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 vector_from_terms(self, terms):
"""
Get a vector representing a weighted set of terms, provided as a
collection of (term, weight) tuples. Note that this does not normalize
the rows of U e^(S/2) before taking their weighted sum; this applies a
natural penalty to low-quality terms.
"""
result = np.zeros((self.k,))
for term, weight in terms:
if term in self.labels:
if term not in self._row_cache:
# Prevent the cache from growing too large
if len(self._row_cache) > 15000:
self._row_cache = {}
# Avoid keeping a slice of a memmap object; Numpy handles
# these inefficiently if you have a lot of them (especially
# in 1.7, but even in 1.6 or 1.8)
row = np.copy(self.u[self.labels.index(term)])
self._row_cache[term] = row
result += self._row_cache[term] * weight
return eigenmath.normalize(result * np.exp(self.sigma / 2))
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 cos_diff(a, b): return normalize(a).dot(normalize(b))
def cos_diff(a, b):
return normalize(a).dot(normalize(b))
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()
