Description
Course info
Level
Intermediate
Updated
Aug 7, 2019
Duration
2h 2m
Description

Are you a data professional who needs a complete, end-to-end classification demonstration of XGBoost and the libraries surrounding it? In this course, Applied Classification with XGBoost, you'll get introduced to the popular XGBoost library, an advanced ML tool for classification and regression. First, you'll explore the underpinnings of the XGBoost algorithm, see a base-line model, and review the decision tree. Next, you'll discover how boosting works using Jupyter Notebook demos, as well as see preliminary exploratory data analysis in action. Finally, you'll learn how to create, evaluate, and explain data using third party libraries. You won't be using the Iris or Titanic data-set, you'll use real survey data! By the end of this course, you'll be able to take raw data, prepare it, model a classifier, and explore the performance of it. Using the provided notebook, you can follow along on your own machine, or take and adapt the code to your needs.

About the author
About the author

Matt Harrison runs MetaSnake, a Python and Data Science consultancy and corporate training shop. He is the author of best selling Python books. He blogs at ``hairysun.com`` and occasionally tweets useful Python related information at ``@__mharrison__``

Section Introduction Transcripts
Section Introduction Transcripts

Course Overview
Hey everyone. Matt Harrison here, Python and data science corporate trainer at MetaSnake and author of the new course Applied Classification with XGBoost. XGBoost has proven itself to be one of the most powerful and useful libraries for structured machine learning. It's used in industry and is the high-performing model that wins many machine learning competitions. I'm really excited about the content of this course and believe this is the most complete and thorough end-to-end demonstration of XGBoost and the libraries surrounding it that support things like visualization, evaluation, and interpretation. In this course, we'll dive into the underpinnings of the XGBoost algorithm, we'll show a baseline model, and review the decision tree, the fundamental model that XGBoost is based on. Then we'll explain how boosting works and how XGBoost implements it. Using Jupyter Notebook demos, we'll show preliminary exploratory data analysis, we'll practice creating the model, evaluating it, and explaining it. Using third-party libraries, we'll explore feature interactions and explaining models. Before you begin this course, you should know some basic Python and pandas. Keep in mind that this is an applied course. By the end of this course, you should be able to take raw data, prepare it, model a classifier, and explore the performance of it. We aren't using the Iris or Titanic dataset. We're using real survey data, and we'll be using more than just the XGBoost library. We'll cover all the tools required for end-to-end classification. Using the provided notebook, you can follow along in your own machine or take and adapt the code to your own needs. Let's get started. I hope you'll join me on this journey with the Applied Classification with XGBoost course at Pluralsight.