# Data Science isn't Magic

Friday February 20, 2015

This is the flow for a DC Open Data Day 2015 workshop. It may not make sense out of context. For a fun summary in tweets (with photos!) you might check out a storification of it.

View this page as slides to make this site's base URL appear quite large so that people can find this easily.

planspace.org

### Workshop Outline

- Intro / Disclaimer
- 80% Definitions (slides)
- Data Science is OSEMN (slides)
- What's the Problem? (slides)
- Find NYC attendance data
- Data Science Tools (slides)
- Connect to RStudio in the cloud
- Backup plan:
- Install the appropriate
`R`

distribution for your system from this mirror. - Install the RStudio IDE for
`R`

. The RStudio site should suggest an appropriate package for your system. - Download and unzip the files we're using. (They're on GitHub, so you can clone if you prefer.)

- Install the appropriate

- Backup plan:
- Working with
`R`

- Working with one day of data (
`01-day_attendance.R`

) - Selecting usable data points (
`02-select_totals.R`

) - The relationship between temperature and attendance (
`03-merge_and_plot.R`

)

- Working with one day of data (
- Bonus: Introducing the DC voter file

### Additional Resources

- For learning
`R`

:- Try R is an interactive web site that guides you through
`R`

functionality in your web browser. - The walking introduction to R is an
`R`

script that you can open and work through in RStudio.

- Try R is an interactive web site that guides you through
- For more fun data: