Series

Learning path: Getting started with IBM Cloud Pak for Data

Patterns, tutorials, and code to help you learn and use IBM Cloud Pak for Data

Save Like

By Scott Dangelo
Updated February 24, 2020 | Published October 7, 2019

Level Topic Type
100 Introduction to IBM Cloud Pak for Data Article
101 Data Virtualization on IBM Cloud Pak for Data Tutorial
201 Data visualization with Data Refinery Tutorial
202 Find, prepare, and understand data with Watson Knowledge Catalog Tutorial
301A Data analysis, model building, and deploying with Watson Machine Learning with notebook Pattern
301B Automate model building with AutoAI Tutorial
301C Build a predictive machine learning model quickly and easily with IBM SPSS Modeler Tutorial
401 Monitoring the model with Watson OpenScale Pattern

For many industries, the journey to AI is a long-term strategy that's only beginning. In this learning path, we'll examine the case of a Telco company and use IBM Cloud Pak® for Data as the data and AI platform. We'll look at the process of collecting data, which can reside on multiple clouds, in various database formats, and with various needs for access control. In our Telco, we'll show how to organize the data with visualizations and other tools. Next, we'll look at the case of customer churn, and create a machine learning model that helps us to predict the risk that our Telco's clients will leave. Finally, we'll analyze the Telco's deployment of the machine learning model by looking at the model's performance, explainability, and fairness.

Part of this learning path explains how to use AutoAI in Watson Studio to automate the model building process. To learn more about AutoAI, look at the Simplify your AI lifecycle with AutoAI series.

The learning path consists of step-by-step tutorials and patterns. To get started, click on a card below, or see the table above for a complete list of topics covered.

Introduction to IBM Cloud Pak for Data

Article

Introduction to IBM Cloud Pak for Data

October 8, 2019

Learn about:

  • What is IBM Cloud Pak for Data?
  • Terms and concepts
  • Take a product walkthrough
  • Architecture

Data Virtualization on IBM Cloud Pak for Data

Tutorial

Data Virtualization on IBM Cloud Pak for Data

October 4, 2019

Learn about:

  • Adding data sets
  • Adding data source to data virtualization
  • Virtualizing data and creating joined view
  • Assigning virtualized data to a project
  • Adding roles to users and performing admin tasks

Data visualization with Data Refinery

Tutorial

Data visualization with Data Refinery

October 4, 2019

Learn about:

  • Loading data into IBM Cloud Pak for Data for use with Data Refinery
  • Transforming a sample data set
  • Using Data Flow steps to track your work
  • Visualizing data with charts and graphs

Find, prepare, and understand data with Watson Knowledge Catalog

Tutorial

Find, prepare, and understand data with Watson Knowledge Catalog

February 18, 2020

Learn about:

  • Setting up the catalog and data
  • Adding collaborators, control access, and categories
  • Adding data classes, business terms, and policy rules

Data analysis, model building, and deploying with Watson Machine Learning with notebook

Code Pattern

Data analysis, model building, and deploying with Watson Machine Learning with notebook

October 4, 2019

Learn about:

  • Using Jupyter Notebooks to analyze data
  • Running Notebooks in IBM Cloud Pak for Data
  • Building, testing, and deploying a machine learning model
  • Creating a front-end app to interface with deployed model

Automate model building with AutoAI

Tutorial

Automate model building with AutoAI

January 15, 2020

Learn about:

  • Handling regression and classification problems without code
  • Using this for feature engineering, model selection, hyperparameter tuning
  • Deploying and using models

Build a predictive machine learning model quickly with IBM SPSS Modeler

Tutorial

Build a predictive machine learning model quickly and easily with IBM SPSS Modeler

February 24, 2020

Learn about:

  • Uploading data
  • Creating an SPSS® Modeler flow
  • Using the SPSS tool to inspect data and glean insights
  • Modifying and preparing data for AI model creation using SPSS
  • Training a machine learning model with SPSS and evaluating results

Monitoring the model with Watson OpenScale

Code Pattern

Monitoring the model with Watson OpenScale

October 4, 2019

Learn about:

  • Setting up Watson OpenScale™ Data Mart
  • Binding Watson Machine Learning to OpenScale
  • Enabling payload logging and performance monitor
  • Scoring German credit model using machine learning


Next: Introduction to IBM Cloud Pak for Data

Legend

Related

Article

Predicting telecom call drops with AI

August 24, 2020
Event | Conference

Big Data London 2020 - Building fair and explainable AI pipelines with Margriet Groenendijk

London September 24, 2020 1:45 pm GMT
Event | Workshop

IBM Cloud Day @ KFUPM

March 4, 2020 1:00 pm MSK