main.py

# Import necessary libraries
import pandas as pd
import numpy as np
import re
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

# Load the datasets
fake_df = pd.read_csv('dataset/Fake.csv')  # Path to your fake news file
true_df = pd.read_csv('dataset/True.csv')  # Path to your true news file

# Add a label column: 1 for fake news and 0 for true news
fake_df['label'] = 1
true_df['label'] = 0

# Combine the two datasets
df = pd.concat([fake_df, true_df], ignore_index=True)

# Display the first few rows
print(df.head())

# Preprocess text data
def preprocess_text(text):
    text = text.lower()  # Lowercase
    text = re.sub(r'[^a-zA-Z\s]', '', text)  # Remove special characters
    return text

# Apply preprocessing to the text column
df['text'] = df['text'].apply(preprocess_text)

# Define target and features
X = df['text']
y = df['label']

# Split data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Initialize TF-IDF Vectorizer
tfidf_vectorizer = TfidfVectorizer(max_features=5000)  # Limit features for simplicity

# Fit and transform the data
X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)
X_test_tfidf = tfidf_vectorizer.transform(X_test)

# Initialize and train the model
model = MultinomialNB()
model.fit(X_train_tfidf, y_train)

# Make predictions
y_pred = model.predict(X_test_tfidf)

# Calculate accuracy
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy:.2f}')

# Classification report
print("Classification Report:\n", classification_report(y_test, y_pred))

# Confusion Matrix
print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))

def model_details():
    print("Model: Naive Bayes Classifier")
    print(f"Accuracy: {accuracy:.2f}")
    print("Classification Report:\n", classification_report(y_test, y_pred))
    print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))

# Call the model details function
model_details()