myClassify.py

import nltk
import csv
import pickle
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords

class Analise (object):
    def __init__(self):
        self.stop_words = set(stopwords.words("portuguese"))
        self.dataPath_treino = 'output.txt'
        self.stopwordsnltk = nltk.corpus.stopwords.words('portuguese')

    def getBaseTeste(self):
        dados = []

        with open(self.dataPath_teste, 'r', encoding="utf8") as file:
            reader = csv.reader(file)
            for row in reader:
                dados.append((row[0], row[1]))
        return dados

    def getBase(self):
        dados = []

        with open(self.dataPath_treino, 'r', encoding="utf8") as file:
            reader = csv.reader(file)
            for row in reader:
                dados.append((row[0],row[1]))
        return dados

    def removerStopWords(self,texto):
        frases_stop = []
        for(palavras,emocao) in texto:
            frase = ' '.join([word for word in word_tokenize(palavras) if word not in self.stop_words])
            frases_stop.append((frase,emocao))
        return frases_stop

    def aplicastemmer(self,texto):
        stemmer = nltk.stem.RSLPStemmer()
        frasesstemming =[]
        for (palavras,emocao) in texto:
            comstemming = [str(stemmer.stem(p)) for p in palavras.split() if p not in self.stopwordsnltk]
            frasesstemming.append((comstemming,emocao))
        return frasesstemming