def generate(self, edgeCount, tfidf = False, window_size = 0, degree = False, closeness = False, groups= False):
parser = XMLDataframeParser()
text = parser.getText("./data/smokingRecords.xml")
parser.addFeatureFromText(text, "HISTORY OF PRESENT ILLNESS :", "", True, True, "illness")
df = parser.getDataframe()
df_xml = parser.removeEmptyEntries(df, "illness")
normalizer = Normalizer()
if tfidf:
if window_size == 0:
vectorizer = TfidfVectorizer(tokenizer = lambda text: normalizer.normalize(text, True, False), ngram_range = (2, 2))
mostFreq2Grams = self.get_first_n_words(vectorizer, df_xml.illness, edgeCount)
else:
vectorizer = TfidfVectorizer(analyzer = lambda text: self.custom_analyser(text, 2, int(window_size)))
mostFreq2Grams = self.get_first_n_words(vectorizer, normalizer.normalizeArray(df_xml.illness, True, False), edgeCount)
else:
if window_size == 0:
vectorizer = CountVectorizer(tokenizer = lambda text: normalizer.normalize(text, True, False), ngram_range = (2, 2))
mostFreq2Grams = self.get_first_n_words(vectorizer, df_xml.illness, edgeCount)
else:
vectorizer = CountVectorizer(analyzer = lambda text: self.custom_analyser(text, 2, int(window_size)))
mostFreq2Grams = self.get_first_n_words(vectorizer, normalizer.normalizeArray(df_xml.illness, True, False), edgeCount)
df_graph = self.create_dataframe(mostFreq2Grams)
GF = nx.from_pandas_edgelist(df_graph, 'Node1', 'Node2', ["Weight"])
if degree:
# calculate degree centrality
degree_centrality = nx.degree_centrality(GF)
nx.set_node_attributes(GF, degree_centrality, "degree_centrality")
if closeness:
# calculate closeness centrality
closeness_centrality = nx.closeness_centrality(GF)
nx.set_node_attributes(GF, closeness_centrality, "closeness_centrality")
if groups:
# calculate partitions
partition = community.best_partition(GF)
nx.set_node_attributes(GF, partition, "group")
payload = json_graph.node_link_data(GF)
return payload
