Skip to main content

Course

Machine Learning in the Tidyverse

IntermediateSkill Level

4.9+

Updated 05/2025

Leverage tidyr and purrr packages in the tidyverse to generate, explore, and evaluate machine learning models.

Start Course for Free

Included withPremium or Teams

RMachine Learning5 hours15 videos52 Exercises4,300 XP15,449Statement of Accomplishment

Create Your Free Account

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.

Training 2 or more people?

Try DataCamp for Business

Loved by learners at thousands of companies

Course Description

Welcome to the tidyverse! In this course, you will continue on your journey to learn the tidyverse and apply your knowledge to machine learning concepts.

This course is ideal if you’re looking to integrate R's Tidyverse tools into your machine learning workflows.

Evaluating machine learning models

Throughout this course, you will focus on leveraging the tidyverse tools in R to build, explore, and evaluate machine learning models efficiently.

The course begins by introducing the List Column Workflow (LCW), a method for managing multiple models within a single dataframe. It also covers using the broom package to tidy up and explore model outputs, making the complex results more interpretable.

Utilizing tidyr and purrr

Work through practical exercises including building and evaluating regression along with classification models. Explore techniques for tuning hyperparameters to optimize model performance.

You will use packages like tidyr and purrr to handle complex data manipulations and model evaluations, ensuring a tidy and systematic approach to machine learning.

Gain real-world application

Explore real-world examples through multiple case studies, such as using the gapminder dataset to predict life expectancy with linear models.

By the end of the course, you will have a strong foundation in applying Tidyverse principles to machine learning, enabling them to build, tune, and evaluate models efficiently in a tidy and reproducible manner.

Prerequisites

Modeling with Data in the Tidyverse

1

Foundations of "tidy" Machine learning

Foundations of "tidy" machine learning

Nesting your data

Unnesting your data

Explore a nested cell

The map family of functions

Mapping your data

Expecting mapped output

Mapping many models

Tidy your models with broom

The three ways to tidy your model

Extracting model statistics tidily

Augmenting your data

2

Multiple Models with broom

Exploring coefficients across models

Tidy up the coefficients of your models

What can we learn about these 77 countries?

Evaluating the fit of many models

Glance at the fit of your models

Best and worst fitting models

Visually inspect the fit of many models

Augment the fitted values of each model

Explore your best and worst fitting models

Improve the fit of your models

Build better models

Predicting the future

3

Build, Tune & Evaluate Regression Models

Training, test and validation splits

The test-train split

Cross-validation data frames

Measuring cross-validation performance

Build cross-validated models

Preparing for evaluation

Evaluate model performance

Building and tuning a random forest model

Build a random forest model

Evaluate a random forest model

Fine tune your model

The best performing parameter

Measuring the test performance

Build & evaluate the best model

4

Build, Tune & Evaluate Classification Models

Logistic regression models

Prepare train-test-validate parts

Build cross-validated models

Evaluating classification models

Predictions of a single model

Performance of a single model

Prepare for cross-validated performance

Calculate cross-validated performance

Random forest for classification

Tune random forest models

Random forest performance

Build final classification model

Measure final model performance

Machine Learning in the Tidyverse

Course
Complete

Earn Statement of Accomplishment

Add this credential to your LinkedIn profile, resume, or CV
Share it on social media and in your performance review

Included withPremium or Teams

Don’t just take our word for it

*4.9

from 22 reviews

91%

9%

0%

0%

0%

Highest to Lowest
Lowest to Highest
Most recent
Top reviews

YI XUAN

about 23 hours

Donovan

3 days

Christopher

7 days

Mihail

12 days

Very well explained and put together. Greate work Dmitriy!

Silvestre

about 2 months

Huw

15 days

The one thing that is missing is explaining how you can see in the random forests etc,,, what are the variables that are contirbuting to the model. Are there variables that are redundant. I would think it would be critical if you have many feature variables and many observations. The datasets we are using in the course are tiny compared to real world examples of millions of rows of customers and 100 variables to model.

YI XUAN

Donovan

Christopher

FAQs

Join over 17 million learners and start Machine Learning in the Tidyverse today!

Create Your Free Account

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.