[x] + '*' + matrep1[x] + ')')
else: self._matrep.append('(' + matrep2[x] + '+' + matrep1[x] + ')')
# inherit the function's extra lexical matrix
else:
self._matrep.append(matrep2[x])
# right function application
if arity1 > arity2 and not re.search('empty$',matrep2[0]) and not re.search('empty$',matrep1[0]):
for x in range(0, arity1):
if x == 0:
self._matrep.append('(' + matrep1[x] + '+' + matrep1[arity1] + '*' + matrep2[x] + ')')
# compute a matrix
# If both daughters have matrices in the xth position in
# their vector-matrix structures, add or multiply those
# matrices according to the multiply_matrices parameter
elif x < len(matrep2):
if multiply_matrices: self._matrep.append('(' + matrep1[x] + '*' + matrep2[x] + ')')
else: self._matrep.append('(' + matrep1[x] + '+' + matrep2[x] + ')')
else:
self._matrep.append(matrep1[x])
# ignore 'empty' elements
if re.search('empty$',matrep1[0]):
self._matrep = matrep2
if re.search('empty$',matrep2[0]):
self._matrep = matrep1
# computing numeric matrix representation of a node from those of its two daughters
numrep1=self.get_child(0)._numrep
numrep2=self.get_child(1)._numrep
if arity1-arity2 == 0 and numrep1 and numrep2:
for x in range(0, arity1+1):
self._numrep.append(numrep1[x].__add__(numrep2[x]))
# left function application
if arity1 < arity2 and not numrep1==[] and not numrep2==[]:
for x in range(0, arity2):
if x == 0: #compute the vector
self._numrep.append(numrep2[x].__add__(numrep2[arity2] * padd_matrix(numrep1[x],0)))
elif x < len(numrep1):
if multiply_matrices:
self._numrep.append(numrep2[x] * numrep1[x])
else:
self._numrep.append(numrep1[x].__add__(numrep2[x]))
else:
self._numrep.append(numrep2[x])
# right function application
if arity1 > arity2 and not numrep1==[] and not numrep2==[]:
for x in range(0, arity1):
if x == 0: # compute the vector
self._numrep.append(numrep1[x].__add__(numrep1[arity1] * padd_matrix(numrep2[x],0)))
elif x < len(numrep2):
if multiply_matrices:
self._numrep.append(numrep2[x] * numrep1[x])
else:
self._numrep.append(numrep1[x].__add__(numrep2[x]))
else:
self._numrep.append(numrep1[x])
# ignore 'empty' elements
if (numrep1 == []):
self._numrep = numrep2
if (numrep2 == []):
self._numrep = numrep1
# end of numrep computation
# Raise an exception for non-binary branching - we don't want to handle those structures
if len(self._children)>2:
raise ValueError("Matrix representations are not defined for trees with more than binary branching")
def tracenorm_regression(matrix_a , matrix_b, lmbd, iterations, intercept=False):
#log.print_info(logger, "In Tracenorm regression..", 4)
#log.print_matrix_info(logger, matrix_a, 5, "Input matrix A:")
#log.print_matrix_info(logger, matrix_b, 5, "Input matrix B:")
"""
Performs Trace Norm Regression.
This method uses approximate gradient descent
to solve the problem:
:math:`X = argmin(||AX - B||_2 + \\lambda||X||_*)`
where :math:`||X||_*` is the trace norm of :math:`X`, the sum of its
singular values.
It is implemented for dense matrices only.
The algorithm is the Extended Gradient Algorithm from (Ji and Ye, 2009).
Args:
matrix_a: input matrix A, of type Matrix
matrix_b: input matrix A, of type Matrix. If None, it is defined as matrix_a
lambda_: scalar, lambda parameter
intercept: bool. If True intercept is used. Optional, default False.
Returns:
solution X of type Matrix
"""
if intercept:
matrix_a = matrix_a.hstack(matrix_type(np.ones((matrix_a.shape[0],
1))))
if matrix_b == None:
matrix_b = matrix_a
# TODO remove this
matrix_a = DenseMatrix(matrix_a).mat
matrix_b = DenseMatrix(matrix_b).mat
# Matrix shapes
p = matrix_a.shape[0]
q = matrix_a.shape[1]
assert_same_shape(matrix_a, matrix_b, 0)
# Initialization of the algorithm
W = (1.0/p)* Linalg._kronecker_product(matrix_a)
# Sub-expressions reused at various places in the code
matrix_a_t = matrix_a.transpose()
at_times_a = np.dot(matrix_a_t, matrix_a)
# Epsilon: to ensure that our bound on the Lipschitz constant is large enough
epsilon_lbound = 0.05
# Expression of the bound of the Lipschitz constant of the cost function
L_bound = (1+epsilon_lbound)*2*Linalg._frobenius_norm_squared(at_times_a)
# Current "guess" of the local Lipschitz constant
L = 1.0
# Factor by which L should be increased when it happens to be too small
gamma = 1.2
# Epsilon to ensure that mu is increased when the inequality hold tightly
epsilon_cost = 0.00001
# Real lambda: resized according to the number of training samples (?)
lambda_ = lmbd*p
# Variables used for the accelerated algorithm (check the original paper)
Z = W
alpha = 1.0
# Halting condition
epsilon = 0.00001
last_cost = 1
current_cost = -1
linalg_error_caught = False
costs = []
iter_counter = 0
while iter_counter < iterations and (abs((current_cost - last_cost)/last_cost)>epsilon) and not linalg_error_caught:
sys.stdout.flush()
# Cost tracking
try:
next_W, tracenorm = Linalg._next_tracenorm_guess(matrix_a, matrix_b, lambda_, L, Z, at_times_a)
except LinAlgError:
print "LinAlgError caught in trace norm regression"
linalg_error_caught = True
break
last_cost = current_cost
current_fitness = Linalg._fitness(matrix_a, matrix_b, next_W)
current_cost = current_fitness + lambda_ * tracenorm
if iter_counter > 0: # The first scores are messy
cost_list = [L, L_bound, current_fitness, current_cost]
costs.append(cost_list)
while (current_fitness + epsilon_cost >=
Linalg._intermediate_cost(matrix_a, matrix_b, next_W, Z, L)):
if L > L_bound:
print "Trace Norm Regression: numerical error detected at iteration "+str(iter_counter)
break
L = gamma * L
try:
next_W, tracenorm = Linalg._next_tracenorm_guess(matrix_a, matrix_b, lambda_, L, Z, at_times_a)
except LinAlgError:
print "LinAlgError caught in trace norm regression"
linalg_error_caught = True
break
last_cost = current_cost
current_fitness = Linalg._fitness(matrix_a, matrix_a, next_W)
current_cost = current_fitness + lambda_*tracenorm
if linalg_error_caught:
break
previous_W = W
W = next_W
previous_alpha = alpha
alpha = (1.0 + sqrt(1.0 + 4.0*alpha*alpha))/2.0
Z = W
# Z = W + ((alpha - 1)/alpha)*(W - previous_W)
iter_counter += 1
sys.stdout.flush()
W = np.real(W)
return DenseMatrix(W), costs