def test_space_train_dense(self):
test_cases = [([("a","b","a_b")], self.space4, self.space5),
([("a","b","a_b")], self.space4, self.space6),
([("a","b","a_b"),("a","b","a_a")], self.space4, self.space7),
]
learners = [RidgeRegressionLearner(intercept=False, crossvalidation=False, param=0),
LstsqRegressionLearner(intercept=False),
LstsqRegressionLearner(intercept=True)]
for in_data, arg_space, phrase_space in test_cases:
for learner_ in learners:
comp_model = FullAdditive(learner=learner_)
comp_model.train(in_data, arg_space, phrase_space)
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, phrase_space.id2column)
self.assertDictEqual(comp_space.column2id, phrase_space.column2id)
self.assertListEqual(comp_space.id2row, phrase_space.id2row)
self.assertDictEqual(comp_space.row2id, phrase_space.row2id)
self.assertEqual(comp_model._has_intercept, learner_._intercept)
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_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_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_train_dense(self):
test_cases = [
([("a", "b", "a_b")], self.space4, self.space5),
([("a", "b", "a_b")], self.space4, self.space6),
([("a", "b", "a_b"), ("a", "b", "a_a")], self.space4, self.space7),
]
learners = [
RidgeRegressionLearner(intercept=False,
crossvalidation=False,
param=0),
LstsqRegressionLearner(intercept=False),
LstsqRegressionLearner(intercept=True)
]
for in_data, arg_space, phrase_space in test_cases:
for learner_ in learners:
comp_model = FullAdditive(learner=learner_)
comp_model.train(in_data, arg_space, phrase_space)
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,
phrase_space.id2column)
self.assertDictEqual(comp_space.column2id,
phrase_space.column2id)
self.assertListEqual(comp_space.id2row, phrase_space.id2row)
self.assertDictEqual(comp_space.row2id, phrase_space.row2id)
self.assertEqual(comp_model._has_intercept,
learner_._intercept)
from composes.composition.full_additive import FullAdditive
#training data
train_data = [("good", "car", "good_car"),
("good", "book", "good_book")
]
#load an argument space
arg_space = io_utils.load("./data/out/ex10.pkl")
#load a phrase space
phrase_space = io_utils.load("data/out/PHRASE_SS.ex10.pkl")
print("Training phrase space")
print(phrase_space.id2row)
print(phrase_space.cooccurrence_matrix)
#train a FullAdditive model on the data
my_comp = FullAdditive()
my_comp.train(train_data, arg_space, phrase_space)
#print its parameters
print("\nA:", my_comp._mat_a_t.transpose())
print("B:", my_comp._mat_b_t.transpose())
#use the model to compose the train data
composed_space = my_comp.compose([("good", "bike", "good_bike")],
arg_space)
print("\nComposed space:")
print(composed_space.id2row)
print(composed_space.cooccurrence_matrix)
from composes.composition.full_additive import FullAdditive
#training data
train_data = [("good", "car", "good_car"),
("good", "book", "good_book")
]
#load an argument space
arg_space = io_utils.load("./data/out/ex10.pkl")
#load a phrase space
phrase_space = io_utils.load("data/out/PHRASE_SS.ex10.pkl")
print "Training phrase space"
print phrase_space.id2row
print phrase_space.cooccurrence_matrix
#train a FullAdditive model on the data
my_comp = FullAdditive()
my_comp.train(train_data, arg_space, phrase_space)
#print its parameters
print "\nA:", my_comp._mat_a_t.transpose()
print "B:", my_comp._mat_b_t.transpose()
#use the model to compose the train data
composed_space = my_comp.compose([("good", "bike", "good_bike")],
arg_space)
print "\nComposed space:"
print composed_space.id2row
print composed_space.cooccurrence_matrix
