def write_topic_terms(self, top_term_mat):
"""
Write the topic x term matrix to the database
@param top_term_mat: topics x terms matrix, should represent log-lieklihood for accurate calculations
"""
ntops = top_term_mat.shape[0]
nterms = top_term_mat.shape[1]
execution_str = 'INSERT INTO topic_term (id, topic, term, score) VALUES(NULL, ?, ?, ?)'
for topic_no in xrange(ntops):
topic = top_term_mat[topic_no,:]
res = generic_generator((topic_no,)*nterms, range(nterms), topic)
self.dbase.executemany(execution_str, res)
def write_topic_topic(self, top_term_mat):
"""
Write the topic x topic matrix to the database
@param top_term_mat: topics x terms matrix, should represent log-lieklihood for accurate calculations
"""
# TODO make distance metric a user option
execution_str = 'INSERT INTO topic_topic (id, topic_a, topic_b, score) VALUES(NULL, ?, ?, ?)'
for i in xrange(top_term_mat.shape[0]):
scores = 1/hellinger_distance(top_term_mat[i,:]**0.5, top_term_mat[i+1:,:]**0.5)
scores[np.where(np.isinf(scores))] = -1
res = generic_generator((i,)*len(scores), range(i+1, i+1+len(scores)), scores)
self.dbase.executemany(execution_str, res)
def write_topic_terms(self, top_term_mat):
"""
Write the topic x term matrix to the database
@param top_term_mat: topics x terms matrix, should represent log-lieklihood for accurate calculations
"""
ntops = top_term_mat.shape[0]
nterms = top_term_mat.shape[1]
execution_str = 'INSERT INTO topic_term (id, topic, term, score) VALUES(NULL, ?, ?, ?)'
for topic_no in xrange(ntops):
topic = top_term_mat[topic_no, :]
res = generic_generator((topic_no, ) * nterms, range(nterms),
topic)
self.dbase.executemany(execution_str, res)
def write_topic_topic(self, top_term_mat):
"""
Write the topic x topic matrix to the database
@param top_term_mat: topics x terms matrix, should represent log-lieklihood for accurate calculations
"""
# TODO make distance metric a user option
execution_str = 'INSERT INTO topic_topic (id, topic_a, topic_b, score) VALUES(NULL, ?, ?, ?)'
for i in xrange(top_term_mat.shape[0]):
scores = 1 / hellinger_distance(top_term_mat[i, :]**0.5,
top_term_mat[i + 1:, :]**0.5)
scores[np.where(np.isinf(scores))] = -1
res = generic_generator((i, ) * len(scores),
range(i + 1, i + 1 + len(scores)), scores)
self.dbase.executemany(execution_str, res)
