Applied Data Science with Yhat

669 views

Published on

Yhat at the San Francisco Data Science Meetup (02/26/2014)

Published in: Technology
0 Comments
5 Likes
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
669
On SlideShare
0
From Embeds
0
Number of Embeds
47
Actions
Shares
0
Downloads
13
Comments
0
Likes
5
Embeds 0
No embeds

No notes for slide

Applied Data Science with Yhat

  1. 1. Applied Data Science with Yhat SF Data Science Meetup Feb 26, 2014
  2. 2. 1) Intro (1 min) 2) The Problem (3 mins) 3) Case Study: Beer Recommender (5 mins) 4) Demo (3 min) 5) Q/A (5 min)
  3. 3. Founders Company Investors Greg Lamp, CTO Austin Ogilvie, CEO ● Launched in 2013 ● HQ in Brooklyn
  4. 4. Data science in the real world. regression
  5. 5. Get Raw Data Strategic Insights Real World Scoring Data Driven Products Business Impact Clean Data Stages of the Analytics Project Life Cycle Expert data teams Management Customers & Front Line Employees
  6. 6. What makes building analytical apps hard?
  7. 7. Hi, I’m Trey. Meet Trey, the Data Scientist
  8. 8. We need to reduce churn. Okay. I'll look into it.
  9. 9. I figured out that....some complex stuff about vector space that'll improve... ....and that's how we'll reduce churn. Sounds good. Let's do that...
  10. 10. Any of you know what Gradient Boosting is? So when can we go live with the new model?
  11. 11. Now what?
  12. 12. use your tools
  13. 13. use your tools move quickly
  14. 14. use your tools move quickly any workflow
  15. 15. use your tools move quickly any workflow no translating
  16. 16. Case Study
  17. 17. + = ?
  18. 18. A Beer Recommender in Python
  19. 19. http://beers.yhathq.com
  20. 20. The Data
  21. 21. http://snap.stanford.edu/data/web-BeerAdvocate.html
  22. 22. Beers
  23. 23. Users
  24. 24. Ratings
  25. 25. Distance
  26. 26. vs
  27. 27. vs
  28. 28. calculating distance
  29. 29. eeny ? ?
  30. 30. eeny meeny ?
  31. 31. ? Cosine eeny meeny miny
  32. 32. ? Cosine moe
  33. 33. pick one. you can always change
  34. 34. Thank you,
  35. 35. Scoring
  36. 36. Aggregate
  37. 37. Sort
  38. 38. Filter
  39. 39. Return
  40. 40. Deployment
  41. 41. What does this mean?
  42. 42. Import Yhat
  43. 43. Create a YhatModel
  44. 44. Define execute
  45. 45. Grab incoming data
  46. 46. Call your function
  47. 47. Format and return results
  48. 48. Demo http://cloud.yhathq.com/ http://beers.yhathq.com/
  49. 49. deploy your own IPython Notebook
  50. 50. Thanks! @yhathq greg@yhathq.com yhathq.com
  51. 51. Questions?

×