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)
def test_train1(self):
test_cases = [(self.m11, self.m21, self.ph1, np.mat([[2]]), np.mat([[3]])),
(self.m11, self.m21, DenseMatrix(np.mat([[0],[0]])),
np.mat([[0]]), np.mat([[0]]))]
for m1, m2, ph, expected_a, expected_b in test_cases:
comp_model = FullAdditive(learner=LstsqRegressionLearner(intercept=False))
comp_model._train(m1, m2, ph)
np.testing.assert_array_almost_equal(comp_model._mat_a_t.transpose().mat,
expected_a, 10)
np.testing.assert_array_almost_equal(comp_model._mat_b_t.transpose().mat,
expected_b, 10)
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_train1(self):
test_cases = [(self.m11, self.m21, self.ph1, np.mat([[2]]),
np.mat([[3]])),
(self.m11, self.m21, DenseMatrix(np.mat([[0], [0]])),
np.mat([[0]]), np.mat([[0]]))]
for m1, m2, ph, expected_a, expected_b in test_cases:
comp_model = FullAdditive(learner=LstsqRegressionLearner(
intercept=False))
comp_model._train(m1, m2, ph)
np.testing.assert_array_almost_equal(
comp_model._mat_a_t.transpose().mat, expected_a, 10)
np.testing.assert_array_almost_equal(
comp_model._mat_b_t.transpose().mat, expected_b, 10)
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 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_train2(self):
dim_ = 2
dim_1 = 3
dim_2 = 5
for dim in [dim_1 + dim_2, dim_1 + dim_2 + 2]:
expected_a = np.mat(np.random.random((dim_,dim_1)))
expected_b = np.mat(np.random.random((dim_,dim_2)))
m1 = np.mat(np.random.random((dim,dim_1)))
m2 = np.mat(np.random.random((dim,dim_2)))
ph = np.mat(expected_a*m1.T + expected_b*m2.T)
comp_model = FullAdditive(learner=LstsqRegressionLearner(intercept=False))
comp_model._train(DenseMatrix(m1),DenseMatrix(m2),
DenseMatrix(ph).transpose())
np.testing.assert_array_almost_equal(comp_model._mat_a_t.transpose().mat,
expected_a, 10)
np.testing.assert_array_almost_equal(comp_model._mat_b_t.transpose().mat,
expected_b, 10)
for dim in [dim_1 + dim_2 + 6, dim_1 + dim_2 + 20]:
expected_a = np.mat(np.random.random((dim_,dim_1)))
expected_b = np.mat(np.random.random((dim_,dim_2)))
m1 = np.mat(np.random.random((dim,dim_1)))
m2 = np.mat(np.random.random((dim,dim_2)))
ph = np.mat(expected_a*m1.T + expected_b*m2.T)
comp_model = FullAdditive(learner=LstsqRegressionLearner(intercept=True))
comp_model._train(DenseMatrix(m1),DenseMatrix(m2),
DenseMatrix(ph).transpose())
np.testing.assert_array_almost_equal(comp_model._mat_a_t.transpose().mat,
expected_a, 10)
np.testing.assert_array_almost_equal(comp_model._mat_b_t[:-1,:].transpose().mat,
expected_b, 10)
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_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 test_train2(self):
dim_ = 2
dim_1 = 3
dim_2 = 5
for dim in [dim_1 + dim_2, dim_1 + dim_2 + 2]:
expected_a = np.mat(np.random.random((dim_, dim_1)))
expected_b = np.mat(np.random.random((dim_, dim_2)))
m1 = np.mat(np.random.random((dim, dim_1)))
m2 = np.mat(np.random.random((dim, dim_2)))
ph = np.mat(expected_a * m1.T + expected_b * m2.T)
comp_model = FullAdditive(learner=LstsqRegressionLearner(
intercept=False))
comp_model._train(DenseMatrix(m1), DenseMatrix(m2),
DenseMatrix(ph).transpose())
np.testing.assert_array_almost_equal(
comp_model._mat_a_t.transpose().mat, expected_a, 10)
np.testing.assert_array_almost_equal(
comp_model._mat_b_t.transpose().mat, expected_b, 10)
for dim in [dim_1 + dim_2 + 6, dim_1 + dim_2 + 20]:
expected_a = np.mat(np.random.random((dim_, dim_1)))
expected_b = np.mat(np.random.random((dim_, dim_2)))
m1 = np.mat(np.random.random((dim, dim_1)))
m2 = np.mat(np.random.random((dim, dim_2)))
ph = np.mat(expected_a * m1.T + expected_b * m2.T)
comp_model = FullAdditive(learner=LstsqRegressionLearner(
intercept=True))
comp_model._train(DenseMatrix(m1), DenseMatrix(m2),
DenseMatrix(ph).transpose())
np.testing.assert_array_almost_equal(
comp_model._mat_a_t.transpose().mat, expected_a, 10)
np.testing.assert_array_almost_equal(
comp_model._mat_b_t[:-1, :].transpose().mat, expected_b, 10)
composed_space = comp_model.compose(test_phrases, space) print "Reading similarity test data..." test_similarity_file = data_path + "ML08data_new.txt" test_pairs = io_utils.read_tuple_list(test_similarity_file, fields=[0, 1]) gold = io_utils.read_list(test_similarity_file, field=2) print "Computing similarity with lexical function..." pred = composed_space.get_sims(test_pairs, CosSimilarity()) #use this composed space to assign similarities print "Scoring lexical function..." print scoring_utils.score(gold, pred, "spearman") print "Training Full Additive composition model..." comp_model = FullAdditive(learner=RidgeRegressionLearner(param=2)) comp_model.train(train_data, space, per_space) composed_space = comp_model.compose(test_phrases, space) pred = composed_space.get_sims(test_pairs, CosSimilarity()) print scoring_utils.score(gold, pred, "spearman") print "Training Weighted Additive composition model..." comp_model = WeightedAdditive() comp_model.train(train_data, space, per_space) print "alpha, beta:", comp_model.alpha, comp_model.beta composed_space = comp_model.compose(test_phrases, space) pred = composed_space.get_sims(test_pairs, CosSimilarity()) print scoring_utils.score(gold, pred, "spearman") print "Training Dilation composition model..." comp_model = Dilation()
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