Machine Learning Python Challenge: Regression

In this lab challenge, you will be tested on your scikit-learn skills to build a machine learning pipeline to predict the price of a stock. Here, you will be tested on data preprocessing, fitting, and evaluation of the regression model. 

To get the most from this lab, it is recommended to have confidence and exposure to at least the following libraries: pandas, matplotlib and scikit-learn.

You are strongly encourage to have completed the following courses, available in our content library:

• Building a Machine Learning pipeline with scikit-learn: part 01
• Building a Machine Learning pipeline with scikit-learn: part 02

as well as the following lab:

• Introduction to Financial Data Manipulation with Python

before starting this challenge.

Updates

July 29th, 2025 - Updated dependency

February 27th, 2025 - Updated finance and pandas versions

April 6th, 2023 - Resolved a dependency issue causing the stock ticker data frame 

January 27th, 2022 - Updated Python libraries to resolve an issue using the Yahoo APIs

September 20th, 2021 - Updated Python libraries to resolve an issue using the Yahoo APIs

• Knowledge of regression: Completion of the Building a Machine Learning pipeline with scikit-learn: part 02 course is highly recommended
• Knowledge of preprocessing: Completion of the Building a Machine Learning pipeline with scikit-learn: part 01 course is highly recommended

• Machine Learning Engineers
• Data scientists

• Your ability to create a machine learning pipeline
• Your ability to fit a linear regression model
• Your ability to evaluate a fitted model