def test_transform(rng):
v1 = Vocabulary(32, rng=rng)
v2 = Vocabulary(64, rng=rng)
A = v1.parse('A')
B = v1.parse('B')
C = v1.parse('C')
# Test transform from v1 to v2 (full vocbulary)
# Expected: np.dot(t, A.v) ~= v2.parse('A')
# Expected: np.dot(t, B.v) ~= v2.parse('B')
# Expected: np.dot(t, C.v) ~= v2.parse('C')
t = v1.transform_to(v2)
assert v2.parse('A').compare(np.dot(t, A.v)) > 0.95
assert v2.parse('C+B').compare(np.dot(t, C.v + B.v)) > 0.9
# Test transform from v1 to v2 (only 'A' and 'B')
t = v1.transform_to(v2, keys=['A', 'B'])
assert v2.parse('A').compare(np.dot(t, A.v)) > 0.95
assert v2.parse('B').compare(np.dot(t, C.v + B.v)) > 0.95
# Test transform_to when either vocabulary is read-only
v1.parse('D')
v2.parse('E')
# When both are read-only, transform_to shouldn't add any new items to
# either and the transform should be using keys that are the intersection
# of both vocabularies
v1.readonly = True
v2.readonly = True
t = v1.transform_to(v2)
assert v1.keys == ['A', 'B', 'C', 'D']
assert v2.keys == ['A', 'B', 'C', 'E']
# When one is read-only, transform_to should add any new items to the non
# read-only vocabulary
v1.readonly = False
v2.readonly = True
t = v1.transform_to(v2)
assert v1.keys == ['A', 'B', 'C', 'D', 'E']
assert v2.keys == ['A', 'B', 'C', 'E']
# When one is read-only, transform_to should add any new items to the non
# read-only vocabulary
v1.readonly = True
v2.readonly = False
t = v1.transform_to(v2)
assert v1.keys == ['A', 'B', 'C', 'D', 'E']
assert v2.keys == ['A', 'B', 'C', 'E', 'D']
def test_transform(rng):
v1 = Vocabulary(32, rng=rng)
v2 = Vocabulary(64, rng=rng)
A = v1.parse("A")
B = v1.parse("B")
C = v1.parse("C")
# Test transform from v1 to v2 (full vocbulary)
# Expected: np.dot(t, A.v) ~= v2.parse('A')
# Expected: np.dot(t, B.v) ~= v2.parse('B')
# Expected: np.dot(t, C.v) ~= v2.parse('C')
t = v1.transform_to(v2)
assert v2.parse("A").compare(np.dot(t, A.v)) > 0.95
assert v2.parse("C+B").compare(np.dot(t, C.v + B.v)) > 0.9
# Test transform from v1 to v2 (only 'A' and 'B')
t = v1.transform_to(v2, keys=["A", "B"])
assert v2.parse("A").compare(np.dot(t, A.v)) > 0.95
assert v2.parse("B").compare(np.dot(t, C.v + B.v)) > 0.95
# Test transform_to when either vocabulary is read-only
v1.parse("D")
v2.parse("E")
# When both are read-only, transform_to shouldn't add any new items to
# either and the transform should be using keys that are the intersection
# of both vocabularies
v1.readonly = True
v2.readonly = True
t = v1.transform_to(v2)
assert v1.keys == ["A", "B", "C", "D"]
assert v2.keys == ["A", "B", "C", "E"]
# When one is read-only, transform_to should add any new items to the non
# read-only vocabulary
v1.readonly = False
v2.readonly = True
t = v1.transform_to(v2)
assert v1.keys == ["A", "B", "C", "D", "E"]
assert v2.keys == ["A", "B", "C", "E"]
# When one is read-only, transform_to should add any new items to the non
# read-only vocabulary
v1.readonly = True
v2.readonly = False
t = v1.transform_to(v2)
assert v1.keys == ["A", "B", "C", "D", "E"]
assert v2.keys == ["A", "B", "C", "E", "D"]
def test_transform(rng):
