Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!

Grab it

This course is a complete guide to supervised and unsupervised learning using R, covering practical data science comprehensively. Companies globally use R to analyze vast data, and mastering it can enhance your career. Unlike other courses, this one provides in-depth knowledge of R's machine learning features, from data reading and cleaning to implementing and evaluating algorithms. -You'll explore topics such as R framework, data structures, pre-processing, machine learning, model building, and selection. -Emphasizing real data, you'll use packages like Caret and understand unsupervised learning, dimension reduction, and supervised learning. -You'll read data, pre-process in R Studio, implement K-means clustering, PCA, Random Forests, and evaluate models. Ideal for students starting with R Studio data science, those wanting to apply unsupervised learning to real data, and anyone with R experience aiming to enhance practical skills. Prior exposure to common machine learning terms would be needed.

Syllabus

Introduction to the Course

In this module, we will introduce the course, outlining the fundamental concepts of clustering and classification in machine learning. We will also guide you through the installation and setup of R and R Studio, ensuring you are prepared to dive into the practical aspects of the course.

Read in Data from Different Sources in R

In this module, we will explore the different methods to import data into R from various sources. You will learn to read data from CSV and Excel files, unzipped folders, online CSVs, Google Sheets, HTML tables, and databases, setting the foundation for data manipulation and analysis.

Data Pre-processing and Visualization

In this module, we will delve into data cleaning and preprocessing, ensuring your data is ready for analysis. You will learn to summarize and explore data using the dplyr package and create visualizations with ggplot2. Additionally, we'll cover methods to evaluate associations between variables and test for correlation.

Machine Learning for Data Science

In this module, we will explore the differences between machine learning and traditional statistical analysis, providing a theoretical overview of machine learning. You will gain a foundational understanding of machine learning concepts and their relevance to data science.

Unsupervised Learning in R

In this module, we will cover unsupervised learning techniques, focusing on clustering algorithms. You will learn to implement and evaluate different clustering methods, including K-Means, Fuzzy K-Means, DBSCAN, and more. We'll also discuss how to select the best algorithm for your specific data needs.

Feature/Dimension Reduction

In this module, we will explore techniques for reducing the dimensionality of your data. You will learn the theoretical aspects of dimension reduction and how to apply methods such as PCA, Multidimensional Scaling, and SVD in R to simplify your datasets while preserving essential information.

Feature Selection to Select the Most Relevant Predictors

In this module, we will focus on feature selection techniques to identify the most relevant predictors for your models. You will learn to remove correlated variables and use methods like LASSO regression, FSelector, and Boruta analysis to select important features, enhancing your model's performance.

Supervised Learning Theory

In this module, we will introduce the fundamental concepts of supervised learning. You will learn how to preprocess data for supervised learning and gain insights into various types of supervised learning problems, preparing you for more advanced classification and regression techniques.

Supervised Learning: Classification

In this module, we will delve into classification techniques in supervised learning. You will learn to implement logistic regression, Decision Trees, Random Forests, and Support Vector Machines (SVM). We will also cover methods to evaluate classification accuracy and understand variable importance in your models.

Additional Lectures

In this module, we will provide additional lectures focusing on advanced clustering methods. You will learn about Fuzzy C-Means Clustering, understanding its theoretical underpinnings and practical applications in R, further enhancing your clustering analysis skills.