def main():
import time
import datetime
c = DataCenterClient("tcp://10.1.1.211:32011")
x = c.searchPublications("data mining")
data_fields = ["id", "mid", "uid",
"parent", "type", "t",
"user_created_at", "followers_count", "statuses_count",
"friends_count", "username", "text", "words", "verified", "emotion"];
items = []
for p in x.publications:
au = "0"
if len(p.author_ids) > 0:
au = p.author_ids[0]
dt = datetime.datetime(p.year, 1, 1, 1, 1)
t = int(time.mktime(dt.timetuple()))
children = []
parents = []
for x in p.cited_by_pubs:
children.append(str(x))
y = [str(p.id), str(p.id), str(au), children, 0,
t, t, p.n_citations,
p.n_citations, p.n_citations, p.authors, p.title, "hello,world"]
items.append(y)
import json
dump = open("pubs_dump.json","w")
d = json.dumps(items)
dump.write(d)
dump.close()
import pickle
terms = pickle.load(open("..\\static\\pickle\\terms_dump_all.pickle"))
def main():
import time
import datetime
c = DataCenterClient("tcp://10.1.1.211:32011")
x = c.searchPublications("data mining")
data_fields = ["id", "mid", "uid",
"parent", "type", "t",
"user_created_at", "followers_count", "statuses_count",
"friends_count", "username", "text", "words", "verified", "emotion"];
items = []
for p in x.publications:
au = "0"
if len(p.author_ids) > 0:
au = p.author_ids[0]
dt = datetime.datetime(p.year, 1, 1, 1, 1)
t = int(time.mktime(dt.timetuple()))
children = []
parents = []
for x in p.cited_by_pubs:
children.append(str(x))
y = [str(p.id), str(p.id), str(au), children, 0,
t, t, p.n_citations,
p.n_citations, p.n_citations, p.authors, p.title, "hello,world"]
items.append(y)
import json
dump = open("pubs_dump.json","w")
d = json.dumps(items)
dump.write(d)
dump.close()
import pickle
terms = pickle.load(open("..\\static\\pickle\\terms_dump_all.pickle"))
def getCitationNetwork():
import time
import datetime
from collections import defaultdict
c = DataCenterClient("tcp://10.1.1.211:32011")
x = c.searchPublications("deep learning")
data_fields = [
"id", "mid", "uid", "parent", "type", "t", "user_created_at",
"followers_count", "statuses_count", "friends_count", "username",
"text", "words", "verified", "emotion"
]
items = []
cite_pubs = []
key_terms = defaultdict(int)
year_terms = defaultdict(lambda: defaultdict(int))
for p in x.publications:
if p.year <= 1970:
continue
item, children, parents, kt = extractPublication(p)
if len(children) > 0:
items.append(item)
cite_pubs.extend(children)
cite_pubs.extend(parents)
for k in kt:
key_terms[k.lower()] += 1
year_terms[p.year][k.lower()] += 1
cite_pubs = list(set(cite_pubs))
x = c.getPublicationsById(cite_pubs)
for p in x.publications:
if p.year <= 1970:
continue
item, children, parents, kt = extractPublication(p)
if len(children) > 0 and len(children) > 0:
items.append(item)
cite_pubs.extend(children)
for k in kt:
key_terms[k.lower()] += 1
year_terms[p.year][k.lower()] += 1
sorted_key_terms = sorted(key_terms.items(),
key=lambda x: x[1],
reverse=True)
import json
dump = open("pubs_dump.json", "w")
d = json.dumps(items)
dump.write(d)
dump.close()
def getCitationNetwork():
import time
import datetime
from collections import defaultdict
c = DataCenterClient("tcp://10.1.1.211:32011")
x = c.searchPublications("deep learning")
data_fields = ["id", "mid", "uid",
"parent", "type", "t",
"user_created_at", "followers_count", "statuses_count",
"friends_count", "username", "text", "words", "verified", "emotion"];
items = []
cite_pubs = []
key_terms = defaultdict(int)
year_terms = defaultdict(lambda: defaultdict(int))
for p in x.publications:
if p.year <= 1970:
continue
item, children, parents, kt = extractPublication(p)
if len(children) > 0:
items.append(item)
cite_pubs.extend(children)
cite_pubs.extend(parents)
for k in kt:
key_terms[k.lower()] += 1
year_terms[p.year][k.lower()] += 1
cite_pubs = list(set(cite_pubs))
x = c.getPublicationsById(cite_pubs)
for p in x.publications:
if p.year <= 1970:
continue
item, children, parents, kt = extractPublication(p)
if len(children) > 0 and len(children) > 0:
items.append(item)
cite_pubs.extend(children)
for k in kt:
key_terms[k.lower()] += 1
year_terms[p.year][k.lower()] += 1
sorted_key_terms = sorted(key_terms.items(), key=lambda x: x[1], reverse=True)
import json
dump = open("pubs_dump.json", "w")
d = json.dumps(items)
dump.write(d)
dump.close()
