Update app.py

app.py

@@ -1,3 +1,4 @@
+
 import pandas as pd
 from sklearn.model_selection import train_test_split
 from sklearn.feature_extraction.text import TfidfVectorizer
@@ -5,35 +6,23 @@ from sklearn.naive_bayes import MultinomialNB
 import joblib
 import gradio as gr
 import datasets
-
-df_true_raw = datasets.load_dataset('csv', data_files='True.csv', split='train')['text']
-df_fake_raw = datasets.load_dataset('csv', data_files='Fake.csv', split='train')['text']
-
-df_true = pd.DataFrame(df_true_raw)
-df_fake = pd.DataFrame(df_fake_raw)
-
+df_true = datasets.load_dataset('csv', data_files='True.csv')
+df_fake = datasets.load_dataset('csv', data_files='Fake.csv')
 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)
@@ -49,4 +38,3 @@ iface = gr.Interface(
 )
 
 iface.launch()
-