This course goes through the stages of a data science project from importing data to deployment, using services in Watson Studio and Watson Machine Learning for Cloud Pak for Data.

• Introduction to Watson Studio and Watson Machine Learning for Cloud Pak for Data 
• Work with analytics projects 
• Import data 
• Prepare data for modeling with Data Refinery 
• Automate building supervised models with AutoAI experiment 
• Work with notebooks 
• Deploy Watson Machine Learning models

Clients who want to use the data science capabilities on Cloud Pak for Data or those who want to learn more about data science

Knowledge of your business requirements

Introduction to Watson Studio and Watson Machine Learning for Cloud Pak for Data 
• Describe the IBM Cloud Pak for Data platform and AI 
• Describe the four rungs in the ladder to AI 
• Describe the personas on the platform 
• Describe how to collaborate on the platform 
• Describe the CRISP-DM methodology 

Work with analytics projects 
• Describe analytics projects 
• Create analytics projects 
• Leverage industry accelerators 

Import data 
• Identify key concepts in working with data 
• Describe correct column types 
• Add local files to the project 
• Created connections 
• Add connected data sets to the project 

Prepare data for modeling with Data Refinery 
• Identify three tasks in preparing data for modeling  
• Describe the capabilities of Data Refinery 
• Describe steps, flows, and jobs 
• Join data 
• Profile data 
• Visualize data 

Automate building supervised models with AutoAI experiment 
• Describe when AutoAI experiment can be used 
• Describe the importance of column types 
• Describe how the best model is identified 
• Describe pipelines 
• Save AutoAI experiment pipelines to the project 
• Explain evaluation measures 

Work with notebooks 
• Work with notebooks 
• Load data into a notebook 
• Prepare data for modeling 
• Build machine learning models 
• Save machine learning models to the project 

Deploy Watson Machine Learning models 
• Identify Watson Machine Learning models 
• Describe deployment spaces 
• Create deployment spaces 
• Describe model deployment options 
• Create deployments 
• Test deployments