Detecting email spam or ham using logistic regression and stremlit depolyment

Abstract

The use of email as a key form of communication has led to an increase in uninvited and potentially hazardous spam messages. This study presents a comprehensive approach to classifying emails as either spam or ham using logistic regression. Leveraging a dataset obtained from Kaggle, we performed extensive exploratory data analysis (EDA) with visualizations such as pie charts, bar plots, and confusion matrices. Using performance parameters like accuracy, precision, recall, and F1 score, the model's potential for prediction was assessed. In order to facilitate smooth interaction for real-time email classification, Streamlit was also used to develop an intuitive application. This work demonstrates the utility of logistic regression in tackling the spam problem while paving the way for further exploration using advanced machine learning models.