On the Current Applications page, click Open next to the application you want to manage and click Build. The Build page allows you to modify the configuration of an application using widgets. Before the app opens, you must sign in with DataRobot and authorize access. To test a new configuration and open a preview of the end-user application, click Consume.
|Widget menu||Opens the widget menu, allowing you to add new widgets.|
|Settings||Modifies general configurations and permissions as well as displays app usage.|
|Build||Allows you to edit the application configuration.|
|Consume||Opens a preview of the end-user application.|
|Active Page||Displays each page in the application. Open the dropdown to view or manage pages.|
|Preview||Previews the application on different devices.|
|Save||Saves changes to the application.|
|Share||Shares an application with users, groups, or organzations.|
|Widget actions||Moves, resizes, hides, and deletes widgets.|
Applications are composed of widgets that create visual, interactive, and purpose-driven end-user applications. There are two types of widgets available—chart widgets and header widgets. All widgets must be configured before using an application. If a widget is not configured or is configured incorrectly, DataRobot displays an error message.
To add a widget to your application, click the widget menu in the upper-left corner, then drag-and-drop a widget from the left pane into the canvas.
Header widgets provide additional filtering options within an application. Parameters specified in a filtering widget are applied to all visible chart widgets.
See the table below for information on the available header widgets:
|Categories||Filters by one or more categorical features.|
|Dates||Filters by date features.|
|Numbers||Filters by numeric features. You must define a Min and Max in the widget properties.|
To configure a header widget, click the widget and select a feature to filter on. If there are no results in the filter drop-down, the dataset doesn’t include the required feature type.
Chart widgets add visualizations to an application and can be configured to surface important insights in your data and prediction results.
To configure a chart widget:
- Click to select the widget. The active selection is displayed in the left pane.
Click Manage. The Manage Feature window appears.
In the Dimensions tab, click the orange arrows next to one or more features you’d like to visualize on the x-axis. You can select categorical, date, and boolean features.
Click Measures and click the arrow next to the feature you'd like to measure on the y-axis. The Measures tab only displays numeric and custom features.
Click Save to apply the configuration.
With a widget selected, use the Data and Properties tabs to further customize its appearance and behavior.
You must select at least one dimension and one measure to configure a widget (with the exception of the Single Value widget).
If the widget displays a yellow error message stating there is no valid data, the application does not have access to the training data. You must create a project from the dataset in the AI Catalog.
Similar to feature transformations in the main DataRobot platform, you can create custom features for chart widgets in your application.
In the Manage Feature window, click Add custom feature.
Name the custom feature, then type the function and features using the supported syntax. The example below measures the cost of shipments per kilogram.
Click Create. The custom feature appears in the Measures tab of the Manage Features window.
You can only use numeric features to create custom feature expressions.
What-if and Optimizer¶
The What-if and Optimizer widget provides two tools for interacting with prediction results:
- What-if: A decision-support tool that allows you to create and compare multiple prediction simulations to identify the option that provides the best outcome. You can also make a prediction, then change one or more inputs to create a new simulation, and see how those changes affect the target feature.
- Optimizer: Identifies the maximum or minimum predicted value for a target by varying the values of a selection of flexible features in the model.
The What-if and Optimizer widget can be a scenario comparison tool, a scenario optimizer tool, or both.
To access the What-if and Optimizer widget, open the Active Page dropdown menu and select One Row.
With the widget selected, click Properties.
The app offers a number of settings that enhance the output of predicted values for your target. The table below describes each configurable parameter:
|What-if and Optimizer toggles||Enable scenario what-if: Toggle to enable or disable the comparison functionality.
Enable scenario optimizer: Toggle to enable or disable the optimizer functionality. If optimizer is enabled, you must select an option under Outcome of optimal scenario and can include a custom optimization expression.
|Outcome of optimal scenario||Sets whether to minimize or maximize the predicted values for the target feature. Minimizing leads to the lowest outcome (e.g., custom churn), and maximizing the highest (e.g., sale price).|
|Custom optimization expression||Allows inclusion of more than one target feature in your optimization. Create an equation contained in curled braces that uses one or more features, such as
|Set optimization algorithm||If enabled, choose from the algorithms listed and determine the number of simulations to run. Choose from the Grid Search, Particle Swarm, and Hyperopt algorithms or allow DataRobot to select the best algorithm for your selection of features.
