Book Image

Data Democratization with Domo

By : Jeff Burtenshaw
Book Image

Data Democratization with Domo

By: Jeff Burtenshaw

Overview of this book

Domo is a power-packed business intelligence (BI) platform that empowers organizations to track, analyze, and activate data in record time at cloud scale and performance. Data Democratization with Domo begins with an overview of the Domo ecosystem. You’ll learn how to get data into the cloud with Domo data connectors and Workbench; profile datasets; use Magic ETL to transform data; work with in-memory data sculpting tools (Data Views and Beast Modes); create, edit, and link card visualizations; and create card drill paths using Domo Analyzer. Next, you’ll discover options to distribute content with real-time updates using Domo Embed and digital wallboards. As you advance, you’ll understand how to use alerts and webhooks to drive automated actions. You’ll also build and deploy a custom app to the Domo Appstore and find out how to code Python apps, use Jupyter Notebooks, and insert R custom models. Furthermore, you’ll learn how to use Auto ML to automatically evaluate dozens of models for the best fit using SageMaker and produce a predictive model as well as use Python and the Domo Command Line Interface tool to extend Domo. Finally, you’ll learn how to govern and secure the entire Domo platform. By the end of this book, you’ll have gained the skills you need to become a successful Domo master.
Table of Contents (26 chapters)
1
Section 1: Data Pipelines
7
Section 2: Presenting the Message
12
Section 3: Communicating to Win
17
Section 4: Extending
21
Section 5: Governing

Training a Domo AutoML model

To understand the utility of Domo AutoML, let's get a public dataset on the prices of used cars and use it to build a predictive model based on used car prices:

  1. Download the Used Car Dataset from Kaggle: https://www.kaggle.com/austinreese/craigslist-carstrucks-data.
  2. Use the Domo File Upload Connector to place the vehicles.csv data into a Domo dataset named Vehicles, as shown in the following screenshot. The file is large, so it may take several hours to load:

Figure 16.2 – Vehicles dataset post-import

  1. After the file has been loaded in, click on MORE, then AutoML.
  2. This will take us to a page that looks similar to the one shown in Figure 16.1. Click the GET STARTED button.
  3. In the AutoML window, set the modeling parameters shown in the following screenshot. Set price for Column to predict and Automatic (Recommended) for Task type. Then, expand the Advanced tab and set AUTOML CANDIDATES TO RUN...