Update app.py

app.py

@@ -5,47 +5,26 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.naive_bayes import MultinomialNB
 import joblib
 import gradio as gr
-import datasets
-
-
-dataset_true = datasets.load_dataset('csv', data_files='True.csv', split='train')
-dataset_fake = datasets.load_dataset('csv', data_files='Fake.csv', split='train')
-
-
-df_combined = pd.concat([pd.DataFrame(dataset_true), pd.DataFrame(dataset_fake)])
-
-
-df_combined['label'] = df_combined['label'].astype(int)
-
-
+df_true['label'] = 1
+df_fake['label'] = 0
+df_combined = pd.concat([df_true, df_fake])
 X = df_combined['text']
 y = df_combined['label']
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-
-
 tfidf_vectorizer = TfidfVectorizer(max_features=5000)
 X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)
 X_test_tfidf = tfidf_vectorizer.transform(X_test)
-
-
 clf = MultinomialNB()
 clf.fit(X_train_tfidf, y_train)
-
-
 accuracy = clf.score(X_test_tfidf, y_test)
 print("Model Accuracy:", accuracy)
-
-
 joblib.dump(clf, 'fake_news_classifier_model.pkl')
 joblib.dump(tfidf_vectorizer, 'tfidf_vectorizer.pkl')
-
- 
 def predict_fake_or_true_news(text):
     text_tfidf = tfidf_vectorizer.transform([text])
     prediction = clf.predict(text_tfidf)
     return "True" if prediction[0] == 1 else "Fake"
 
-
 iface = gr.Interface(
     fn=predict_fake_or_true_news,
     inputs="text",
@@ -55,5 +34,4 @@ iface = gr.Interface(
     description="Enter a news article text to classify as 'Fake' or 'True'."
 )
 
-
 iface.launch()