%matplotlib inline
from matplotlib import pyplot

from bulbs.rexster import Graph, Config, REXSTER_URI

REXSTER_URI = 'http://localhost:8182/graphs/plos'
config = Config(REXSTER_URI)

g = Graph(config)

# Bulbs Models
from bulbs.model import Node, Relationship
from bulbs.property import String, Integer, DateTime, List

class Author(Node):
    element_type = 'author'
    name = String(nullable=False)
    
class Article(Node):
    element_type = 'article'
    title = String(nullable=False)
    published = DateTime()
    doi = String()
    
class Authorship(Relationship):
    label = 'authored'

class Citation(Relationship):
    label = 'cites'
    reference_count = Integer(nullable=False)
    tag = String()

g.add_proxy('authors', Author)
g.add_proxy('articles', Article)
g.add_proxy('authored', Authorship)
g.add_proxy('cites', Citation)

nodes = g.V
edges = g.E

authors = {n.name: n for n in nodes if n.element_type == 'author'}

authors.keys()[:10]

articles = {n.doi: n for n in nodes if n.element_type == 'article'}

articles.keys()[:10]

len(articles.keys())

article = articles['10.1371/journal.pbio.1000584']

article.title

list(article.inE())

for author in article.inV():
    print author.name

list(article.outE())

for citation in article.outV():
    print citation.title
    print [n.name for n in citation.inV() if n.element_type == 'author']
    print citation.doi

sum(1 for n in nodes if n.element_type == 'article' and n.outV() > 0)

for citation in article.outE():
    print citation.reference_count

citation_counts = []
for doi in articles.keys():
    if articles[doi].outE():
        for e in articles[doi].outE():
            if e.label == 'cites':
                citation_counts.append(e.reference_count)

pyplot.hist(citation_counts, bins=range(20))
pyplot.xlabel('number of times cited')
pyplot.ylabel('count')

def article_pp(article):
    authors = unicode(', '.join([n.name for n in article.inV() if n.element_type == 'author']))
    s = ('Title: %s\n'
        'Authors: %s\n'
        'DOI: %s' % (article.title, authors, article.doi))
    
    return s

for edge in edges:
    if edge.label == 'cites':
        if edge.reference_count >= 21:
            print('Citer:')
            print(article_pp(edge.outV()))
            print('')
            print('Citee')
            print(article_pp(edge.inV()))
            print('')
            print('Citer cites citee %d times.' % edge.reference_count)
            print('-----------------------------------------------------')

def are_different_authors(article_1, article_2):
    authors_1 = []
    authors_2 = []
    
    for n in article_1.inV():
        if n.element_type == 'author':
            authors_1.append(n.name)
    for n in article_2.inV():
        if n.element_type == 'author':
            authors_2.append(n.name)
            
    authors_1 = set(authors_1)
    authors_2 = set(authors_2)
    
    return len(authors_1.intersection(authors_2)) == 0


citation_counts = []

for edge in edges:
    if edge.label == 'cites':
        if are_different_authors(edge.inV(), edge.outV()):
            citation_counts.append(edge.reference_count)

pyplot.hist(citation_counts, bins=range(20))
pyplot.xlabel('number of times cited')
pyplot.ylabel('count')

for edge in edges:
    if edge.label == 'cites':
        if edge.reference_count >= 16 and are_different_authors(edge.inV(), edge.outV()):
            print('Citer:')
            print(article_pp(edge.outV()))
            print('')
            print('Citee')
            print(article_pp(edge.inV()))
            print('')
            print('Citer cites citee %d times.' % edge.reference_count)
            print('-----------------------------------------------------')

inspirators = []

for article in articles.values():
    in_nodes = []
    if article.inE():
        for edge in article.inE():
            if edge.label == 'cites':
                if are_different_authors(edge.inV(), edge.outV()) and edge.reference_count >= 3:
                    in_nodes.append([edge.outV(), edge.reference_count])
                    
    if len(in_nodes) >= 3:
        inspirators.append([article, in_nodes])

len(inspirators)

for inspirator in inspirators:
    print('Inspirator')
    print article_pp(inspirator[0])
    print('')
    for el in inspirator[1]:
        print('Inspired Article')
        print article_pp(el[0])
        print('Cites inspirator %d times.' % el[1])
        print('')
    print('--------------------------------------')
    print('')