Your SlideShare is downloading. ×
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Predictive Models for Production Apps with Yhat
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×
Saving this for later? Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime – even offline.
Text the download link to your phone
Standard text messaging rates apply

Predictive Models for Production Apps with Yhat

2,751

Published on

Yhat presentation at PyData Boston 2013. Predictive Models for Production Apps with Yhat. Building a beer recommender with Python and Yhat.

Yhat presentation at PyData Boston 2013. Predictive Models for Production Apps with Yhat. Building a beer recommender with Python and Yhat.

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

No Downloads
Views
Total Views
2,751
On Slideshare
0
From Embeds
0
Number of Embeds
5
Actions
Shares
0
Downloads
63
Comments
0
Likes
3
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide

Transcript

  • 1. Predictive Models for Production Applications July 2013
  • 2. Why building analytical apps is hard Overcoming the challenge Case study: building a beer recommender
  • 3. If you double the number of experiments you do per year, you're going to double your inventiveness. “ ”- Jeff Bezos
  • 4. We need to reduce churn. Okay. I'll look into it. Lots of conversations like this
  • 5. 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... The "a ha" moment isn't the end.
  • 6. Now what? Any of you know what Gradient Boosting is? So when can we go live with the new model?
  • 7. It's hard to incorporate analytical work into day-to-day operations
  • 8. We know finding a data scientist tough. http://drewconway.com/
  • 9. Building applications from their insights is tougher.
  • 10. "cool. what do we do now?" scenarios http://scikit-learn.org/stable/auto_examples/index.html
  • 11. Product Page Search Results Order Confirmation / Checkout Page Reduce QA time for classifying purchases made online
  • 12. How to go from prototype to product?
  • 13. How do companies address this problem?
  • 14. Rewriting Code Common Approaches Challenge
  • 15. Rewriting Code Common Approaches Cross-environment validation Challenge
  • 16. Rewriting Code Batch Jobs Common Approaches Cross-environment validation Challenge
  • 17. Rewriting Code Batch Jobs Common Approaches Cross-environment validation High maintenance and config Challenge
  • 18. Rewriting Code Batch Jobs PMML Common Approaches Cross-environment validation High maintenance and config Challenge
  • 19. Rewriting Code Batch Jobs PMML Common Approaches Cross-environment validation High maintenance and config Limited to certain libraries, Still rewriting Challenge
  • 20. Rewriting Code Batch Jobs PMML Common Approaches Cross-environment validation High maintenance and config Limited to certain libraries, Still rewriting Challenge More people, more tools, more time to market.
  • 21. Can we build and bring to market smarter applications faster?
  • 22. Rewriting Code Batch Jobs PMML Common Approaches Cross-environment validation High maintenance and config Limited to certain libraries, Still rewriting Challenge A platform for running predictive models in production applications.
  • 23. Key Tenets
  • 24. 1. Work with the tools you already know Key Tenets
  • 25. 1. Work with the tools you already know 2. Iterate quickly Key Tenets
  • 26. 1. Work with the tools you already know 2. Iterate quickly 3. Low touch Key Tenets
  • 27. 1. Work with the tools you already know 2. Iterate quickly 3. Low touch 4. No rewriting code Key Tenets
  • 28. demo
  • 29. A Beer Recommender in Python
  • 30. What beer should I drink?
  • 31. Tell us a beer you like
  • 32. We'll tell you some other beers you'll like
  • 33. 1. Import the data 2. Find common reviewers 3. Calculate review distance 4. Rank beers Plan
  • 34. 1. Import the data 2. Find common reviewers 3. Calculate review distance 4. Rank beers Plan
  • 35. The Dataset
  • 36. The Dataset
  • 37. The Dataset
  • 38. 1. Import the data 2. Find common reviewers 3. Calculate review distance 4. Rank beers Plan
  • 39. Find common reviewers
  • 40. 1. Import the data 2. Find common reviewers 3. Calculate distance 4. Rank beers Plan
  • 41. Comparing 2 Similar Beers vs
  • 42. Dale's Pale Ale and Fat Tire Amber Ale
  • 43. Dale's Pale Ale and Fat Tire Amber Ale "Perfect Agreement"
  • 44. Dale's Pale Ale and Fat Tire Amber Ale
  • 45. Dale's Pale Ale and Fat Tire Amber Ale
  • 46. Dale's Pale Ale and Fat Tire Amber Ale
  • 47. Dale's Pale Ale and Fat Tire Amber Ale Similar reviews
  • 48. Comparing 2 Dissimilar Beers vs
  • 49. Dale's Pale Ale and Fat Tire Amber Ale
  • 50. Michelob Ultra and Fat Tire Amber Ale
  • 51. Measuring distance
  • 52. Measuring distance ...yes, there are other ways to do this.
  • 53. Calculating Distance
  • 54. Distance Implementation
  • 55. Calculate the Distance ● Generate all beer pairs ● Calculate distance between each pair
  • 56. 1. Import the data 2. Find common reviewers 3. Calculate review distance 4. Rank results Plan
  • 57. So if I like Coors Light, what other beers might I like?
  • 58. shipping your work with
  • 59. Make analytical routines available to other apps { "beer": "Coors Light", "weights": [3, 2, 0, 1]} [ ["Bud Light", 9.2], ["Budweiser", 12.2], ["Sierra Nevada", 21.2], ]
  • 60. 1. Pre-processing & transformations
  • 61. 2. Prediction & post-processing
  • 62. Use the same code you wrote during exploration and modeling. 2. Prediction & post-processing
  • 63. We're ready to deploy
  • 64. Analytical routine is now ready to be deployed Go-to-market with as little overhead as possible
  • 65. Deploy Pass objects you'd like included in your model as named arguments
  • 66. Specify User Defined Functions you want to include in your project Deploy
  • 67. Pass the name of your model and your BaseModel object to the deploy function Deploy
  • 68. Execute deploy to host your model on Yhat Deploy
  • 69. Make predictions in a production app
  • 70. pydata-beer.herokuapp.com https://github.com/yhat/Beer-Rec-Flask
  • 71. Data/Code Bundle Webapp: https://github.com/yhat/Beer-Rec-Flask IPython Notebook: http://bit.ly/1bkCTHz Dataset: http://bit.ly/14Wl64k
  • 72. Want to try? yhathq.com
  • 73. We're Hiring info@yhathq.com yhathq.com/jobs
  • 74. Questions? greg@yhathq.com austin@yhathq.com yhathq.com @YhatHQ blog.yhathq.com
  • 75. Appendix
  • 76. Learn by iteration from the context of real- world business applications.
  • 77. Deployment Execute the deploy function to host your model on Yhat Pass the name of your model and your BaseModel object to the deploy function Pass objects you'd like included in your model as named arguments Specify User Defined Functions you want to include in your project

×