def test_vectorizing_and_similar_terms():
# Simple test for vectorizing weighted terms
assoc = AssocSpace.from_entries(ENTRIES, k=3)
weighted_terms = [('apple', 5), ('banana', 22), ('not a term', 17)]
apple = assoc.row_named('apple')
banana = assoc.row_named('banana')
vector = assoc.vector_from_terms(weighted_terms)
# The similarity of 'apple' to itself is approximately 1
assert abs(assoc.assoc_between_two_terms('apple', 'apple') - 1.0) < 1e-3
# 'apple' and 'banana' are at least 10% less similar to each other than
# to themselves
assert assoc.assoc_between_two_terms('apple', 'banana') < 0.9
# The vector is some linear combination of apple and banana. Test this
# by subtracting out apple and banana components, so that there is nothing
# left.
norm_apple = normalize(apple)
banana_perp_apple = normalize(banana - norm_apple * norm_apple.dot(banana))
residual = vector - norm_apple * norm_apple.dot(vector)
residual -= banana_perp_apple * banana_perp_apple.dot(residual)
assert norm(residual) < 1e-3
# Simple test for finding similar terms
labels, scores = zip(*assoc.terms_similar_to_vector(vector))
eq_(list(scores), sorted(scores, reverse=True))
most_similar = assoc.most_similar_to_vector(vector)
eq_(most_similar[0], labels[0])
eq_(most_similar[1], scores[0])
assert labels.index('banana') < labels.index('apple')
assert labels.index('apple') < labels.index('green')
assert labels.index('apple') < labels.index('celery')
def test_vectorizing_and_similar_terms():
# Simple test for vectorizing weighted terms
assoc = AssocSpace.from_entries(ENTRIES, k=3)
weighted_terms = [('apple', 5), ('banana', 22), ('not a term', 17)]
apple = assoc.row_named('apple')
banana = assoc.row_named('banana')
vector = assoc.vector_from_terms(weighted_terms)
# The similarity of 'apple' to itself is approximately 1
assert abs(assoc.assoc_between_two_terms('apple', 'apple') - 1.0) < 1e-3
# 'apple' and 'banana' are at least 10% less similar to each other than
# to themselves
assert assoc.assoc_between_two_terms('apple', 'banana') < 0.9
# The vector is some linear combination of apple and banana. Test this
# by subtracting out apple and banana components, so that there is nothing
# left.
norm_apple = normalize(apple)
banana_perp_apple = normalize(banana - norm_apple * norm_apple.dot(banana))
residual = vector - norm_apple * norm_apple.dot(vector)
residual -= banana_perp_apple * banana_perp_apple.dot(residual)
assert norm(residual) < 1e-3
# Simple test for finding similar terms
labels, scores = zip(*assoc.terms_similar_to_vector(vector))
eq_(list(scores), sorted(scores, reverse=True))
most_similar = assoc.most_similar_to_vector(vector)
eq_(most_similar[0], labels[0])
eq_(most_similar[1], scores[0])
assert labels.index('banana') < labels.index('apple')
assert labels.index('apple') < labels.index('green')
assert labels.index('apple') < labels.index('celery')
def test_truncation():
# Simple test of truncation
assoc = AssocSpace.from_entries(ENTRIES, k=3)
truncated = assoc.truncated_to(2)
assert np.allclose(truncated.u, assoc.u[:, :2])
assert np.allclose(truncated.sigma, assoc.sigma[:2])
eq_(truncated.labels, assoc.labels)
assert 0.999 < norm(truncated.assoc[0]) < 1.0
def test_truncation():
# Simple test of truncation
assoc = AssocSpace.from_entries(ENTRIES, k=3)
truncated = assoc.truncated_to(2)
assert np.allclose(truncated.u, assoc.u[:, :2])
assert np.allclose(truncated.sigma, assoc.sigma[:2])
eq_(truncated.labels, assoc.labels)
assert 0.999 < norm(truncated.assoc[0]) < 1.0
def test_filter():
# Build and filter an assoc space
assoc = AssocSpace.from_entries(ENTRIES, k=5)
filtered = assoc.filter(_filter)
# Check simple properties of the filtered space
eq_(filtered.k, 5)
eq_(' '.join(filtered.labels), 'red green celery banana lemon')
# Check that redecomposition happened
assert np.allclose(norm(filtered.u[:, 1]), 1.0)
# Redecomposition can be kind of weird, but this result is intuitive
assert (assoc.assoc_between_two_terms(
'red', 'banana') < filtered.assoc_between_two_terms('red', 'banana') <
assoc.assoc_between_two_terms('yellow', 'banana'))
def test_filter():
# Build and filter an assoc space
assoc = AssocSpace.from_entries(ENTRIES, k=5)
filtered = assoc.filter(_filter)
# Check simple properties of the filtered space
eq_(filtered.k, 5)
eq_(' '.join(filtered.labels), 'red green celery banana lemon')
# Check that redecomposition happened
assert np.allclose(norm(filtered.u[:, 1]), 1.0)
# Redecomposition can be kind of weird, but this result is intuitive
assert (assoc.assoc_between_two_terms('red', 'banana') <
filtered.assoc_between_two_terms('red', 'banana') <
assoc.assoc_between_two_terms('yellow', 'banana'))
def test_norm_and_normalize():
vec = np.asarray([8.0, 9.0, 12.0])
assert np.allclose(norm(vec), 17.0)
assert np.allclose(normalize(vec), vec / 17.0)
# We normalize the zero vector to itself rather than raising an error
assert (np.zeros(5) == normalize(np.zeros(5))).all()
def test_norm_and_normalize():
vec = np.asarray([8.0, 9.0, 12.0])
assert np.allclose(norm(vec), 17.0)
assert np.allclose(normalize(vec), vec / 17.0)
# We normalize the zero vector to itself rather than raising an error
assert (np.zeros(5) == normalize(np.zeros(5))).all()
