Spam vs. Ham
In the Spam vs. Ham project, the goal is to create a classifier capable of distinguishing spam emails from legitimate ones (ham).
Overview
In the Spam vs. Ham project, the goal is to create a classifier capable of distinguishing spam emails from legitimate ones (ham).
Description
- The project involves feature engineering, logistic regression, and cross-validation techniques to develop an effective spam detection model
- Created classifier that can distinguish between spam emails from ham (non-spam) emails using feature engineering and logistic regression with text data and sklearn to fit models
- Achieved 90% accuracy on a 1000 email test set
Skills Developed:
- Extracting relevant features from text data
- Cleaning and preprocessing text data for analysis
- Implementing a classification algorithm for spam detection
- Evaluating model performance and avoiding overfitting