import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
 
Load the dataset
data = pd.read_csv('fake_news.csv')
 
Extract the features and labels
X = data['text']
y = data['label']
 
Convert text to numerical features
vectorizer = CountVectorizer()
X_vectorized = vectorizer.fit_transform(X)
 
Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X_vectorized, y, test_size=0.2, random_state=42)
 
Train the logistic regression model
model = LogisticRegression()
model.fit(X_train, y_train)
 
Evaluate the model
y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy:.2f}')
 

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