Accéder au contenu principal

Cours

Apprentissage supervisé en R : Classification

IntermédiaireNiveau de compétence

Actualisé 04/2026

Dans ce cours, vous apprendrez les bases du machine learning pour la classification.

Commencer le cours gratuitement

RMachine Learning

4 h

14 vidéos

55 Exercices

3,950 XP

100K+

Certificat de formation

Apprécié par des utilisateurs provenant de milliers d'entreprises

Former une équipe ?

Essayez pour les entreprises

Description du cours

Cette introduction à l'apprentissage automatique couvre quatre des algorithmes de classification les plus courants. Vous en ressortirez avec une compréhension de base de la manière dont chaque algorithme aborde une tâche d'apprentissage, et vous apprendrez les fonctions R nécessaires pour appliquer ces outils à votre propre travail.

Prérequis

1

k-Nearest Neighbors (kNN)

As the kNN algorithm literally "learns by example" it is a case in point for starting to understand supervised machine learning. This chapter will introduce classification while working through the application of kNN to self-driving vehicle road sign recognition.

Classification with Nearest Neighbors

Recognizing a road sign with kNN

Thinking like kNN

Exploring the traffic sign dataset

Classifying a collection of road signs

What about the 'k' in kNN?

Understanding the impact of 'k'

Testing other 'k' values

Seeing how the neighbors voted

Data preparation for kNN

Why normalize data?

Commencer le chapitre

2

Naive Bayes

Naive Bayes uses principles from the field of statistics to make predictions. This chapter will introduce the basics of Bayesian methods while exploring how to apply these techniques to iPhone-like destination suggestions.

Understanding Bayesian methods

Computing probabilities

Understanding dependent events

A simple Naive Bayes location model

Examining "raw" probabilities

Understanding independence

Understanding NB's "naivety"

Who are you calling naive?

A more sophisticated location model

Preparing for unforeseen circumstances

Understanding the Laplace correction

Applying Naive Bayes to other problems

Handling numeric predictors

Commencer le chapitre

3

Logistic Regression

Logistic regression involves fitting a curve to numeric data to make predictions about binary events. Arguably one of the most widely used machine learning methods, this chapter will provide an overview of the technique while illustrating how to apply it to fundraising data.

Making binary predictions with regression

Building simple logistic regression models

Making a binary prediction

The limitations of accuracy

Model performance tradeoffs

Calculating ROC Curves and AUC

Comparing ROC curves

Dummy variables, missing data, and interactions

Coding categorical features

Handling missing data

Understanding missing value indicators

Building a more sophisticated model

Automatic feature selection

The dangers of stepwise regression

Building a stepwise regression model

Commencer le chapitre

4

Classification Trees

Classification trees use flowchart-like structures to make decisions. Because humans can readily understand these tree structures, classification trees are useful when transparency is needed, such as in loan approval. We'll use the Lending Club dataset to simulate this scenario.

Making decisions with trees

Building a simple decision tree

Visualizing classification trees

Understanding the tree's decisions

Growing larger classification trees

Why do some branches split?

Creating random test datasets

Building and evaluating a larger tree

Conducting a fair performance evaluation

Tending to classification trees

Preventing overgrown trees

Creating a nicely pruned tree

Why do trees benefit from pruning?

Seeing the forest from the trees

Understanding random forests

Building a random forest model

Commencer le chapitre

Apprentissage supervisé en R : Classification

Cours
terminé

Obtenez un certificat de réussite

Ajoutez cette certification à votre profil LinkedIn, à votre CV ou à votre portfolio
Partagez-la sur les réseaux sociaux et dans votre évaluation de performanceS'inscrire maintenant

Rejoignez plus de 19 millions d'utilisateurs et commencez Apprentissage supervisé en R : Classification dès aujourd'hui !

Apprenez où que vous soyez avec l'application DataCamp

Progressez où que vous soyez grâce à nos cours conçus pour mobile et à nos défis quotidiens de 5 minutes.