Grid Search is an exhaustive, brute-force search of options on up to three flexible features. This may have long run time because it tries many possibilities, even if prior iterations don't suggest a strong outcome.
Particle Swarm is a metaheuristic strategy that tests a large number of options with up to 30 flexible features. It can be effective for numeric flexible features but may not be as effective for flexible categorical features.
Hyperopt efficiently explores significantly fewer options on up to 20 flexible features. It is effective for categorical and numeric features. With this algorithm, you can set up to 400 simulations. More iterations may yield better results, but can result in longer run times as it takes many iterations to converge.
|Constrain sum of features||Constraints ensure that each record’s optimization iterations don’t output results that exceed a given value for the target feature. For example, if you are optimizing the price of a home, you may want to expand the gross living area by finishing part of the basement or adding a bedroom. You can use a sum constraint to limit the space each project is allowed to occupy in sq/ft. Choose Maximum (selected solutions must never exceed) or Equality (selected solutions must be equal) to the constrain value.|
|Views||Display the information as a chart, a table, or both.|
The default configuration is determined by the template selected during app creation. The What-if and Optimizer widget is disabled for the Predictor template but can be enabled by clicking the Eye icon.
Custom optimization expressions¶
For batch prediction optimization, use a field defined in the batch upload as part of the custom optimization expression the same way you use a feature from the dataset that the app is deployed from. For example, if you label a field in a spreadsheet
net_profit, and you have a
time_to_market feature in the project's underlying dataset, the following would be a valid custom expression:
Constrain sum of features¶
To select the features that you want to be part of the sum, turn on Constrain sum of features at the bottom of the Properties tab. Under Part of sum features, click Select.
In the Manage Features window, check the box next to at least two fixed or flexible features—the selected features must be numeric. This option is not available if you use the Hyperopt algorithm.
Click Save when you are finished selecting features.
The Data tab allows you to select the features that represent the factors you have control over when searching for your optimized outcome. For example, when optimizing the price of homes, some flexible features are the quality of the kitchen, the cost of the mortgage, and the size of the garage.
To manage flexible features, click Manage.
Use the orange arrows to add or remove features.
Click Save to confirm your flexible features.
When you have selected flexible features, you can apply constraints to them. This instructs the app to only include values falling in the range determined by numeric constraints or specific values for a categorical feature.
To apply constraints to a feature, click Set Constraints on the Data tab.
Selecting a flexible feature expands a dropdown displaying the feature distribution.
For categorical features, open the Search from categories dropdown menu and choose which features to include in the simulation by checking the corresponding box.
For numeric features, you can enter individual values for the minimum and maximum numeric ranges or drag the boundaries on the histogram.
Toggle Integer values on to include only integer values (exclude decimals).
Click Save to confirm your feature constraints.
Pages divide an application into separate sections that you can navigate between—allowing you to organize and group insights in a way that makes sense for your use case. By default, each application has the following pages:
|Home||Includes the Add Row widget to upload batch predictions and All Rows widget to view a history of prediction results.|
|Create||The single record prediction page. Configures available feature fields for making predictions.|
|One row||The prediction results page. Configures prediction insights for end-users.|
Default pages can be renamed but not deleted. To manage pages, click the Active Page drop-down and select Manage pages.
In the Manage Pages window, you can:
|Add new page||Adds a new page to the application.|
|Reorder||Modifies the order of the pages.|
|Rename||Renames a page.|
|Delete||Deletes a page (excludes default pages).|
|Hide||Hides a page from end-users.|
When editing an application, click the Settings tab to manage the following application details:
The General Configuration tab allows you to edit the application name and description.
The Permissions tab allows you to manage access to the application and share it with other users, groups, and organizations.
If you want to share an application with a user that does not have a DataRobot license, open the Who can access the app dropdown menu and select Anyone outside your network. A shareable link is generated in the Link sharing on field.
All users who access the app with this link have Consumer permissions. Note that you can revoke access to users accessing the link by clicking Generate new link. You will need to share the new link to provide those users with access again.
The App Usage tab displays the number of users who viewed the application over the specified time range, as well as user activity.
To select a different time range for the chart, open the Time range dropdown menu and select a new option. The chart automatically updates.