I have coded up a program that has a scoring target value plus other necessary values associated with that target value, plus the same features are used as dependents in my prediction engine. Up to now I have been calling these arrays [target_data, context_data]. Now I must split out the scoring target variable and I feel like I don't have the right language to make this clear. The prediction engine is for a time series network, so the same features are used in the X array as in the Y array. [Y_target, Y_context, X_target, X_context] doesn't feel right.
For the sake of clarity, I have data containing feature_names = ["feature0", "feature1", ... "feature9"], with "feature0" determining the score on values from time_t based in an array containing these values from time_0,..time_n. My real data has descriptive names.
My desired output has test/train/validation versions for a Y structure containing an array of the scoring feature(s) alongside an array of the non-scoring feature(s), and X having the same scoring/non-scoring structure. I need names for these arrays. I am definitely overthinking things, so any basic clarity or obvious answers please. Broader answers appreciated too, so I don't get tangled up in future.
