Introduction to R

R is an open-source programming language for statistical computing and graphics. R is extensible, and has a large collection of high-quality user contributed packages that provides easy tools for common data analysis tasks. This mini-course will introduce you the fundamentals of R programming with a focus on data management, data visualization and quantitative finance applications in R.

---

What To Prepare

• Please install R and RStudio Desktop before the first session.

  RStudio is the most popular IDE (Integrated Development Environment) for R. Most people use RStudio if they want to write some R code.

  If you encounter technical difficulties installing the software, you can instead create a free RStudio Cloud account so you can run R and RStudio in the cloud via your browser.

  An alternative to RStudio Cloud is the UofT JupyterHub/RStudio system. Go to its home page, choose the RStudio option, and click Log in to start. You will need your UTORid.

• We will also use Google Colab, and I assume you all have a Google account.

  Google Colab lets you combine code and notes in a “notebook”. It is a great setup to get started with R programming.

  UofT JupyterHub offers a similar notebook setting. Go to its home page, choose the Jupyter Notebook option, and click Log in to start. You will need your UTORid.

---

Part 1 (Overview & Basics)

• Slides
• Motivation Examples
  • Analyze portfolio performance (R Script: performance_analysis.R)
  • Perform simple sentiment analysis on earning call transcripts (R script: earning_call.R; Word Cloud)
  • Recognize handwritten digits, a deep learning “Hello World” example
    • R script 1 (using Tensorflow for R): dl_hello_world.R
    • R script 2 (using Torch for R): dl_hello_world_torch.R
• Basic Data and Programming Structures
  • Data structures (R Notebook )
  • Programming structures (R Notebook )
• Data Science Workflow - A Regression Example (Housing prices and clean air)
  • Linear Regression - Base R (R Notebook )
  • Linear Regression - Tidyverse & Others (R Notebook )
    • Data Import
    • Data Manipulation
    • Modelling
    • Report (sample regression report)
• Additional materials on data and programming structures (from past workshops; optional)
  • Data structures
    • Vectors
    • Derived data structures
  • Programming structures
• Reading list
  • R for Data Science (Chapter 1 Intro, 4 Workflow: basics, 5 Data transformation, 6 Workflow: scripts, 8 Workflow: projects, 10 Tibbles, 11 Data import, 18 Pipes, 19 Functions, 20 Vectors, and 21 Iteration.)

Part 2 (Data Manipulation)

• Slides
• Code
  • Data Manipulation (R notebook: )
• Reading list
  • R for Data Science (Chapter 5 Data transformation, 12 Tidy data, and 13 Relational data.)

Part 3 (Visualization)

• Slides
• Code (ggplot)
  • R notebook:
  • R markdown: part3_visualization.Rmd (Let’s take this opportunity to learn about R Markdown.)
• Code (tidyquant charting, dygraph, and R markdown flexdashboard)
  • R script: finance_charting.R
  • R markdown: time_series_flexboard.Rmd (HTML output: time_series_flexboard.html)
• Reading list
  • R for Data Science (Chapter 3 Data visualization, 7 Exploratory Data Analysis (EDS), and 28 Graphics for communication.)

Part 4 (Tidymodels, Time Series and Some R Finance Packages)

• Slides (1. tidymodels; 2. time series and finance packages)
• Code
  • Tidymodels (R markdown: tidymodels_intro.Rmd; HTML: tidymodels_intro.html)
  • Time series and finance packages (R markdown: part4_timeseries_finance_pkg.Rmd; HTML: part4_timeseries_finance_pkg.html)

---

Resources

• From Zero to Hero
  • Step 1: Hands-on Programming with R (never programmed before; start from scratch)
  • Step 2: R for Data Science (Data science with R’s Tidyverse eco-system. Work in progress 2ed here.)
  • Step 3: Advanced R (master R)
• R Graphics
  • R Graphics Cookbook
  • ggplot2: Elegant Graphics for Data Analysis
  • The R Graph Gallery (R graph samples with code)
• R and Econometrics
  • Tidy Finance with R
  • Introduction to Econometrics with R
  • Forecasting: Principles and Practice (2nd ed.; 3rd ed.)
  • Financial Engineering Analytics: A Practice Manual Using R
• R and Machine Learning
  • An Introduction to Statistical Learning / with Applications in R (you can download the book and its R code)
  • Tensorflow for R (deep learning with R)
  • Torch for R (deep learning with R)
• Others
  • A Short R Tutorial by Germán Rodríguez
  • Introductory Econometrics Examples (data and examples from Wooldridge)
  • STAT545 by Jenny Bryan : Data wrangling, exploration, and analysis with R
  • Programming with R (from software carpentry)
  • DoSStoolkit (self-paced interactive learning modules from Uoft Dept. of Statistical Science)
  • R Cheat Sheets (cheat sheets for many popular R packages)
  • Many more R books here

---

Back to TDMDAL Computing Page