Lesson 1 of 5
Step 1: Define the training data
Explanation
Every ML project starts with data. You will build a classifier that tells apples apart from oranges using two features: weight in grams, and a texture score from 0 (very smooth) to 10 (very bumpy). Below is a small labeled dataset — each entry already has the correct label, exactly like the labeled examples from earlier modules.
Visual explanation
Read this from left to right: what goes in, what happens, and what comes out.
Your project begins by turning a real item into clear input features and a label.
In plain language
First define what each training example contains and what answer the classifier should predict.
Remember
A clear problem definition makes every later step easier.
What to do
Run the starter code as-is to see the training set printed, then add one more labeled fruit of your own to the trainingData array and run it again.
Code Lab
JavaScriptRun the code, then add one more fruit object to trainingData and run again.
Console
Click Run to execute your code and see console output here.