for i in range(m):
for j in range(i+1,m):
sim = similarity(clusters[i], clusters[j], adj)
if sim > best_sim:
best_sim = sim
best_i = i
best_j = j
cluster = clusters[best_i].union(clusters[best_j])
del clusters[best_j]
del clusters[best_i]
clusters.append(cluster)
ans = []
for item in clusters:
s = set()
for ind in item:
s.add(ind2id[ind])
ans.append(s)
return ans
if __name__ == '__main__':
pubs = es._get_all_publications()
authors = {}
for pub in pubs:
for author in pub['authors']:
uid = str(author['uid'])
authors.setdefault(uid, set())
authors[uid].add(pub['id'])
print(cluster_writers(authors))
for j in range(i + 1, m):
sim = similarity(clusters[i], clusters[j], adj)
if sim > best_sim:
best_sim = sim
best_i = i
best_j = j
cluster = clusters[best_i].union(clusters[best_j])
del clusters[best_j]
del clusters[best_i]
clusters.append(cluster)
ans = []
for item in clusters:
s = set()
for ind in item:
s.add(ind2id[ind])
ans.append(s)
return ans
if __name__ == '__main__':
pubs = es._get_all_publications()
authors = {}
for pub in pubs:
for author in pub['authors']:
uid = str(author['uid'])
authors.setdefault(uid, set())
authors[uid].add(pub['id'])
print(cluster_writers(authors))
def _get_rank(cites):
"""
:param cites: np.array presenting citation of i -> j
:return: array of page ranks
indices are assumed 0..N
"""
n = cites.shape[0]
p = np.array(cites, dtype=np.float64)
alpha = 0.1
for i in range(n):
p[i, :] = p[i, :] * (1 - alpha) + np.ones((1, n)) * alpha
p[i, :] /= np.sum(p[i, :])
a = np.ones((n, n))
for i in range(50):
p = np.dot(p, p)
(CACHE_DIR / 'pagerank.progress').write_text('{}%'.format(i * 2 + 2))
a = np.dot(a, p)
return a
if __name__ == '__main__':
pubs = es._get_all_publications()
ranks = get_rank(pubs)
es.update_ranks(pubs, ranks)
es.refresh()
print(es._get_all_publications()[20]['rank'])
def _get_rank(cites):
"""
:param cites: np.array presenting citation of i -> j
:return: array of page ranks
indices are assumed 0..N
"""
n = cites.shape[0]
p = np.array(cites, dtype=np.float64)
alpha = 0.1
for i in range(n):
p[i, :] = p[i, :] * (1 - alpha) + np.ones((1, n)) * alpha
p[i, :] /= np.sum(p[i, :])
a = np.ones((n, n))
for i in range(50):
p = np.dot(p, p)
(CACHE_DIR / "pagerank.progress").write_text("{}%".format(i * 2 + 2))
a = np.dot(a, p)
return a
if __name__ == "__main__":
pubs = es._get_all_publications()
ranks = get_rank(pubs)
es.update_ranks(pubs, ranks)
es.refresh()
print(es._get_all_publications()[20]["rank"])
