Displayr incorporates advances in AI technology into our software to make it easier for you to analyze your data. In order to use these features, you must opt in to Displayr AI; see our Displayr AI article for more details. This article will walk you through the different features that are available if Displayr AI is enabled.
- Chat
- Research Agent
- Tidy and Clean Your Data
- Text Analytics
- Using AI Prompts to Create Outputs
- AI-generated Custom Variables
- Help with Code
Chat
Use our AI-based Chat agent to help you build and analyze your report using guided prompts. Once you click on a prompt, let Displayr do the work for you. In addition to using the guided prompts, you can ask Chat how to do anything in Displayr. It will provide the steps that you'll need to take, as well as link to our Help documentation for related content.
Research Agent
The Research Agent feature allows you to use AI to analyze and create reports. Think of Research Agent as a data analysis intern; you provide the data and guidance on what questions and information you want covered in the report, and Research Agent automatically analyzes the data and creates the report for your review. It will automatically find and highlight key insights found in your data, as well as any specific questions you need investigated.
Tidy and Clean Your Data
We all know data can be messy. Get some of the grunt work done, and let Displayr AI tidy your data for you using the Data Preparation Agent. You can choose which functions you want Displayr AI to run from a list of options. Additionally, once Displayr AI is enabled, new variable sets you create will be automatically relabeled in a smarter way. See Better Variable Set Labeling on Combine.
Text Analytics
Text Categorization
If you're looking for an AI-assist when it comes to classifying your text data, but still want some flexibility to refine and edit with a human eye, you can use Displayr AI text categorization. The built-in categorization tool allows you to utilize AI to help create themes and classify your text data while enabling you to create and modify themes and edit and refine the classification. For details on how to do this, go to How to Classify Text Data.
Translation
You can use AI to translate your text data. This method will create a new text variable containing the translated text, which you can use for text categorization. Select the text variable in the Data Sources tree that needs translation, then hover and click + > Text Manipulation > Translate. From there, you can refine the default Prompt as needed and specify the Source language. The Source language dropdown includes options to auto-detect the input language and to specify using a variable if you have an existing variable with a list of languages in your data set.
Identify Poor Text Data
Oftentimes, raw text data contains non-sensical responses, contains expletives, or is, in general, "garbage". You can identify good vs bad responses in your text variables by hovering over the variable in the Data Sources tree, clicking + > Data Quality > Poor Text Data, and then entering a Prompt. For example:
A new variable will be created, which you can use as a filter variable and edit the raw data or remove cases, if necessary.
Sentiment Analysis
To take your text analysis a step further, you can assign numeric values to the text responses using AI to determine sentiment using + > Numeric Transformations > Sentiment from the Data Sources tree. For example, I can take the translated hotel reviews from above and prompt AI to assign a value of 1 to positive reviews and -1 to negative reviews:
Using AI Prompts to Create Outputs
You can use various functions available using Calculation > Custom AI from the toolbar or by clicking Plus + > Calculation > Custom AI in the Report tree. See examples in Using Customizable Displayr AI Features. And make sure to read Getting Started with AI Prompting in Displayr for tips to help improve your prompts when using the AI features.
Additionally, you can use AI to analyze your data and create a report for you using the Research Agent. You provide guidance about the data and questions you want answered, and AI does the rest. All of the outputs are editable and can be updated, allowing you to check and correct before shipping your report to your clients. See Research Agent for more information.
AI-generated Custom Variables
If you want to create new custom variables, AI can help. In the Data Sources tree, the Plus + > Custom Code > AI menu creates different types of variables based on a Prompt and Input Variables. The default behavior will do a complete case analysis of the variables selected and will flag cases with complete data. Flags are coded based on the type of variable you want to create:
- Date: Constructs a Date/Time variable that takes today’s date if the data is complete, and is a missing value if there is incomplete data.
- Numeric: Constructs a Numeric variable which takes the value of 1 if the data is complete and 0 if the data has any missing values. You can click Usable as filter to be able to filter in complete cases on outputs and analyses.
- Nominal: Constructs a Nominal variable that takes the label 'Complete' if the data is complete and 'Incomplete' if the data has any missing values.
- Ordinal: Same as 'Nominal' but creates an Ordinal variable.
- Text: Same as 'Nominal' but creates a Text variable.
You can also customize the Prompt via the object inspector to have the AI perform different actions, such as converting numbers stored as a Text variable into an actual Numeric variable or identifying mentions of proper names (e.g., brands) in text, and then creating a new text variable that has only that information in it.
Help with Code
Before getting the AI to help write code, you should review the programming section of our writing prompts article. The features used to help you with programming in Displayr are:
- R Code - can help you generate code in the R language. It's useful for creating or checking code for calculations, calculation grids, and R variables. As discussed in Getting Started with AI Prompting in Displayr, our R function libraries have not been specifically used to train the AI; thus, it's recommended to search the Help Center for specific custom coding tasks, such as creating formatted tables with our CreateCustomTable() function. See AI R Code Writer for examples and tips.
Next
How to Automatically Check and Prepare Your Data with Data Preparation Agent
Using Customizable Displayr AI Features