def test_save_load(self):
with tempfile.NamedTemporaryFile(mode="r") as fid:
gtn.savetxt(fid.name, self.g)
loaded = gtn.loadtxt(fid.name)
self.assertTrue(gtn.isomorphic(self.g, loaded))
with tempfile.NamedTemporaryFile(mode="r") as fid:
gtn.save(fid.name, self.g)
loaded = gtn.load(fid.name)
self.assertTrue(gtn.isomorphic(self.g, loaded))
def test_transitions(self):
num_tokens = 4
# unigram
transitions = make_transitions_graph(1, num_tokens)
expected = gtn.Graph()
expected.add_node(True, True)
for i in range(num_tokens):
expected.add_arc(0, 0, i)
self.assertTrue(gtn.isomorphic(transitions, expected))
# bigram
transitions = make_transitions_graph(2, num_tokens)
expected = gtn.Graph()
expected.add_node(True, False)
for i in range(num_tokens):
expected.add_node(False, False)
expected.add_arc(0, i + 1, i)
for i in range(num_tokens):
for j in range(num_tokens):
expected.add_arc(i + 1, j + 1, j)
expected.add_node(False, True)
for i in range(num_tokens + 1):
expected.add_arc(i, num_tokens + 1, gtn.epsilon)
self.assertTrue(gtn.isomorphic(transitions, expected))
# trigram
transitions = make_transitions_graph(3, num_tokens)
expected = gtn.Graph()
expected.add_node(True, False)
for i in range(num_tokens):
expected.add_node(False, False)
expected.add_arc(0, i + 1, i)
for i in range(num_tokens):
for j in range(num_tokens):
expected.add_node(False, False)
expected.add_arc(i + 1, num_tokens * i + j + num_tokens + 1, j)
for i in range(num_tokens):
for j in range(num_tokens):
for k in range(num_tokens):
expected.add_arc(
num_tokens * i + j + num_tokens + 1,
num_tokens * j + k + num_tokens + 1,
k,
)
end_idx = expected.add_node(False, True)
self.assertEqual(end_idx, num_tokens * num_tokens + num_tokens + 1)
for i in range(end_idx):
expected.add_arc(i, end_idx, gtn.epsilon)
self.assertTrue(gtn.isomorphic(transitions, expected))
def test_sum(self):
# Empty graph
self.assertTrue(gtn.equal(gtn.union([]), gtn.Graph()))
# Check single graph is a no-op
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node(False, True)
g1.add_arc(0, 1, 1)
self.assertTrue(gtn.equal(gtn.union([g1]), g1))
# Simple union
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node(False, True)
g1.add_arc(0, 1, 1)
g2 = gtn.Graph()
g2.add_node(True)
g2.add_node(False, True)
g2.add_arc(0, 1, 0)
expected = gtn.Graph()
expected.add_node(True)
expected.add_node(True)
expected.add_node(False, True)
expected.add_node(False, True)
expected.add_arc(0, 2, 1)
expected.add_arc(1, 3, 0)
self.assertTrue(gtn.isomorphic(gtn.union([g1, g2]), expected))
# Check adding with an empty graph works
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node(False, True)
g1.add_arc(0, 1, 1)
g2 = gtn.Graph()
g3 = gtn.Graph()
g3.add_node(True, True)
g3.add_arc(0, 0, 2)
expected = gtn.Graph()
expected.add_node(True)
expected.add_node(False, True)
expected.add_node(True, True)
expected.add_arc(0, 1, 1)
expected.add_arc(2, 2, 2)
self.assertTrue(gtn.isomorphic(gtn.union([g1, g2, g3]), expected))
def test_loadsave(self):
_, tmpfile = tempfile.mkstemp()
g = gtn.Graph()
gtn.save(tmpfile, g)
g2 = gtn.load(tmpfile)
self.assertTrue(gtn.equal(g, g2))
g = gtn.Graph()
g.add_node(True)
g.add_node(True)
g.add_node()
g.add_node()
g.add_node(False, True)
g.add_node(False, True)
g.add_arc(0, 1, 0, 1, 1.1)
g.add_arc(1, 2, 1, 2, 2.1)
g.add_arc(2, 3, 2, 3, 3.1)
g.add_arc(3, 4, 3, 4, 4.1)
g.add_arc(4, 5, 4, gtn.epsilon, 5.1)
gtn.save(tmpfile, g)
