Videos
You can watch videos to learn about Cloud Pak for Data as a Service, including the core services of Watson Studio, Watson Machine Learning, and Watson Knowledge Catalog, plus the other services that add tools to Watson Studio.
Choose a category:
- Getting started
- Notebooks
- Dashboards
- Data Refinery
- Machine learning
- Decision Optimization
- Visual Recognition
- Natural Language Classifier
- RStudio
- Streams flows
- Watson Knowledge Catalog
Getting started
-
Figure 1. 
Sign up for an account -
Figure 2. Create an empty project, imported project, and project from sample -
Figure 3. Tour the gallery -
Figure 4. Create a catalog and find assets quickly -
Figure 5. Manage object storage -
Figure 6. Collaborate on projects -
Figure 7. Add connected data from a data source -
Figure 8. Create a folder asset in a project
Notebooks
-
Figure 9. Jupyter notebook basics -
Figure 10. Create Jupyter notebook and custom environment -
Figure 11. Load and analyze public data sets -
Figure 12. Publish notebooks to GitHub -
Figure 13. Analyze NY restaurant inspections data -
Figure 14. Analyze precipitation data using a Gallery notebook -
Figure 15. Analyze Db2 Warehouse on Cloud data in a Scala notebook -
Figure 16. Use Spark Machine Learning libraries in a Jupyter notebook -
Figure 17. Use Spark R to load data and run SQL queries -
Figure 18. Use the SQL-Cloudant connector in a Scala notebook -
Figure 19. Use the SQL-Cloudant connector in a Python notebook -
Figure 20. Visualize data with Brunel
Dashboards
-
Figure 21. Create and share a Business Analytics Dashboard
Data Refinery
-
Figure 23. Add connected data from a data source -
Figure 24. Blend data from multiple sources -
Figure 25. Copy data to a new target -
Figure 26. Shape data
Machine learning
-
Figure 27. Run an AutoAI experiment based on a sample -
Figure 28. Build a binary classification model using an AutoAI experiment -
Figure 29. Build a multiclass classification model by running an AutoAI experiment -
Figure 30. Test a model using the Watson Machine Learning APIs -
Figure 31. Score a Predictive Model Built with IBM SPSS Modeler -
Figure 32. Provision the services in IBM Cloud for use with command line and Python client libraries
Decision Optimization
-
Figure 33. Introduction to Decision Optimization -
Figure 34. Build Decision Optimization models using modeling assistant -
Figure 35. Deploy Decision Optimization model -
Figure 36. Develop and deploy machine learning and optimization models -
Figure 37. Walk through the Decision Optimization Interface
For more information, see the Decision Optimization blog.
Visual Recognition
-
Figure 40. Get started with Visual Recognition -
Figure 41. Create, train, and test a Visual Recognition model -
Figure 42. Retrain a Visual Recognition model -
Figure 43. Build an object detection model
Natural Language Classifier
-
Figure 44. Create and train a Natural Language Classification model -
Figure 45. Edit and retrain a Natural Language Classification model
RStudio
-
Figure 46. Overview of RStudio IDE -
Figure 47. Load data into RStudio -
Figure 48. Analyze Db2 Warehouse data in RStudio -
Figure 49. Run Shiny applications in RStudio
Streams flows
-
Figure 50. Streams flows overview -
Figure 51. Create a streams flow manually with the canvas -
Figure 52. Create a streams flow based on a sample -
Figure 53. Monitor a running streams flow -
Figure 54. Ingest data from IoT Devices - Part 1 -
Figure 55. Use Python to process streaming data - Part 2 -
Figure 56. Use Watson Machine Learning Predictive Modeling with Streaming Data
Watson Knowledge Catalog
-
Figure 57. Overview of Watson Knowledge Catalog -
Figure 58. Foundational concepts -
Figure 59. Create a catalog and find assets quickly -
Figure 60. Add assets to a catalog -
Figure 61. Create a folder asset in a catalog -
Figure 62. Use assets in a project -
Figure 63. Polices overview -
Figure 64. Mask data -
Figure 65. Auto-discover assets from a data connection -
Figure 66. Track data asset activity