def random_sent_summary():
meta_repo = CassandraDatabase(project_name='papers',
repo_name='meta',
id_sql_type='BIGINT',
content_sql_type="TEXT")
encoded_sents_repo = CassandraDatabase(project_name='papers',
repo_name='sents',
id_sql_type='BIGINT',
content_sql_type="TEXT")
loc = 0
top3 = 0
top10 = 0
for id, row in meta_repo.list():
meta = ast.literal_eval(row.replace('nan', '\'\''))
ids = meta['children']
random_sent_id = random.choice(ids)
result = ast.literal_eval(
q.query(json.dumps({
"text": random_sent_id,
"count": 205
})))
sims = result['result']
inter = result['keywords']
index = np.where(np.array(list(sims.keys())) == id)[0][0]
if index < 3:
top3 += 1
if index < 10:
top10 += 1
loc += index
print('{:.2f} top3 {} top 10 {}'.format(loc / meta_repo.count(), top3,
top10))
'''tootal count 203. USE: [9.46, 3: 135, 10: 159], upvotes: [9.68,3: 150, 10: 165],
def title_summary():
repo = CassandraDatabase(project_name='papers',
repo_name='title',
id_sql_type='BIGINT',
content_sql_type="TEXT")
loc = 0
top3 = 0
top10 = 0
for id, row in repo.list():
result = ast.literal_eval(
q.query(json.dumps({
"text": row,
"count": 203
})))
sims = result['result']
inter = result['keywords']
index = np.where(np.array(list(sims.keys())) == id)[0][0]
if index < 3:
top3 += 1
if index < 10:
top10 += 1
loc += index
print('{:.2f} top3 {} top 10 {}'.format(loc / repo.count(), top3, top10))
'''tootal count 203. USE: [13.62, 3: 106, 10: 148], upvotes: [20.56, 3: 83, 10: 124],
def title_sents():
repo = CassandraDatabase(project_name='papers',
repo_name='title',
id_sql_type='BIGINT',
content_sql_type="TEXT")
sent_sum_map_repo = CassandraDatabase(project_name='papers',
repo_name='sent_sum_map',
id_sql_type='BIGINT',
content_sql_type="TEXT")
loc = 0
top3 = 0
top10 = 0
k = 0
for id, row in repo.list():
k += 1
print(k)
result = ast.literal_eval(
q.query(json.dumps({
"text": row,
"count": 203
})))
sims = result['result']
inter = result['keywords']
papers_ids = []
for sent_id in list(sims.keys()):
paper_id = int(sent_sum_map_repo.read(sent_id)[0])
if paper_id not in papers_ids:
papers_ids.append(paper_id)
if paper_id == id:
index = len(papers_ids)
break
# papers_ids = np.array(papers_ids)
# index = np.where(np.array(papers_ids) == id)[0][0]
if index < 3:
top3 += 1
if index < 10:
top10 += 1
loc += index
print('{:.2f} top3 {} top 10 {}'.format(loc / repo.count(), top3, top10))
'''tootal count 203. USE: [11.40, 3: 11, 10: 143], upvotes: [17.77, 3: 107, 10: 141],