Data Science in Python: Regression & Forecasting

Description

This is a hands-on, project-based course designed to help you master the foundations for regression analysis in Python.

We’ll start by reviewing the data science workflow, discussing the primary goals & types of regression analysis, and do a deep dive into the regression modeling steps we’ll be using throughout the course.

You’ll learn to perform exploratory data analysis, fit simple & multiple linear regression models, and build an intuition for interpreting models and evaluating their performance using tools like hypothesis tests, residual plots, and error metrics. We’ll also review the assumptions of linear regression, and learn how to diagnose and fix each one.

From there, we’ll cover the model testing & validation steps that help ensure our models perform well on new, unseen data, including the concepts of data splitting, tuning, and model selection. You’ll also learn how to improve model performance by leveraging feature engineering techniques and regularized regression algorithms.

Throughout the course, you'll play the role of Associate Data Scientist for Maven Consulting Group on a team that focuses on pricing strategy for their clients. Using the skills you learn throughout the course, you'll use Python to explore their data and build regression models to help firms accurately predict prices and understand the variables that impact them.

Last but not least, you'll get an introduction to time series analysis & forecasting techniques. You’ll learn to analyze trends & seasonality, perform decomposition, and forecast future values.

COURSE OUTLINE:

• Intro to Data Science

  • Introduce the fields of data science and machine learning, review essential skills, and introduce each phase of the data science workflow

  
  

• Regression 101

  • Review the basics of regression, including key terms, the types and goals of regression analysis, and the regression modeling workflow

  
  

• Pre-Modeling Data Prep & EDA

  • Recap the data prep & EDA steps required to perform modeling, including key techniques to explore the target, features, and their relationships

    
    

• Simple Linear Regression

  • Build simple linear regression models in Python and learn about the metrics and statistical tests that help evaluate their quality and output

  
  

• Multiple Linear Regression

  • Build multiple linear regression models in Python and evaluate the model fit, perform variable selection, and compare models using error metrics

  
  

• Model Assumptions

  • Review the assumptions of linear regression models that need to be met to ensure that the model’s predictions and interpretation are valid

  
  

• Model Testing & Validation

  • Test model performance by splitting data, tuning the model with the train & validation data, selecting the best model, and scoring it on the test data

  
  

• Feature Engineering

  • Apply feature engineering techniques for regression models, including dummy variables, interaction terms, binning, and more

  
  

• Regularized Regression

  • Introduce regularized regression techniques, which are alternatives to linear regression, including Ridge, Lasso, and Elastic Net regression

  
  

• Time Series Analysis

  • Learn methods for exploring time series data and how to perform time series forecasting using linear regression and Facebook Prophet

__________

Ready to dive in? Join today and get immediate, LIFETIME access to the following:

• 8.5 hours of high-quality video

• 14 homework assignments

• 10 quizzes

• 3 projects

• Data Science in Python: Regression ebook (230+ pages)

• Downloadable project files & solutions

• Expert support and Q&A forum

• 30-day Udemy satisfaction guarantee

If you're an aspiring data scientist looking for an introduction to the world of regression modeling with Python, this is the course for you.

Happy learning!

-Chris Bruehl (Data Science Expert & Lead Python Instructor, Maven Analytics)

TAKE THIS COURSE