I don’t understand why when predicting, the ‘data’ is used but we’re predicting the ‘target’
2 Likes
Think of it as a target y
that is computed as a function f
of the data X
. Then f
is learned during fit
and then used to compute y = f(X)
during predict
, i.e. predict the target (outcome) given the data (input).
That makes more sense, thank you.