What are labels in DataSets?

[ApoY2k]

(I am just starting to learn ML in general, and this library in particular. So it might very well be that this question is entirely obsolete when you're more "in the know" of the material, but I just can't seem to find something that helps me)

I don't quite understand how DataSets work here. I understand they represent the training or test data, and, as in ML we operate with numbers and calculations, all data is effectively just numbers.

However, reading the source and documentation i always come across this notion of "labels" in DataSets. most notably in the DataSet class itself, where methods like getY(idx: Int): Float exist. But to me, label as a word has always meant something like a tag attached to something. What "number" is this supposed to be?

If I have training data like in a CSV file as

input_1 | input_2 | input_3 | expected_score
0.4     | 1.5     | -3.4    | 1.2

and wanted to build a model for this, what is the "label" here? And what should fun getX(idx: Int): FloatArray return?

Again, maybe this is entirely obvious when you have used other ML libraries before, but to me none of this is self-explanatory enough. Or did I miss some documentation?

[ApoY2k]

https://saturncloud.io/blog/python-machine-learning-labels-and-features-a-guide-for-data-scientists/

In machine learning, the terms “labels” and “features” refer to two types of data used to build a model. Features are the inputs to the model, while labels are the outputs.

For example, let’s say you are building a model to predict the price of a house. The features might include the number of bedrooms, the square footage, and the neighborhood. The label, in this case, would be the price of the house.

this cleared things up