Learn Data Science

R and Python are two popular languages for data science. We use both at Instacart.

This is a short guide for R.

It’s quick and everything is completely free. Follow in order for a smoother ride.

Setup

Download R and RStudio Desktop.

Getting Started

Complete Try R. Then read about data structures and subsetting. The str() command will be a favorite as you learn.

Your First Model

Kaggle is a platform for data science competitions. Complete the “getting started” competition by following this great tutorial (5 parts).

Keep Learning

Read and do the labs in An Introduction to Statistical Learning (available as a free PDF). Understand the bias-variance tradeoff.

Check out R for Data Science and these courses:

• Practical Machine Learning
• Exploratory Data Analysis
• Regression Models
• Data Cleaning

Get a quick intro to time-series analysis.

Also check out Google’s R Style Guide.

Good to Know

• variables and function names in R can (and often do) contain dots - lm.fit is a variable name, not a call to the lm object