import math
from tslearn.clustering import TimeSeriesKMeans
from sklearn.metrics import mean_absolute_error
from sklearn.cluster import KMeans
from paper_class import paper
papers = {}
with open("datasets_inUse/paper_ids.txt", "r", encoding="utf8") as file:
pid = 0
for i in file.readlines():
l = i.split()
# making the entire title sentence
title = ' '.join(l[1:len(l) - 1])
# paper id pid is increasing values of 1 with eveyr loop
papers[l[0]] = paper(pid, l[0], title, l[-1], "", "")
pid += 1
with open("datasets_inUse/acl-metadata.txt", "r", encoding="utf8") as file:
pid = 0
flag = False
ID = 0
for i in file.readlines():
#print(i)
l = i.split('=')
if (flag):
if (l[0] == "author "):
l[1] = l[1].strip()
auth = l[1][1:-1]
#print(auth)
papers[ID].author = auth
from paper_class import paper
import copy
import nimfa
paper_id={}
id_paper={}
inverse_id={}
with open("datasets_inUse/paper_ids.txt","r", encoding="utf8") as file:
pid=0
for i in file.readlines():
l=i.split()
# making the entire title sentence
title=' '.join(l[1:len(l)-1])
# paper id pid is increasing values of 1 with eveyr loop
obj=paper(pid, l[0], title, l[-1],[],"")
paper_id[l[0]]=obj
id_paper[pid]=obj
inverse_id[pid]=l[0]
pid+=1
#%%
with open("datasets_inUse/acl-metadata.txt","r", encoding="utf8") as file:
pid=0
paper=""
for i in file.readlines():
if(i!='\n'):
l=i.split('=')
if(l[0]=="id "):
l[1]=l[1].strip()
paper=l[1][1:-1]
if(l[0]=="author "):