How to Convert a Predictive Model Simulator into an Allocation Tool for New Data

This article describes how to convert a predictive model simulator created in Displayr into a tool that can allocate a predicted category for a range of records. The predictive model simulator is designed to only predict one record at a time using the control selections. However, we can update this setup to apply the predictions to all records in a new data set. 

Requirements

• An existing regression or machine learning predictive model. This uses the Gradient Boost example from How to Create a Predictive Model Simulator in Displayr.
• New data to apply the predictive model to.

Method

Set up your new data

Either:

• Create a pasted table:
  1. In another data source, such as Excel, copy your table, including any headers.
  2. Navigate to the location you want to paste in the table (either on a Page or an output off a Page directly in the Report tree) and use right click > Paste to create the output. If pasting a table on a Page, you can also use Ctrl+V (Cmd+V on a Mac).
  3. A table output will be created where you selected, as well as a summary.table in the Data Sources tree.
  4. [Optional] If needed, you can modify what is treated as row and column headers in your table, sorting, and more, see Method - Adjusting the look of your pasted summary table.
• Create a raw data table:
  1. Add your new data set to your document via Data Sources > Plus (+).
  2. Select the variables that match the ones used as predictors in your predictive model.
  3. In the toolbar, select Table > Raw Data > Variable(s) and tick Variable Names.

Importantly, the response labels need to match exactly those used in your predictive model; otherwise, the prediction will be NA for that record.

The column names also need to match the variable names used in your predictive model. The variable name is found under General > General > Name when you select a variable in the Data Sources tree:

Set up your prediction calculation

In this example, we now have a table called raw.data. To predict the outcome from the model on this new data, we can simplify the code as follows:

1. Select Calculation > Custom Code in the toolbar and click on the page.

2. Paste the below into the code editor:

DF = raw.data
arguments <- list(model, newdata = DF)
as.vector(do.call(predict, arguments))

Update the names of your new data (DF) table and model above, if necessary.

This will now run the prediction algorithm on all our new data:

3. OPTIONAL: Export the predicted category output from the toolbar via Share > Export Report > Excel.

Next

How to Create a Predictive Model Simulator in Displayr