The ability to take data, understand it, visualize it and extract useful information from it is becoming a hugely important skill. How can you turn all those logs, histories of purchases and trades or open government data, into useful information that help your business make money? In this talk, we’ll look at doing data science using F#. The F# language is perfectly suited for this task – type providers integrate external data directly into the language – your language suddenly _understands_ CSV, XML, JSON, REST services and other sources. The interactive development style makes it easy to explore data and test your algorithms as you’re writing them. Rich set of libraries for working with data frames, time series and for visualization gives you all the tools you need. And finally – F# easily integrates with statistical environments like R and Matlab, giving you access to the industry standard libraries.

1. Doing data science with F#
Tomas Petricek
tomas@tomasp.net | @tomaspetricek
PhD Student at Cambridge & Coordinator of http://fsharp.org

2. software stacks
trainings
mac and linux
teaching F#
user groups
snippets
community books and tutorials
F# Software Foundation
consulting
open-source MonoDevelop
http://www.fsharp.org
contributions research support
cross-platform
mailing lists

4. data acquisition
statistics data cleaning machine learning
data transformation
visualization type providers
F# Data Science Working Group
kaggle
vega grammar
R provider
data sources presentation
www.fslab.org
time-series
visualization
data aggregation

5. The Data

8. Demo: Understanding the world

9. F# Data type providers
First-class data
CSV, REST, WorldBank…
R Type provider
Statistics & visualization
5000 tested packages
www.fslab.org

10. Analyze
Acquire
Visualize

11. Demo: Interactive visualizations

12. F# Charting library
Simple & composable
Interactive style
F# to JS with FunScript
Type-safe JS interop
Type provider support
www.fslab.org

13. Demo: US debt over the last century

14. Deedle data frame
Time-series alignment
Data transformations
Vega visualization
F# wrapper for Vega
Pre-alpha version
www.fslab.org

15. F# for Data Science
acquire, analyze, visualize
interactive experience
safety and efficiency of .net
ready for production
@tomaspetricek

16. Going forward
Use #fsharp for fun & profit
Join local user groups
Help us build data science tools
fsharp.org | fslab.org | tomasp.net
@tomaspetricek