g2 = gtn.load(tmpfile)
self.assertTrue(gtn.equal(g, g2))
self.assertTrue(gtn.isomorphic(g, g2))
def test_comparisons(self):
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node(False, True)
g1.add_arc(0, 1, 0)
g2 = gtn.Graph()
g2.add_node(True)
g2.add_node(False, True)
g2.add_arc(0, 1, 0)
self.assertTrue(gtn.equal(g1, g2))
self.assertTrue(gtn.isomorphic(g1, g2))
g2 = gtn.Graph()
g2.add_node(False, True)
g2.add_node(True)
g2.add_arc(1, 0, 0)
self.assertFalse(gtn.equal(g1, g2))
self.assertTrue(gtn.isomorphic(g1, g2))
def test_loadtxt(self):
g1 = gtn.Graph()
g1.add_node(True, True)
g1.add_node(False, True)
g1.add_node()
g1.add_arc(0, 0, 1)
g1.add_arc(0, 2, 1, 1, 1.1)
g1.add_arc(2, 1, 2, 2, 2.1)
g_str = ["0", "0 1", "0 0 1 1 0", "0 2 1 1 1.1", "2 1 2 2 2.1"]
g2 = create_graph_from_text(g_str)
self.assertTrue(gtn.equal(g1, g2))
self.assertTrue(gtn.isomorphic(g1, g2))
_, tmpfile = tempfile.mkstemp()
# Write the test file
gtn.savetxt(tmpfile, g2)
g3 = gtn.loadtxt(tmpfile)
self.assertTrue(gtn.equal(g1, g3))
# Empty graph doesn't load
g_str = [""]
self.assertRaises(ValueError, create_graph_from_text, g_str)
# Graph without accept nodes doesn't load
g_str = ["1"]
self.assertRaises(ValueError, create_graph_from_text, g_str)
# Graph with repeat start nodes doesn't load
g_str = ["1 0 0", "0 1"]
self.assertRaises(ValueError, create_graph_from_text, g_str)
# Graph loads if the start and accept nodes are specified
g_str = ["0", "1"]
g = gtn.Graph()
g.add_node(True)
g.add_node(False, True)
self.assertTrue(gtn.equal(g, create_graph_from_text(g_str)))
# Graph doesn't load if arc incorrect
g_str = ["0", "1", "0 2"]
self.assertRaises(ValueError, create_graph_from_text, g_str)
g_str = ["0", "1", "0 1 2 3 4 5"]
self.assertRaises(ValueError, create_graph_from_text, g_str)
# Transducer loads
g1 = gtn.Graph()
g1.add_node(True, True)
g1.add_node(False, True)
g1.add_node()
g1.add_arc(0, 0, 1, 1)
g1.add_arc(0, 2, 1, 2, 1.1)
g1.add_arc(2, 1, 2, 3, 2.1)
g_str = ["0", "0 1", "0 0 1", "0 2 1 2 1.1", "2 1 2 3 2.1"]
g2 = create_graph_from_text(g_str)
self.assertTrue(gtn.equal(g1, g2))
self.assertTrue(gtn.isomorphic(g1, g2))
def test_isomorphic(self):
g1 = gtn.Graph()
g1.add_node(True)
g2 = gtn.Graph()
g2.add_node(True)
self.assertTrue(gtn.isomorphic(g1, g2))
g1 = gtn.Graph()
g1.add_node(True)
g2 = gtn.Graph()
g2.add_node(True, True)
self.assertFalse(gtn.isomorphic(g1, g2))
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node(False, True)
g1.add_arc(0, 1, 0, 0, 1)
g2 = gtn.Graph()
g2.add_node(True)
g2.add_node(False, True)
g2.add_arc(0, 1, 0, 0, 1)
self.assertTrue(gtn.isomorphic(g1, g2))
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node(False, True)
g1.add_arc(0, 1, 0, 0, 1)
g2 = gtn.Graph()
g2.add_node(True)
g2.add_node(False, True)
g2.add_arc(0, 1, 0, 0, 1)
g2.add_arc(0, 1, 0, 0, 1)
self.assertFalse(gtn.isomorphic(g1, g2))
# Graph with loops
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node()
g1.add_node(False, True)
g1.add_arc(0, 2, 0)
g1.add_arc(0, 1, 0)
g1.add_arc(1, 1, 3)
g1.add_arc(2, 1, 3)
g2 = gtn.Graph()
g2.add_node(True)
g2.add_node(False, True)
g2.add_node()
g2.add_arc(0, 1, 0)
g2.add_arc(1, 2, 3)
g2.add_arc(0, 2, 0)
g2.add_arc(2, 2, 3)
self.assertTrue(gtn.isomorphic(g1, g2))
# Repeat arcs
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node(False, True)
g1.add_arc(0, 1, 1, 1, 3.1)
g1.add_arc(0, 1, 1, 1, 3.1)
g1.add_arc(0, 1, 1, 1, 4.1)
