Watson Studioで かんたん機械学習モデル作成

Watson Studioで かんたん機械学習モデル作成

2018年12月14日オープンソースカンファレンス2018 OSC2018.Enterpriseでの登壇資料です。

Ca7e4f1680e175e6462a039923e71fc5?s=128

Kyoko Nishito

December 14, 2018
Tweet

Transcript

  1. Watson Studio ) ( Developer Advocate    

    2018 .Enterprise 2018-12-14 () 13:00-13:45 @5F 5A
  2. Kyoko NISHITO  Developer Advocate

  3. "  3 • &$ Watson Studio   !"(/'-

    *) #% ., •  Watson Studio Model Builder+ (/ '- *) 
  4. Watson Studio 4 Model Lifecycle Management c c i c

    c i c o d vf AI C a c e st • IBM liu (LocalC r ) • cS IBM C n fI • R, Python, Scala iu •     •    c c i c c i c iu
  5. ) ( Learning ( 5 • Watson Studio DF Fabric

    for Deep Learning (FfDL) • Code Patterns Deploy and use a multi-framework deep learning platform on Kubernetes • Github https://github.com/IBM/FfDL
  6. IBM Developer https://developer.ibm.com/jp/ 6 •    140 

     Code Patterns •    6,000  
  7. 7  Watson Studio      

    
  8.  8 dog cat cat dog Positive ID: Pug Unknown

    Unknown Positive ID: Pug dog dog dog dog  
  9.   (1'0+) 9 dog cat cat dog Positive ID:

    Pug Unknown Unknown Positive ID: Pug  ,/'0 Watson Studio  #$" (1'0 Spark ML*&+)  #$%!.- Apache Spark
  10. 3 ) 10 ) 3( ) 3 ) I 3

    ) I 3 i : ) • SEPAL LENGTH: cm • SEPAL WIDTH : cm • PETAL LENGTH: cm • PETAL WIDTH : cm • CLASS: Iris-setosa( ), Iris-versicolour( ) ), Iris-virginica ( )I )
  11. %  11    #!   !

     #  "$% • SEPAL LENGTH:    • SEPAL WIDTH :  #  • PETAL LENGTH: !    • PETAL WIDTH : !  #  • CLASS : Iris-setosa(), Iris-versicolour(), Iris-virginica ()
  12. 12      

  13. Watson . 13 IBM Cloud 2. . Watson Studio (

    AI) S/ . 1 Machine Learning ( AI) S/ . 1 Apache Spark ( Web ) S/ . 1 ( ) 
  14. 1. Watson Studio 14 

  15. 2. Watson Studio 15 1.   (IBM Cloud )

    2.  Watson Studio   3. Get Started 
  16. 2. Watson Studio  16 4.   5 

    [Next]( [Done])     
  17. . 17 1. 3 New in the community Explore 

  18. 3 18 2. 3 iris 3. UCI: Iris . .

    
  19. . 19 4. 3 , iris.csv 

  20. 20 5. iris.csv 7 iris_test.csv4 setosa, versicolour, virginica . 10

    4 3 iris_test.csv 4 3 5iris.csv 7  4 
  21. 4. Project 21 1. [Create a Project]  2. [Standard]

     
  22. 4. Project 22 1. Name Project  2. [Create] 

    
  23. 23 . 

  24. . 4 24 1. [Settings] 2. Associated services [+Add services]

    [Spark] 
  25. 25 1. [Existing] .4 . 2. Existing Service Instance 1

    Apache Spark 1. [Select] .4 . 
  26. . 26 [Settings] 4. Associated services [+Add services] [Watson] 4

    5. Machine Learning [Add] 
  27. 27 6. [Existing] .4 . 7. Existing Service Instance 1

    Machine Learning 8. [Select] .4 . 
  28. . 28 9. [Settings] . Associated services .4 

  29. 5 29 1. [0101] . 2. iris.csv 5 

  30. 5 30 1. Files . 2. File . 

  31. 6 31 1. [Assets] . Asset 

  32. . 32 2. Models Watson Machine Learning models [+ New

    Watson Machine Learning model] 
  33. 6 33 3. [Name] 6 4. Machine Learning Service Machine

    Learning . 5. Select model type: Model builder 6. Select runtime: Apache Spark . 7. Manual 8. [Create] 
  34. . 34 9. Select data asset iris.csv [Next] 

  35. 35 9. Select Label Col CLASS . 6 6 6

    
  36. . 36 10. . .Feature Columns . Label Col .

    6 . . 
  37. . 37 11. . . . . . • Binary

    Classification: (2 . 6 • Multiclass Classification: ( . 6 ) • Regression: ( . ) 3 . . . Multiclass Classification 
  38. . 38 11. . 6. . Train 6 Test 6

    Holdout 6( ) . 
  39. . 6 39 12. . [+ Add Estimators] 

  40. 40 13. 6 .[Add] 6 

  41. 41 * Model Builder  Binary Classification Multiclass Classification Regression

    Logistic Regression 6 . Y Decision Tree Regression Y Y Y Random Forest Regression Y Y Y Gradient Boosted Tree Regression 6 Y Y Native Bayes Y Linear Regression Y Isotonic Regression . Y 
  42. 6 42 6 . 6 

  43. 6 43 14. [Next] . 

  44. 65 44 1 . 

  45. 45 1 . F 6 ???? 

  46. 6 46 17. PERFORMANCE [Save] . . 

  47. . 47 18. Overview 

  48. 48 1. 7 Web . [Deployments] 

  49. . 49 3. [Add Deployments 

  50. . 50 4. Name Deployment type Web service [Save] 

  51. . 51 . 

  52. 8 5 52 5 5. . 

  53. 53 DEMO        

  54. 1 . 54 1. Name 

  55. 1 . 55 2. Test 

  56. 56 3. [Predict] iris_test.csv 1 • SEPAL LENGTH : cm

    • SEPAL WIDTH : cm • PETAL LENGTH : . cm • PETAL WIDTH : . cm • Iris-setosa( ), • Iris-versicolour( ) • Iris-virginica ( ) 
  57. 14 57 . .

  58. . 58 Implementation 2 2 Web cURL, snipet

  59. 59 !#  $   " &%  

     
  60.  • Watson StudioModel Builder)1(/# % 0.+* • +* #

    %Web"-'  ,   $!&!,  
  61. IBM Cloud!# • %$ '0IBM Cloud!# )3   •

    "*, +&4-5 Watson6 /.API  42 1(  #  https://www.ibm.com/cloud-computing/jp/ja/lite-account/
  62. u R U etr ou kta IBM Partners https://ibm.biz/ibmpartners cphbdkik

    h I E 6 K A (s I E *IIAI E *41 *41 C (m l ,4 ) 5*3 0 K HE I B C – ) 1 3 C B AE 4C HD E HGHAI M A4 https://ibm.biz/buildwith 1,000 IBM Cloud A4 1 12,000l M 132 P S 1 3 ,C K f nid h k T W
  63. IBM@6F •  "Watson 0/' • IBM Cloud$,-  (

    !Zero +TJBot 23#$' • &%  ).*1  
  64. 64 Thank you twitter.com/KyokoNishito github.com/kyokonishito developer.ibm.com/jp

  65. 65