def processar(self):
strategyTF = tf_class.DoubleNormalization()
# print('\nprocessar ', strategyTF, '\n')
self.tf = {}
self.logNormalization = {}
self.doubleNormalization = {}
for word in self.tokens:
# termo = Termo()
frequency = self.tokens[word]
self.tokens[word] = strategyTF.calcPeso(frequency, self)
self.tf[word] = strategyTF.calcPeso(frequency, self)
self.logNormalization[word] = tf_class.LogNormalization().calcPeso(
frequency, self)
self.doubleNormalization[word] = tf_class.DoubleNormalization(
).calcPeso(frequency, self)
def processar(self, colecao):
strategyTF = self.instanciar(tf, colecao.algoritmo['tf'])
# print('\t\tprocessar ', strategyTF)
# strategyIDF = self.instanciar(idf_class, strategyIDF)
# strategyTFIDF = self.instanciar(tfidf_class, strategyTFIDF)
# print(self.tokens)
for word in self.tokens:
# termo = Termo()
frequency = self.tokens[word]
# termo.tf = strategyTF.calcularPeso(termo, self)
# termo.idf = idf = strategyIDF.calcularPeso(termo, listaDocumentos)
# termo.tfIdf = termo.tf * termo.idf
self.tf[word] = strategyTF.calcPeso(frequency, self)
self.logNormalization[word] = tf.LogNormalization().calcPeso(
frequency, self)
self.doubleNormalization[word] = tf.DoubleNormalization().calcPeso(
frequency, self)
if (word in colecao.qtTermoDocumento):
colecao.qtTermoDocumento[word] += 1
else:
colecao.qtTermoDocumento[word] = 1
if not (word in colecao.listTermosColecao):
colecao.listTermosColecao.append(word)