v1 = Vocabulary(32, rng=rng)
v2 = Vocabulary(64, rng=rng)
A = v1.parse('A')
B = v1.parse('B')
C = v1.parse('C')
t = v1.transform_to(v2)
assert v2.parse('A').compare(np.dot(t, A.v)) > 0.95
assert v2.parse('C+B').compare(np.dot(t, C.v + B.v)) > 0.9
t = v1.transform_to(v2, keys=['A', 'B'])
assert v2.parse('A').compare(np.dot(t, A.v)) > 0.95
assert v2.parse('B').compare(np.dot(t, B.v)) > 0.95
def test_transform(rng):
v1 = Vocabulary(32, rng=rng)
v2 = Vocabulary(64, rng=rng)
A = v1.parse('A')
B = v1.parse('B')
C = v1.parse('C')
t = v1.transform_to(v2)
assert v2.parse('A').compare(np.dot(t, A.v)) > 0.95
assert v2.parse('C+B').compare(np.dot(t, C.v + B.v)) > 0.9
t = v1.transform_to(v2, keys=['A', 'B'])
assert v2.parse('A').compare(np.dot(t, A.v)) > 0.95
assert v2.parse('B').compare(np.dot(t, B.v)) > 0.95
def test_transform(rng):
v1 = Vocabulary(32, rng=rng)
v2 = Vocabulary(64, rng=rng)
A = v1.parse("A")
B = v1.parse("B")
C = v1.parse("C")
t = v1.transform_to(v2)
assert v2.parse("A").compare(np.dot(t, A.v)) > 0.95
assert v2.parse("C+B").compare(np.dot(t, C.v + B.v)) > 0.9
t = v1.transform_to(v2, keys=["A", "B"])
assert v2.parse("A").compare(np.dot(t, A.v)) > 0.95
assert v2.parse("B").compare(np.dot(t, B.v)) > 0.95
def test_transform():
v1 = Vocabulary(32, rng=np.random.RandomState(7))
v2 = Vocabulary(64, rng=np.random.RandomState(8))
A = v1.parse('A')
B = v1.parse('B')
C = v1.parse('C')
t = v1.transform_to(v2)
assert v2.parse('A').compare(np.dot(t, A.v)) > 0.95
assert v2.parse('C+B').compare(np.dot(t, C.v + B.v)) > 0.95
t = v1.transform_to(v2, keys=['A', 'B'])
assert v2.parse('A').compare(np.dot(t, A.v)) > 0.95
assert v2.parse('B').compare(np.dot(t, C.v + B.v)) > 0.95
def test_subset(rng):
v1 = Vocabulary(32, rng=rng)
v1.parse("A+B+C+D+E+F+G")
# Test creating a vocabulary subset
v2 = v1.create_subset(["A", "C", "E"])
assert v2.keys == ["A", "C", "E"]
assert v2["A"] == v1["A"]
assert v2["C"] == v1["C"]
assert v2["E"] == v1["E"]
assert v2.parent is v1
# Test creating a subset from a subset (it should create off the parent)
v3 = v2.create_subset(["C", "E"])
assert v3.parent is v2.parent and v2.parent is v1
v3.include_pairs = True
assert v3.key_pairs == ["C*E"]
assert not v1.include_pairs
assert not v2.include_pairs
# Test transform_to between subsets (should be identity transform)
t = v1.transform_to(v2)
assert v2.parse("A").compare(np.dot(t, v1.parse("A").v)) >= 0.99999999
def test_subset(rng):
v1 = Vocabulary(32, rng=rng)
v1.parse('A+B+C+D+E+F+G')
# Test creating a vocabulary subset
v2 = v1.create_subset(['A', 'C', 'E'])
assert v2.keys == ['A', 'C', 'E']
assert v2['A'] == v1['A']
assert v2['C'] == v1['C']
assert v2['E'] == v1['E']
assert v2.parent is v1
# Test creating a subset from a subset (it should create off the parent)
v3 = v2.create_subset(['C', 'E'])
assert v3.parent is v2.parent and v2.parent is v1
v3.include_pairs = True
assert v3.key_pairs == ['C*E']
assert not v1.include_pairs
assert not v2.include_pairs
# Test transform_to between subsets (should be identity transform)
t = v1.transform_to(v2)
assert v2.parse('A').compare(np.dot(t, v1.parse('A').v)) >= 0.99999999
