validation_steps.py

import nltk
import csv
import pickle
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from sklearn.naive_bayes import MultinomialNB 
from myclassify import Analise
from pandas import DataFrame
import numpy
from sklearn.feature_extraction.text import CountVectorizer

#Here we have the validation steps and a way to load the classifier.

#Load classifier and vectorizer
with open('classifier.pickle', 'rb') as handle:
    classifier = pickle.load(handle)

with open('count_vectorizer.pickle', 'rb') as handle:
    count_vectorizer = pickle.load(handle)

dados = []
x = []
y = []
with open('output_results_processed.txt','r',encoding='utf8') as file:
    reader = csv.reader(file)
    for row in reader:
        dados.append((row[0],row[1]))
        

preprocessor = Analise()
preprocessor.stop_words = set(stopwords.words("portuguese"))
preprocessor.stopwordsnltk = nltk.corpus.stopwords.words('portuguese')


classification_data = preprocessor.removerStopWords(dados)
classification_data = preprocessor.aplicastemmer(classification_data)

x = []
for item in classification_data:
    frase = ""
    for witem in item[0]:
        frase += witem + " "
    x.append(frase)

y = []
for item in classification_data:
    y.append(item[1])


## Classification
teste = x 
teste_counts = count_vectorizer.transform(teste)
predictions = classifier.predict(teste_counts)
predictions

markups = y 
diferencas = predictions == markups
acertos = [a for a in diferencas if a]
rate = 100.0 * len(acertos)/len(predictions)
rate

#scikit-metrics (Use this one)
from sklearn.metrics import classification_report
target_names = ['Class 0 (neutro)','Class 1 (neg)']
print(classification_report(markups,predictions,target_names=target_names))

#Metodo antigo
#from sklearn.metrics import recall_score
#from sklearn.metrics import precision_score
## Precision, recall
# recall
#round(100*recall_score(markups, predictions,average='macro'),3)
#round(100*recall_score(markups, predictions,average='micro'),3)
#round(100*recall_score(markups, predictions,average='weighted'),3)
#recall_score(markups, predictions,average=None)
# precision

#round(100*precision_score(markups, predictions, average='macro'),3)
#round(100*precision_score(markups, predictions,average='micro'),3)
#round(100*precision_score(markups, predictions,average='weighted'),3)
#precision_score(markups, predictions,average=None)