In [ ]:

    

from gensim import corpora, models, similarities
from gensim.utils import simple_preprocess
import pandas as pd

class MyCorpus(object):
    
    def __init__(self,path):
        self.data = pd.read_csv(path, sep="\t", header=0, index_col=0)
        self.data = self.data.drop_duplicates()
    
    def __iter__(self):
        for sent in self.data['tweet']:
            yield self.pre_process(sent)
    
    def pre_process(self,text):
        return simple_preprocess(str(text))


    

In [ ]:

    

mc = MyCorpus('Bases/Prontas/superbow/sentic.patter.en-superbow2013-2.txt')


    

In [ ]:

    

dictionary = corpora.Dictionary(mc)
corpus = [dictionary.doc2bow(text) for text in mc]
tfidf = models.TfidfModel(corpus)
tfidf_corpus = tfidf[corpus]


    

In [ ]:

    

import networkx as nx

G = nx.DiGraph()

# cada texto é um nó do grafo
# a classe do texto é um atributo do nó do grafo
for row in mc.data.itertuples():
    G.add_node(row.Index,klass=row.sentiment)


    

In [ ]:

    

index = similarities.Similarity('tmp',tfidf_corpus,num_features=len(dictionary.keys()),num_best=11)
names = mc.data.index


    

In [ ]:

    

for item in index[tfidf_corpus]:
    if len(item) > 0:
        k = names[item[0][0]]
        for nn in item[1:]:
            G.add_edge(k,names[nn[0]],weight=nn[1])