app.py

app.py

@@ -0,0 +1,92 @@
+import gradio as gr
+import pandas as pd
+import re
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.preprocessing import LabelBinarizer
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score, f1_score
+
+# Define your functions and logic here
+def load_and_prepare_data():
+    try:
+        file_path = 'WELFake_Dataset.csv'  # Ensure this is the correct path
+        dataset = pd.read_csv(file_path)
+        print(f"Dataset loaded with {dataset.shape[0]} records")
+        dataset = dataset.drop(columns=['Unnamed: 0'])
+        dataset = dataset.dropna(subset=['title', 'text'])
+        dataset['clean_text'] = dataset['text'].apply(clean_text)
+        print(f"Dataset cleaned. Records after cleaning: {dataset.shape[0]}")
+        return dataset
+    except Exception as e:
+        return f"Error loading and preparing data: {e}"
+
+def clean_text(text):
+    try:
+        text = re.sub(r'\W', ' ', text)
+        text = re.sub(r'\s+', ' ', text)
+        text = re.sub(r'\d', '', text)
+        text = text.lower().strip()
+        return text
+    except Exception as e:
+        return f"Error cleaning text: {e}"
+
+def train_model(dataset):
+    try:
+        X_train, X_test, y_train, y_test = train_test_split(dataset['clean_text'], dataset['label'], test_size=0.2, random_state=42)
+        print(f"Training data size: {X_train.shape[0]}, Test data size: {X_test.shape[0]}")
+        
+        vectorizer = TfidfVectorizer(max_features=10000)
+        X_train_tfidf = vectorizer.fit_transform(X_train)
+        X_test_tfidf = vectorizer.transform(X_test)
+        
+        lb = LabelBinarizer()
+        y_train_binary = lb.fit_transform(y_train)
+        y_test_binary = lb.transform(y_test)
+        
+        log_reg_model = LogisticRegression(max_iter=1000)
+        log_reg_model.fit(X_train_tfidf, y_train)
+        
+        y_pred_log_reg_train = log_reg_model.predict(X_train_tfidf)
+        train_accuracy_log_reg = accuracy_score(y_train, y_pred_log_reg_train)
+        train_f1_log_reg = f1_score(y_train, y_pred_log_reg_train)
+        
+        y_pred_log_reg = log_reg_model.predict(X_test_tfidf)
+        accuracy_log_reg = accuracy_score(y_test, y_pred_log_reg)
+        f1_log_reg = f1_score(y_test, y_pred_log_reg)
+        
+        print(f"Train Accuracy: {train_accuracy_log_reg}, Train F1 Score: {train_f1_log_reg}")
+        print(f"Test Accuracy: {accuracy_log_reg}, Test F1 Score: {f1_log_reg}")
+        
+        return vectorizer, lb, log_reg_model, accuracy_log_reg, f1_log_reg
+    except Exception as e:
+        return f"Error training model: {e}"
+
+def fake_news_detection(text):
+    try:
+        dataset = load_and_prepare_data()
+        if isinstance(dataset, str):  # Check if there was an error in loading data
+            return dataset
+        vectorizer, lb, log_reg_model, accuracy_log_reg, f1_log_reg = train_model(dataset)
+        if isinstance(vectorizer, str):  # Check if there was an error in training models
+            return vectorizer
+        
+        clean_text_input = clean_text(text)
+        text_tfidf = vectorizer.transform([clean_text_input])
+        prediction = log_reg_model.predict_proba(text_tfidf)
+        result = "Real" if prediction[0][1] >= 0.5 else "Fake"
+        
+        return f"Prediction: {result}"
+    except Exception as e:
+        return f"Error in fake news detection: {e}"
+
+iface = gr.Interface(
+    fn=fake_news_detection, 
+    inputs=gr.Textbox(lines=2, placeholder="Enter news text here..."), 
+    outputs="text",
+    title="Fake News Detector",
+    description="Enter a news headline or article text to check if it is fake or real."
+)
+
+if __name__ == "__main__":
+    iface.launch()