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_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.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)
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_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 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 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.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.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)