Machine Learning with scikit-learn

The aim of this lab is to challenge you on building a supervised machine learning pipeline to predict the median values of owner-occupied housing in USD 1000, denoted as MEDV. We are going to famous Boston dataset, which contains a set of different features that are used to predict the MEDV target variable. Here, you will be guided with an hands-on exercise on data preprocessing, fitting and evaluation of a regression model.

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

I strongly encourage you to have watched the following courses, available in our content library:

• Building a Machine Learning pipeline with scikit-learn: part 1
• Building a Machine Learning pipeline with scikit-learn: part 2

before starting this lab.

 

Learning Objectives

Upon completion of this lab you will be able to:

• Build a standard machine learning pipeline with scikit-learn;
• Scale a dataset using the StandardScaler transformer;
• Train a Ridge Regression Model;
• Fit a scikit-learn Pipeline object with a GridSearchCV.

Intended Audience

This lab is intended for:

• Those interested in performing machine learning with Python.
• Anyone involved in data science pipelines.

Prerequisites

You should possess:

• An intermediate understanding of Python.
• Basic knowledge of the following libraries: pandas, scikit-learn, matplotlib, seaborn.