Learn how to implement XGBoost in Python from start to finish in this comprehensive 57-minute tutorial. Begin with importing necessary modules and data, then explore techniques for identifying and handling missing data. Dive into data formatting, including creating X and y variables and performing one-hot encoding. Discover how XGBoost handles missing data and one-hot encoded features. Build a preliminary XGBoost model, optimize parameters using cross-validation with GridSearchCV, and finally construct and visualize the final XGBoost model. Gain practical insights into machine learning techniques and boost your data science skills through this hands-on guide.
Overview
Syllabus
Awesome song and introduction
Import Modules
Import Data
Missing Data Part 1: Identifying
Missing Data Part 2: Dealing with it
Format Data Part 1: X and y
Format Data Part 2: One-Hot Encoding
XGBoost - Missing Data and One-Hot Encoding
Build a Preliminary XGBoost Model
Optimize Parameters with Cross Validation GridSearchCV
Build and Draw Final XGBoost Model
Taught by
StatQuest with Josh Starmer
