This video shows you how to use classification transformers and Watson machine learning with publicly available data about metabolic diseases to determine if someone has chronic kidney disease. For this video the Watson Machine Learning, Apache Spark, and object storage instances are already provisioned in IBM Bluemix, and there’s a project in Data Science Experience with all of the associated services. If you haven’t done so yet, watch the two “Getting Started” videos in the IBM Watson Machine Learning Center:
- “IBM Watson Machine Learning: Get Started With IBM Watson Machine Learning in IBM Bluemix“
- “IBM Watson Machine Learning: Create a project for Watson Machine Learning“
For this video, you’ll use a dataset available through the DSX community called "Chronic Kidney Disease."
Here you see a data preview and the column definitions.
Bookmark this dataset in the Watson Machine Learning Project so you can easily find it again later. Then download the dataset as a CSV file and navigate to your project. There you see a project that has all three associated services. Back on the overview tab, in the file slide-out panel, browse for the CSV file and open it. Once it’s finished loading, you’ll see it in the list of data assets. Now you’re ready to add a new flow to the project.
Now you’re ready to run the model. Right-click the classification node to run it. When it’s complete you’ll see a new model nugget which is the trained model.
Finally, back in IBM Bluemix on the IBM Watson Machine Learning service launch page, you can access the SPSS stream service dashboard. Upload the streams file and then create some deployment jobs.
Resources for you
- IBM Watson Machine Learning Learning Center
- IBM Data Science Experience
- What is Apache Spark?
- A beginner’s guide to artificial intelligence, machine learning, and cognitive computing
- Learn about > watson
- Learn about > machine learning,spss,r
- Learn about > Cognitive computing
- Machine Learning, Deep Learning 101