Example of prediction with TreeNet® Classification

Note

This command is available with the Predictive Analytics Module. Click here for more information about how to activate the module.

A team of researchers collects and publishes detailed information about factors that affect heart disease. Variables include age, sex, cholesterol levels, maximum heart rate, and more. This example is based on a public data set that gives detailed information about heart disease. The original data are from archive.ics.uci.edu.

The researcher can use the gradient boosted classification tree model to predict response class probabilities for new observations.

Note

This example uses the dataset from Fit Model, but prediction is also available when you use Discover Key Predictors to create the model.

  1. Complete Example of Fit Model with TreeNet® Classification.
  2. Click the Predict button at the bottom of the results.
  3. From the drop-down list, select Enter individual values.
  4. Enter the following values. This example uses 2 values for each predictor, but you can use up to 3 values.
    Age 35 35  
    Rest Blood Pressure 140 140  
    Cholesterol 233 233  
    Max Heart Rate 150 165  
    Old Peak 2.3 2.3  
    Sex Male Female  
    Chest Pain Type 2 1  
    Fasting Blood Sugar True True  
    Rest ECG 0 1  
    Exercise Angina      
    Slope 1 3  
    Major Vessels 0 2  
    Thal Normal Normal  
  5. Click OK.

Interpret the results

Minitab uses the gradient boosted classification trees in the results to estimate the class probability of a heart disease event for the a set of prediction values. The researchers find that the probability of a heart disease event using the specified settings is approximately 0.185 for the first set and 0.55 for the second set.

TreeNet® Classification: Heart Diseas vs Age, Rest Blood P, Cholesterol, ...

Model Summary Total predictors 13 Important predictors 13 Number of trees grown 500 Optimal number of trees 351 Statistics Training Test Average -loglikelihood 0.2341 0.3865 Area under ROC curve 0.9825 0.9089 95% CI (0.9706, 0.9945) (0.8757, 0.9421) Lift 2.1799 2.1087 Misclassification rate 0.0759 0.1750
Tune Hyperparameters to Identify a Better Model... One Predictor Partial Dependence Plots

Select More Predictors to Plot...

Two Predictor Partial Dependence Plots

Select More Predictors to Plot...

Predict... TreeNet® Classification Predict

Prediction for Heart Disease

Settings Age = 35, Rest Blood Pressure = 140, Cholesterol = 233, Max Heart Rate = 150, Old Peak = 2.3, Sex = Male, Chest Pain Type = 2, Fasting Blood Sugar = True, Rest ECG = 0, Exercise Angina = "", Slope = 1, Major Vessels = 0, Thal = Normal
Prediction Prob (Class Prob (Class Obs Class = Yes) = No) 1 No 0.145216 0.854784

Prediction for Heart Disease

Settings Age = 35, Rest Blood Pressure = 140, Cholesterol = 233, Max Heart Rate = 165, Old Peak = 2.3, Sex = Female, Chest Pain Type = 1, Fasting Blood Sugar = True, Rest ECG = 1, Exercise Angina = "", Slope = 3, Major Vessels = 2, Thal = Normal
Prediction Prob (Class Prob (Class Obs Class = Yes) = No) 2 No 0.426671 0.573329
By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy