Logistic Regression 101: US Household Income Classification

This hands-on project will teach Logistic Regression as well as XGBoost models how to predict whether a person earns less or more than 50,000 US dollars annually. The data comes from the U.S. Census database. It includes features such as occupation, age and native country. You will be able: - To understand the theory and intuition behind Logistic Regression models and XGBoost models - To import key Python libraries and datasets and to perform Exploratory Data Analysis such as removing missing values and replacing characters. - Perform data visualization using Seaborn. - Prepare the data for Machine Learning models using One-Hot Coding, Label Encoding and Train/Test Split. - Create and train Logistic Regression models and XGBoost models to classify U.S. Household's Income Bracket. - Evaluate the performance of the trained model and verify its generalization with various KPIs like accuracy, precision, recall.