def test_sim_mat(self):
def sim_func(a, b):
return a * b
items = [1, 2, 3, 4]
expected = np.array([[1., 2., 3., 4.], [2., 1., 6., 8.],
[3., 6., 1., 12.], [4., 8., 12., 1.]])
sim_mat = util.build_sim_mat(items, sim_func)
np.testing.assert_array_equal(sim_mat, expected)
def test_sim_mat(self):
def sim_func(a, b):
return a * b
items = [1,2,3,4]
expected = np.array([
[1., 2., 3., 4.],
[2., 1., 6., 8.],
[3., 6., 1., 12.],
[4., 8., 12., 1.]
])
sim_mat = util.build_sim_mat(items, sim_func)
np.testing.assert_array_equal(sim_mat, expected)
def __call__(self, docs, token_docs):
all_terms = set([t for toks in token_docs for t in toks])
bg_docs = [self.fetch_wikipage(t) for t in all_terms]
# Filter out empty docs (will mess up cosine similarity)
bg_docs = [bg for bg in bg_docs if bg]
n_docs = len(docs)
all_docs = docs + bg_docs
vectr = self.vectorizer()
vecs = vectr.vectorize(all_docs).todense()
doc_vecs = vecs[:n_docs] # target doc vecs
bg_vecs = vecs[n_docs:] # background doc vecs
# Bridging space representation of the docs
doc_vecs = cdist(doc_vecs, bg_vecs, metric='cosine')
return build_sim_mat(doc_vecs, self.compute_bridge_similarity)
def __call__(self, docs, token_docs):
all_terms = set([t for toks in token_docs for t in toks])
bg_docs = [self.fetch_wikipage(t) for t in all_terms]
# Filter out empty docs (will mess up cosine similarity)
bg_docs = [bg for bg in bg_docs if bg]
n_docs = len(docs)
all_docs = docs + bg_docs
vectr = self.vectorizer()
vecs = vectr.vectorize(all_docs).todense()
doc_vecs = vecs[:n_docs] # target doc vecs
bg_vecs = vecs[n_docs:] # background doc vecs
# Bridging space representation of the docs
doc_vecs = cdist(doc_vecs, bg_vecs, metric='cosine')
return build_sim_mat(doc_vecs, self.compute_bridge_similarity)
def __call__(self, token_docs, entities):
pdocs = []
for i, (tks, ents) in enumerate(zip(token_docs, entities)):
pdocs.append(Document(i, ents, tks))
return build_sim_mat(pdocs, self.similarity)
