Watson Studio provides you with the environment and tools to solve your business problems by collaboratively working with data. You can choose the tools you need to analyze and visualize data, to cleanse and shape data, to ingest streaming data, or to create, train, and deploy machine learning/deep learning models. Watson Studio contains both open source and IBM value-add capabilities to help infuse AI into business to drive innovation.
Watson Studio is tightly integrated with the Watson Knowledge Catalog. The Watson Knowledge Catalog is a secure enterprise catalog to discover, catalog and govern your data/models with greater efficiency. The catalog is underpinned by a central repository of metadata describing all the information managed by the platform. Users will be able to share data with their colleagues more easily, regardless of what the data is, where it is stored, or how they intend to use it. In this way, the intelligent asset catalog will unlock the value held within that data across user groups—helping organizations use this key asset to its full potential.
The labs in this workshop will illustrate the myriad features included in Watson Studio, and Watson Knowlege Catalog. The labs need to be completed in order, except for Lab-6 which is standalone.
-
Lab-1 - This lab will set up the Watson Studio environment for subsequent labs and introduce you to the Project and Community features of Watson Studio
-
Lab-2 - This lab will introduce you to the features of IBM's Watson Knowledge Catalog. Watson Knowledge Catalog is a secure enterprise catalog to discover, catalog and govern your data and modeling assets with greater efficiency.
-
Lab-3 - This lab will introduce the Data Refinery. Data Refinery is a self-service data preparation tool for data scientists, data engineers, and business analysts. Data Refinery provides profiling, visualization, and a robust set of transforms to prepare data for analytics purposes. We will continue to use the 3 Trafficking data sets in this lab to demonstrate data profiling, data visualization, and data preparation capabilities of the Data Refinery tool. Note the datasets use simulated data.
-
Lab-4 - In this lab, you will use the Watson SPSS Modeler capability to explore, prepare, and model the trafficking data. The SPSS Modeler is a drag and drop capability to build machine learning pipelines.
-
Lab-5 - In this lab, you will use SparkML in Watson Studio to run simulated travel data through a machine learning algorithm, automatically tune the algorithm, and load the data into a DB2 Warehouse database.
-
Lab-6 -This lab will use the MNIST computer vision data set to train a convolutional neural network (CNN) model to recognize handwritten digits. The Watson Studio neural network flow editor, Watson Studio experiment builder and the Watson Machine Learning component will be used to build, train, save, deploy, and test the model.
-
Lab-7 -In this lab, you will use IBM's Watson Machine Learning GUI to train, evaluate, and deploy a Watson Machine Learning model based on the trafficking datasets. You will then deploy a web application that calls the Watson Machine Learning model.
-
Lab-8 - In this lab, you will learn some of the fundamentals of using RStudio and Shiny in Watson Studio to work and interact with data in a DB2 Warehouse on Cloud database and then to create a fully operational "reactive" web application that you can enhance further.