g2 = gtn.Graph()
g2.add_node(True)
g2.add_node(False, True)
g2.add_arc(0, 1, 1, 1, 3.1)
g2.add_arc(0, 1, 1, 1, 4.1)
g2.add_arc(0, 1, 1, 1, 4.1)
self.assertFalse(gtn.isomorphic(g1, g2))
# Transducer with different outputs
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node(False, True)
g1.add_arc(0, 1, 0, 1, 2.1)
g1.add_arc(1, 1, 1, 3, 4.1)
g2 = gtn.Graph()
g2.add_node(True)
g2.add_node(False, True)
g2.add_arc(0, 1, 0, 1, 2.1)
g2.add_arc(1, 1, 1, 4, 4.1)
self.assertFalse(gtn.isomorphic(g1, g2))
def test_graph_build(self):
# unigram test case
graph = build_graph([[(0, ), (1, )]])
expected = gtn.Graph()
expected.add_node(True, True)
expected.add_arc(0, 0, 0)
expected.add_arc(0, 0, 1)
self.assertTrue(gtn.isomorphic(graph, expected))
# bigram test cases
# fmt: off
ngrams = [
[(0, )], # unigrams
[(-1, 0), (-1, 1), (0, 1), (1, 0), (1, 1)] # bigrams
]
# fmt: on
with self.assertRaises(ValueError):
build_graph(ngrams)
# fmt: off
# text = ["ab, "ba", "bb"]
ngrams = [
[(0, ), (1, ), (-2, )], # unigrams
[(-1, 0), (-1, 1), (0, 1), (1, 0), (1, 1), (0, -2),
(1, -2)] # bigrams
]
# fmt: on
graph = build_graph(ngrams)
expected = gtn.Graph()
expected.add_node(True, False) # <s>
expected.add_node(False, False) # 0
expected.add_node(False, False) # 1
expected.add_node(False, False) # back-off
expected.add_node(False, True) # </s>
expected.add_arc(0, 1, 0)
expected.add_arc(1, 2, 1)
expected.add_arc(0, 2, 1)
expected.add_arc(2, 1, 0)
expected.add_arc(2, 2, 1)
expected.add_arc(0, 3, gtn.epsilon)
expected.add_arc(1, 3, gtn.epsilon)
expected.add_arc(2, 3, gtn.epsilon)
expected.add_arc(3, 1, 0)
expected.add_arc(3, 2, 1)
expected.add_arc(3, 4, gtn.epsilon)
expected.add_arc(1, 4, gtn.epsilon)
expected.add_arc(2, 4, gtn.epsilon)
self.assertTrue(gtn.isomorphic(expected, graph))
# bigram test case with empty string
ngrams = [
[(0, ), (-2, )],
[(-1, 0), (0, 0), (0, -2), (-1, -2)],
] # unigrams # bigrams
graph = build_graph(ngrams)
expected = gtn.Graph()
expected.add_node(True, False) # (<s>)
expected.add_node(False, False) # (a)
expected.add_node(False, False) # (back-off)
expected.add_node(False, True) # (</s>)
expected.add_arc(2, 1, 0) # p(a)
expected.add_arc(2, 3, gtn.epsilon) # p(</s>)
expected.add_arc(1, 1, 0) # p(a/a)
expected.add_arc(0, 1, 0) # p(a/<s>)
expected.add_arc(1, 3, gtn.epsilon) # p(</s>/a)
expected.add_arc(0, 3, gtn.epsilon) # p(</s>/<s>)
expected.add_arc(0, 2, gtn.epsilon)
expected.add_arc(1, 2, gtn.epsilon)
self.assertTrue(gtn.isomorphic(expected, graph))
# trigram test case
# fmt: off
ngrams = [
[(0, ), (1, ), (-2, )], # unigrams
[(-1, 0), (0, 1), (1, 1), (1, -2)], # bigrams
[(-1, 0, 1), (0, 1, 1), (1, 1, 1), (1, 1, -2)], # trigrams
]
# fmt: on
graph = build_graph(ngrams)
expected = gtn.Graph()
expected.add_node(True, False) # (<s>)
expected.add_node(False, False) # unigram back-off
expected.add_node(False, False) # 0
expected.add_node(False, False) # 1
expected.add_node(False, False) # (<s>, 0)
expected.add_node(False, False) # (0, 1)
expected.add_node(False, False) # (1, 1)
expected.add_node(False, True) # </s>
# unigram arcs
expected.add_arc(1, 2, 0)
expected.add_arc(1, 3, 1)
expected.add_arc(1, 7, gtn.epsilon)
# bigram arcs
expected.add_arc(0, 4, 0)
expected.add_arc(2, 5, 1)
expected.add_arc(3, 6, 1)
expected.add_arc(3, 7, gtn.epsilon)
# trigram arcs
expected.add_arc(4, 5, 1)
expected.add_arc(5, 6, 1)
expected.add_arc(6, 6, 1)
