Skip to main content
Search form
  • 00:01

    SPEAKER 1: Step three is about transforming the data.And this builds on your examination.And it's about preparing your data ready for its usage.Every tool that you will analyze your data with or visualizeyour data with requires slightly different formats and shapesof data.So you're readying your data fit for a purpose,

  • 00:22

    SPEAKER 1 [continued]: fit for analysis.In my work as a football club, oneof the reports that releases about 9:30 in the morningbegins life at about 9:10.That's when the data arrives.And so in that 20 minute period, we have to clean.We have to convert.We have to calculate and get that data ready for analysis,to then produce the graphics.

  • 00:43

    SPEAKER 1 [continued]: So it's often about trying to automate and maximizewhat you can do to get the most out of your data.There are four parts.We've got to clean data.Building on the examination again,we need to remove all those issues,resolve all those issues, get rid of data you don't need.We might want to create new columns, new variablesto work with, calculations, new groupings

  • 01:04

    SPEAKER 1 [continued]: that give you different ways to analyze and slice up your data.We might wish to convert data, maybe converting thingsinto a different format, maybe extractingkeywords or sentiments from textual data,maybe normalizing things, so things become comparable.We also may wish to consolidate, add more data,

  • 01:25

    SPEAKER 1 [continued]: append, expand, or enhance our initial data resource.Going back to my film and graphics projects,a couple of examples of this in practice.In this case, we've got a couple examples of creating new data.The very first column is an ID columnthat is just created to keep and preserve

  • 01:46

    SPEAKER 1 [continued]: the ordering of the data, so we can quickly go back to thatand revert back to that.There's also a calculation that was made, for example,about the age of the actor at the time of releaseof that movie.So we could move the analysis between when it came out,and how old they were.The converting in this case was to take the date field

  • 02:06

    SPEAKER 1 [continued]: and convert that into day, month, and year elements.This was also a project that required consolidating.To compare modern movies with historical movies,we need to convert the takings, the box office takings, values.And one of the methods to do this

  • 02:27

    SPEAKER 1 [continued]: is to bring in historical ticket prices,to use that as an inflation device,to then modify and reform all the takings.So once again, that was a new, calculated columnthat was created to expand what I could use.I also brought in, for all the individual movies,a URL that pointed to an image of the poster of that movie.

  • 02:49

    SPEAKER 1 [continued]: And again, as I mentioned, we oftendeal with non-textual, non-quantitative datain the form of images, audio files, videos.In this case, I brought in not just the poster images,but also illustrations of the individuals themselvesto use as menu devices.So consolidating brings more data in

  • 03:10

    SPEAKER 1 [continued]: and gives you much more potential to work with.

Video Info

Series Name: Introduction to Data Visualisation

Episode: 8

Publisher: SAGE Publications Ltd

Publication Year: 2017

Video Type:Tutorial

Methods: Data cleaning, Data management, Data visualization

Keywords: data management; data transformations; data visualisation; design aspects

Segment Info

Segment Num.: 1

Persons Discussed:

Events Discussed:



Andy Kirk, using examples, explains the steps to prepare data for visualization: cleaning, creating, converting, and consolidating.

Looks like you do not have access to this content.

Module Two: Transforming the Data

Andy Kirk, using examples, explains the steps to prepare data for visualization: cleaning, creating, converting, and consolidating.

Copy and paste the following HTML into your website