def test_batch_basic():
model = Numila(PARSE='batch', CHUNK_THRESHOLD=2)
log = utils.log_parse(model, 'a b c')
assert log.count('bump a -> b') is 1
assert log.count('bump b -> c') is 1
log = utils.log_parse(model, 'a b c d')
assert log.count('bump a -> b') is 1
assert log.count('bump b -> c') is 1
assert log.count('bump c -> d') is 1
def test_inc_basic():
model = Numila(PARSE='incremental', CHUNK_THRESHOLD=2)
log = utils.log_parse(model, 'a b c')
assert log.count('bump a -> b') is 2
assert log.count('bump b -> c') is 2
log = utils.log_parse(model, 'a b c d')
assert log.count('bump a -> b') is 3
assert log.count('bump b -> c') is 3
assert log.count('bump c -> d') is 3
log = utils.log_parse(model, 'a b c d e')
assert log.count('bump a -> b') is 3
assert log.count('bump b -> c') is 3
assert log.count('bump c -> d') is 3
assert log.count('bump d -> e') is 3
def test_easy(model):
model.params['CHUNK_THRESHOLD'] = 2
# One simple utterance 50 times.
utterance = 'a b a c a b d'
corpus = [utterance] * 50
model.parse(corpus[0])
print(utils.log_parse(model, corpus[0]))
a, b, c, d = (model.graph[x] for x in 'abcd') # node objects
def weight(edge, n1, n2):
return n1.edge_weight(n2, edge)
# Check that all connections are positive after one utterance
for x, y in utils.neighbors(utterance.split(' ')):
assert weight('ftp', model.graph[x], model.graph[y])
assert weight('btp', model.graph[y], model.graph[x])
# Equal conditional probability, but more evidence
#assert weight('btp', b, a) < weight('btp', c, a)
model.fit(corpus)
# Check that weights don't change when they shouldn't change.
w1 = weight('ftp', a, b)
model.parse('b c')
w2 = weight('ftp', a, b)
assert w1 - w2 < .001
w1 = weight('btp', b, a)
model.parse('d a d a d a d a d a d a')
w2 = weight('btp', b, a)
assert w1 - w2 < .001
# Check that more common edges are more highly weighted.
# We vary the conditional (ab | a) and raw (ab) probabilities.
# Reference: a b a c a b d
# Higher conditional, higher raw.
assert weight('ftp', a, b) > weight('ftp', a, c)
# Higher conditional, equal raw.
assert weight('ftp', c, a) > weight('ftp', b, d)
return # TODO
# Equal conditional, higher raw. But lots of evidence for both.
print()
print(weight('btp', c, a, verbose=True))
assert 0
assert weight('btp', b, a) - weight('btp', c, a) < 0.001
# This always fails for vector. The edge weights do not really
# represent probabilities. They are more sensitive to the raw
# occurrence counts.
# p(ab | a) = 0.66
# p(ca | c) = 1
# p(ab) = 0.4
# p(ca) = 0.2
#assert weight('ftp', c, a) > weight('ftp', a, b)
assert weight('ftp', a, a) < 0.05
assert weight('ftp', b, b) < 0.05
assert weight('ftp', c, c) < 0.05
assert weight('ftp', b, c) < 0.05
