Training Course Details

Mastering the Tidyverse

Course Level: Foundation

The tidyverse is essential for any statistician or data scientist who deals with data on a day-to-day basis. By focusing on small key tasks, the tidyverse suite of packages removes the pain of data manipulation.  The tidyverse allows you to

  • Import data from databases and data sources with ease
  • Remove the pain of data cleaning
  • Start understanding that data by transforming it, visualising it with imagery and modelling it
  • Communicate your findings throughout your organisation securely and simply with apps, documents or plots
  • Make business decisions based on accurate data

This training course covers key aspects of the tidyverse, including dplyr, lubridate, tidyr and tibbles.

Leeds, UK | January 10, 2019

Price:
£375.00 ex VAT per person
Venue Details:
Date:
January 10, 2019
Time:
9.30 am - 5.00 pm
Duration:
1 day
Select if you qualify for a discount
Ask For More Details About This Course

Course Details

Course Structure

Tibbles

The core tidyverse data structure is a tibble; this is a modern take on the data frame.
The course commences with a brief introduction to this structure.

  • What are they?
  • How do they differ from data frames?
  • Convert a data frame to a tibble and back
  • Why tibbles – motivation for the other tidyverse packages and sets the theme for the day

dplyr: the workhorse of the tidyverse

Before the first coffee break, we’ll tackle the dplyr package. This package forms the foundation of the tidyverse by providing a standardised data manipulation grammar.

  • What is dplyr?
  • The grammar of tidyverse functions
  • filter(), summarise() – it may be that a review of boolean algebra is necessary at this point for subsetting
  • The pipe operator %>% and chaining functions into a workflow
  • Some other useful dplyr functions group_by()

Tidy data

Your data should be tidy. An obvious statement, except what do we mean by tidy? This section will elucidate what we mean by tidy data and how to make it part of our workflow.

  • Tidy data
    • What is tidy data?
  • Using tidyr
    • spread() and gather() for reshaping data
    • seperate() and unite() for splitting data into one column or the reverse
    • dealing with missing values
  • Joins for dealing with data split across multiple data frames

Data Input/Output

In order to manipulate data, we need to be able to load data into R. We’ll cover the key packages and provide advice as required.

  • Data storage: practical advice for managing data
  • Tidyverse packages
    • readr and readxl for dealing with .csv and .xls/.xlsx files
    • Database connections
  • Non-tidyverse packages
    • Not all data sets can be loaded using tidyverse packages
    • foreign package for reading data from other statistical systems (SAS, SPSS, Minitab)

Data manipulation

We’ll finish the day by looking at common difficulties that may crop up in a data scientist’s day

  • Dates/times with the lubridate package
  • String manipulation with stringr
    • First steps in regular expressions

Materials