Filter - Filters for Train-Test Split

This QScript creates 2 new filters based on a random 70%/30% split of the selected data. These filters can then be applied to predictive models in order to separate a training data set from a test data set. The QScript can be amended to adjust the split ratio.

Example

The result of running this script is shown below. The first 2 variables are the new filters created.

Technical details

The value of trainPercentage in the QScript code below controls the split ratio. The default of 70 means that 70% of the data (rounded to the nearest whole number of instances) is selected as part of the Training split and the remaining 30% is selected by the Testing split filter.

By adjusting this value as described below in Customizing the QScript the percentages in the training and testing filters can be controlled.

How to apply this QScript

Start typing the name of the QScript into the Search features and data box in the top right of the Q window.
Click on the QScript when it appears in the QScripts and Rules section of the search results.

OR

Select Automate > Browse Online Library.
Select this QScript from the list.

Customizing the QScript

This QScript is written in JavaScript and can be customized by copying and modifying the JavaScript.

Customizing QScripts in Q4.11 and more recent versions

Start typing the name of the QScript into the Search features and data box in the top right of the Q window.
Hover your mouse over the QScript when it appears in the QScripts and Rules section of the search results.
Press Edit a Copy (bottom-left corner of the preview).
Modify the JavaScript (see QScripts for more detail on this).
Either:
- Run the QScript, by pressing the blue triangle button.
- Save the QScript and run it at a later time, using Automate > Run QScript (Macro) from File.

Customizing QScripts in older versions

Copy the JavaScript shown on this page.
Create a new text file, giving it a file extension of .QScript. See here for more information about how to do this.
Modify the JavaScript (see QScripts for more detail on this).
Run the file using Automate > Run QScript (Macro) from File.

JavaScript

// This script creates 2 new filters based upon a random split of the data.
 
includeWeb("QScript Selection Functions");
includeWeb("QScript Functions to Generate Outputs"); 
 
filtersForTrainTestSplit();

function filtersForTrainTestSplit() {
    
    const is_displayr = inDisplayr();

    // Set percentage of data used for training set
    let trainPercentage = prompt("What percentage of the data set should be used as the training set?", 70);
    if (trainPercentage < 0 || trainPercentage > 100) {
        log("Invalid split.  Please ensure that trainPercentage is between 0 and 100.");
        return false;
    }
    
    // Get the data
    let dataFile;
    const user_selections = getAllUserSelections()
    let selected_questions = user_selections.selected_questions;
    if (selected_questions.length > 0)
        dataFile = project.report.selectedQuestions()[0].dataFile;
    else if (project.dataFiles.length == 1)
        dataFile = project.dataFiles[0];
    else if (project.dataFiles.length == 0) {
        log("Please add a data set.");
        return false;
    } else if (!is_displayr) {
        dataFile = dataFileSelection()[0];
    } else {
        log("Please select data from a single data set.")
        return false;
    }


    // Create a training filter based on a random sample 
    let RText = "percentage <- " + trainPercentage + " # Change this number to change the percentage in the training sample\n" +
                "set.seed(123) # This ensures that the randomization is identical each time\n" +
                "n <- " + dataFile.totalN + " # This is the total sample size\n" +
                "indices <- sample.int(n, round(percentage * n / 100))\n" +
                "filter <- rep(0, n)\n" +
                "filter[indices] <- 1\n" + 
                "filter";
    let new_q_name = preventDuplicateQuestionName(dataFile, "Training sample");
    
    let test;
    let train;

    try {
        train = dataFile.newRVariable(RText, preventDuplicateVariableName(dataFile, "training"), new_q_name, null);
    } catch (e) {
        log("Could not create train filter: " + e);
        return false;
    }
    train.needsCheck = false;

    // Create testing filter of the data not selected by the training filter 
    RText = "as.numeric(!`" + dataFile.name + "`$Variables$" + train.name + ")";    // backticks allow hyphen in dataFile.fileName
    try {
        test = dataFile.newRVariable(RText, preventDuplicateVariableName(dataFile, "testing"), "Testing sample", null);
    } catch (e)
    {
        log("Could not create test filter: " + e);
        return false;
    }
    test.needsCheck = false;

    // Combine the 2 new variables into a Pick-Any question
    trainTest = dataFile.setQuestion(preventDuplicateQuestionName(dataFile, "Train test split"), "Pick Any", [train, test]);
    let suffix = trainTest.name.replace(/^Train test split/, "");
    trainTest.variables[0].label = "Training sample" + suffix;
    trainTest.variables[1].label = "Testing sample" + suffix;
    trainTest.needsCheckValuesToCount = false;
    trainTest.isFilter = true;
    insertAtHoverButtonIfShown(trainTest);
    reportNewRQuestion(trainTest, "Filter");
    return true;
}