Interactive Course

Supervised Learning in R: Regression

In this course you will learn how to predict future events using linear regression, generalized additive models, random forests, and xgboost.

Start Course For Free

4 hours
19 Videos
65 Exercises
11,875 Participants
5,300 XP

Create Your Free Account

By continuing you accept the Terms of Use and Privacy Policy, that your data will be stored outside of the EU, and that you are 16 years or older.

Loved by learners at thousands of top companies:

Course Description

From a machine learning perspective, regression is the task of predicting numerical outcomes from various inputs. In this course, you'll learn about different regression models, how to train these models in R, how to evaluate the models you train and use them to make predictions.

In this chapter we introduce the concept of regression from a machine learning point of view. We will present the fundamental regression method: linear regression. We will show how to fit a linear regression model and to make predictions from the model.

Before moving on to more sophisticated regression techniques, we will look at some other modeling issues: modeling with categorical inputs, interactions between variables, and when you might consider transforming inputs and outputs before modeling. While more sophisticated regression techniques manage some of these issues automatically, it's important to be aware of them, in order to understand which methods best handle various issues -- and which issues you must still manage yourself.

In this chapter we will look at modeling algorithms that do not assume linearity or additivity, and that can learn limited types of interactions among input variables. These algorithms are *tree-based* methods that work by combining ensembles of *decision trees* that are learned from the training data.

Now that we have learned how to fit basic linear regression models, we will learn how to evaluate how well our models perform. We will review evaluating a model graphically, and look at two basic metrics for regression models. We will also learn how to train a model that will perform well in the wild, not just on training data. Although we will demonstrate these techniques using linear regression, all these concepts apply to models fit with any regression algorithm.

Now that we have mastered linear models, we will begin to look at techniques for modeling situations that don't meet the assumptions of linearity. This includes predicting probabilities and frequencies (values bounded between 0 and 1); predicting counts (nonnegative integer values, and associated rates); and responses that have a non-linear but additive relationship to the inputs. These algorithms are variations on the standard linear model.

1
What is Regression?
Free

In this chapter we introduce the concept of regression from a machine learning point of view. We will present the fundamental regression method: linear regression. We will show how to fit a linear regression model and to make predictions from the model.
View Chapter Details Play Chapter Now
Training and Evaluating Regression Models

Now that we have learned how to fit basic linear regression models, we will learn how to evaluate how well our models perform. We will review evaluating a model graphically, and look at two basic metrics for regression models. We will also learn how to train a model that will perform well in the wild, not just on training data. Although we will demonstrate these techniques using linear regression, all these concepts apply to models fit with any regression algorithm.
View Chapter Details Play Chapter Now
Issues to Consider

Before moving on to more sophisticated regression techniques, we will look at some other modeling issues: modeling with categorical inputs, interactions between variables, and when you might consider transforming inputs and outputs before modeling. While more sophisticated regression techniques manage some of these issues automatically, it's important to be aware of them, in order to understand which methods best handle various issues -- and which issues you must still manage yourself.
View Chapter Details Play Chapter Now
Dealing with Non-Linear Responses

Now that we have mastered linear models, we will begin to look at techniques for modeling situations that don't meet the assumptions of linearity. This includes predicting probabilities and frequencies (values bounded between 0 and 1); predicting counts (nonnegative integer values, and associated rates); and responses that have a non-linear but additive relationship to the inputs. These algorithms are variations on the standard linear model.
View Chapter Details Play Chapter Now
Tree-Based Methods

In this chapter we will look at modeling algorithms that do not assume linearity or additivity, and that can learn limited types of interactions among input variables. These algorithms are *tree-based* methods that work by combining ensembles of *decision trees* that are learned from the training data.
View Chapter Details Play Chapter Now

What do other learners have to say?

“I've used other sites, but DataCamp's been the one that I've stuck with.”

Devon Edwards Joseph

Lloyd's Banking Group

“DataCamp is the top resource I recommend for learning data science.”

Louis Maiden

Harvard Business School

“DataCamp is by far my favorite website to learn from.”

Ronald Bowers

Decision Science Analytics @ USAA

Nina Zumel

Co-founder, Principal Consultant at Win-Vector, LLC

Nina is a co-founder and principal consultant at Win-Vector LLC, a San Francisco data science consultancy. She is co-author of the popular text Practical Data Science with R and occasionally blogs at the Win-Vector Blog on data science and R. Her technical interests include data science, statistics, statistical learning, and data visualization.

John Mount

Co-founder, Principal Consultant at Win-Vector, LLC

John is a co-founder and principal consultant at Win-Vector LLC, a San Francisco data science consultancy. He is the author of several R packages, including the data treatment package vtreat. John is co-author of Practical Data Science with R and blogs at the Win-Vector Blog about data science and R programming. His interests include data science, statistics, R programming, and theoretical computer science.

Popular Courses

Popular Searches

If you type... We will search for...

Press enter to see all search results

Courses

Tracks

Instructors

Supervised Learning in R: Regression

Create Your Free Account

Loved by learners at thousands of top companies:

Course Description

What is Regression?

Welcome and Introduction

Identify the regression tasks

Linear regression - the fundamental method

Code a simple one-variable regression

Examining a model

Predicting once you fit a model

Predicting from the unemployment model

Multivariate linear regression (Part 1)

Multivariate linear regression (Part 2)

Wrapping up linear regression

Issues to Consider

Categorical inputs

Examining the structure of categorical inputs

Modeling with categorical inputs

Interactions

Modeling an interaction

Modeling an interaction (2)

Transforming the response before modeling

Relative error

Modeling log-transformed monetary output

Comparing RMSE and root-mean-squared Relative Error

Transforming inputs before modeling

Input transforms: the "hockey stick"

Input transforms: the "hockey stick" (2)

Tree-Based Methods

The intuition behind tree-based methods

Predicting with a decision tree

Random forests

Build a random forest model for bike rentals

Predict bike rentals with the random forest model

Visualize random forest bike model predictions

One-Hot-Encoding Categorical Variables

vtreat on a small example

Novel levels

vtreat the bike rental data

Gradient boosting machines

Find the right number of trees for a gradient boosting machine

Fit an xgboost bike rental model and predict

Evaluate the xgboost bike rental model

Visualize the xgboost bike rental model

Training and Evaluating Regression Models

Evaluating a model graphically

Graphically evaluate the unemployment model

The gain curve to evaluate the unemployment model

Root Mean Squared Error (RMSE)

Calculate RMSE

R-Squared

Calculate R-Squared

Correlation and R-squared

Properly Training a Model

Generating a random test/train split

Train a model using test/train split

Evaluate a model using test/train split

Create a cross validation plan

Evaluate a modeling procedure using n-fold cross-validation

Dealing with Non-Linear Responses

Logistic regression to predict probabilities

Fit a model of sparrow survival probability

Predict sparrow survival

Poisson and quasipoisson regression to predict counts

Poisson or quasipoisson

Fit a model to predict bike rental counts

Predict bike rentals on new data

Visualize the Bike Rental Predictions

GAM to learn non-linear transforms

Writing formulas for GAM models

Writing formulas for GAM models (2)

Model soybean growth with GAM