import gradio as gr
import nltk
from sklearn.feature_extraction.text import CountVectorizer 
from sklearn.feature_extraction.text import TfidfVectorizer
import joblib
from nltk.stem.porter import PorterStemmer
from nltk.corpus import stopwords
import re

nltk.download('stopwords')

# import warnings
# from sklearn.exceptions import InconsistentVersionWarning
# warnings.filterwarnings("ignore", category=InconsistentVersionWarning)

ps = PorterStemmer()

def preprocess_for_bow_and_tfidf(text):
    corpus = []
    text = re.sub('[^a-zA-Z0-9$£€¥%]',' ',text)
    text = text.lower()
    text = text.split()
    text = [ps.stem(t) for t in text if t not in stopwords.words('english')]
    corpus.append(' '.join(text))

    return corpus
    
vectorizer = joblib.load('./vectorizer.pkl')
nb_classifier = joblib.load('./nb_classifier.pkl')
tfidf_vectorizer = joblib.load('./tfidf_vectorizer.pkl')
random_forest = joblib.load('./random_forest.pkl')

def classify(text,choice):
  corpus=[text]
  if(choice == 1):
      corpus = preprocess_for_bow(text)
      features = vectorizer.transform(corpus).toarray()
      prediction = nb_classifier.predict(features)
  elif(choice == 2):
      corpus = preprocess_for_bow_and_tfidf
      features = tfidf_vectorizer.transform(corpus).toarray()
      prediction = random_forest.predict(features)
  if(prediction == 1):
     return "Fake News"
  else:
     return "Not Fake News"
GUI = gr.Interface(
    inputs = ['text', gr.Radio( choices = [("Naive Bayes",1) , ("Random Forest",2) ] , value = 1 , label = "Model") ],
    outputs = ['text'],
    fn = classify,
    title = "Fake News Detection System"
)
GUI.launch(debug = True)