expected.add_arc(6, 7, gtn.epsilon)
# back-off to bigram
expected.add_arc(4, 2, gtn.epsilon)
expected.add_arc(5, 3, gtn.epsilon)
expected.add_arc(6, 3, gtn.epsilon)
# back-off to unigram
expected.add_arc(0, 1, gtn.epsilon)
expected.add_arc(2, 1, gtn.epsilon)
expected.add_arc(3, 1, gtn.epsilon)
self.assertTrue(gtn.isomorphic(expected, graph))
def test_composition(self):
# Compos,ing with an empty graph gives an empty graph
g1 = gtn.Graph()
g2 = gtn.Graph()
self.assertTrue(gtn.equal(gtn.compose(g1, g2), gtn.Graph()))
g1.add_node(True)
g1.add_node()
g1.add_arc(0, 1, 0)
g2.add_node(True)
g2.add_node(False, True)
g2.add_arc(0, 1, 0)
g2.add_arc(0, 1, 0)
self.assertTrue(gtn.equal(gtn.compose(g1, g2), gtn.Graph()))
self.assertTrue(gtn.equal(gtn.compose(g2, g1), gtn.Graph()))
self.assertTrue(gtn.equal(gtn.intersect(g2, g1), gtn.Graph()))
# Check singly sorted version
g1.arc_sort(True)
self.assertTrue(gtn.equal(gtn.compose(g1, g2), gtn.Graph()))
# Check doubly sorted version
g2.arc_sort()
self.assertTrue(gtn.equal(gtn.compose(g1, g2), gtn.Graph()))
# Self-loop in the composed graph
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node(False, True)
g1.add_arc(0, 0, 0)
g1.add_arc(0, 1, 1)
g1.add_arc(1, 1, 2)
g2 = gtn.Graph()
g2.add_node(True)
g2.add_node()
g2.add_node(False, True)
g2.add_arc(0, 1, 0)
g2.add_arc(1, 1, 0)
g2.add_arc(1, 2, 1)
g_str = ["0", "2", "0 1 0", "1 1 0", "1 2 1"]
expected = create_graph_from_text(g_str)
self.assertTrue(gtn.isomorphic(gtn.compose(g1, g2), expected))
self.assertTrue(gtn.isomorphic(gtn.intersect(g1, g2), expected))
# Check singly sorted version
g1.arc_sort(True)
self.assertTrue(gtn.isomorphic(gtn.compose(g1, g2), expected))
# Check doubly sorted version
g2.arc_sort()
self.assertTrue(gtn.isomorphic(gtn.compose(g1, g2), expected))
# Loop in the composed graph
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node(False, True)
g1.add_arc(0, 1, 0)
g1.add_arc(1, 1, 1)
g1.add_arc(1, 0, 0)
g2 = gtn.Graph()
g2.add_node(True)
g2.add_node(False, True)
g2.add_arc(0, 0, 0)
g2.add_arc(0, 1, 1)
g2.add_arc(1, 0, 1)
g_str = ["0", "2", "0 1 0", "1 0 0", "1 2 1", "2 1 1"]
expected = create_graph_from_text(g_str)
self.assertTrue(gtn.isomorphic(gtn.compose(g1, g2), expected))
self.assertTrue(gtn.isomorphic(gtn.intersect(g1, g2), expected))
# Check singly sorted version
g1.arc_sort(True)
self.assertTrue(gtn.isomorphic(gtn.compose(g1, g2), expected))
# Check doubly sorted version
g2.arc_sort()
self.assertTrue(gtn.isomorphic(gtn.compose(g1, g2), expected))
g1 = gtn.Graph()
g1.add_node(True)
g1.add_node()
g1.add_node()
g1.add_node()
g1.add_node(False, True)
for i in range(g1.num_nodes() - 1):
for j in range(3):
g1.add_arc(i, i + 1, j, j, j)
g2 = gtn.Graph()
g2.add_node(True)
g2.add_node()
g2.add_node(False, True)
g2.add_arc(0, 1, 0, 0, 3.5)
g2.add_arc(1, 1, 0, 0, 2.5)
g2.add_arc(1, 2, 1, 1, 1.5)
g2.add_arc(2, 2, 1, 1, 4.5)
g_str = [
"0",
"6",
"0 1 0 0 3.5",
"1 2 0 0 2.5",
"1 4 1 1 2.5",
"2 3 0 0 2.5",
"2 5 1 1 2.5",
"4 5 1 1 5.5",
"3 6 1 1 2.5",
"5 6 1 1 5.5",
]
expected = create_graph_from_text(g_str)
self.assertTrue(gtn.isomorphic(gtn.compose(g1, g2), expected))
self.assertTrue(gtn.isomorphic(gtn.intersect(g1, g2), expected))
# Check singly sorted version
g1.arc_sort(True)
self.assertTrue(gtn.isomorphic(gtn.compose(g1, g2), expected))
# Check doubly sorted version
g2.arc_sort()
self.assertTrue(gtn.isomorphic(gtn.compose(g1, g2), expected))