Update app.py

app.py

@@ -2,10 +2,12 @@ import gradio as gr
 import nltk
 from sklearn.feature_extraction.text import CountVectorizer 
 from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.preprocessing import StandardScaler
 import joblib
 from nltk.stem.porter import PorterStemmer
 from nltk.corpus import stopwords
 import re
+import numpy as np
 
 nltk.download('stopwords')
 
@@ -14,6 +16,7 @@ nltk.download('stopwords')
 # warnings.filterwarnings("ignore", category=InconsistentVersionWarning)
 
 ps = PorterStemmer()
+scaler = StandardScaler()
 
 def preprocess_for_bow_and_tfidf(text):
     corpus = []
@@ -24,11 +27,35 @@ def preprocess_for_bow_and_tfidf(text):
     corpus.append(' '.join(text))
 
     return corpus
+
+def preprocess_for_word2vec(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(text)
+
+def average_word_vectors(words, model, vocabulary, num_features):
+    feature_vector = np.zeros((num_features,), dtype="float64")
+    nwords = 0.
+    
+    for word in words:
+        if word in vocabulary:
+            nwords = nwords + 1.
+            feature_vector = np.add(feature_vector, model.wv[word])
+    
+    if nwords:
+        feature_vector = np.divide(feature_vector, nwords)
+        
+    return feature_vector
     
 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')
+word2vec_model = joblib.load('./word2vec_model.pkl')
+svm_classifier = joblib.load('./svm_classifier.pkl')
 
 def classify(text,choice):
   corpus=[text]
@@ -36,16 +63,29 @@ def classify(text,choice):
       corpus = preprocess_for_bow_and_tfidf(text)
       features = vectorizer.transform(corpus).toarray()
       prediction = nb_classifier.predict(features)
+      
   elif(choice == 2):
       corpus = preprocess_for_bow_and_tfidf(text)
       features = tfidf_vectorizer.transform(corpus).toarray()
       prediction = random_forest.predict(features)
+      
+  elif(choice == 3):
+      corpus = preprocess_for_word2vec(text)
+      X = [average_word_vectors(title, word2vec_model, word2vec_model.wv.key_to_index, 100) for title in corpus]
+      X = np.array(X)
+      X = scaler.transform(X)
+      prediction = svm_classifier.predict(X)
+      
+      
   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") ],
+    inputs = [
+    gr.Textxox(label = "Input" , placeholder = "Enter News Title here"),
+    gr.Radio( choices = [("Naive Bayes",1) , ("Random Forest",2) , ("Support Vector Machine",3) ] , value = 1 , label = "Model") ],
     outputs = ['text'],
     fn = classify,
     title = "Fake News Detection System"