

In [4]:

    
import json

with open("data/super_data_3.json", "r") as f:
    super_data = json.load(f)

p_data=super_data['papers']
del super_data['markov_ranks']
del super_data['index_phrase']

for p in p_data:
    del p['abstract']
    del p['prop_group']
    del p['pid']
    del p['prop_ratio']
    del p['phrases']
    del p['detc']
    del p['actual_ratio']
    del p['broad_topic']
    del p['phrases_size']
    del p['topics']
    del p['cited_by']
    del p['cited_by_sim']
    del p['all_cite_sim']
    del p['citations_sim']
    del p['markov_rank']
    del p['author_ids']

print p_data[790]
import os
path = "data/super_data_4.json" 
if(os.path.isfile(path)): 
    os.remove(path) 
with open(path, "w") as f: 
    json.dump(super_data, f)









    



{u'year': 2008, u'all_cite': [u'441', u'537', u'664'], u'index': u'790', u'title': u'An Efficient Re-Analysis Methodology for Probabilistic Vibration of Large-Scale Structures', u'edge_set': [441, 537, 664], u'citations': [], u'bayes_rank': 4.346697600581699, u'ppm_index': 21, u'authors': [u'Geng Zhang', u'Efstratios Nikolaidis', u'Zissimos P. Mourelatos'], u'url': u'http://proceedings.asmedigitalcollection.asme.org//proceeding.aspx?articleID=1627303', u'louvain_index': 20}