Xiaowei's processed feature data file (processed_features.npy) has 20 input variables. But in sntemp_input_output_subset.feather there are 24 features. Three of those are not meaningful as model input (IMO): 'seg_id_nat', 'model_idx', 'date' which leaves 21 total variables. So my question is, which one of these did Xiaowei not include? Or are we working from a different dataset?
Xiaowei's processed feature data file (
processed_features.npy
) has 20 input variables. But insntemp_input_output_subset.feather
there are 24 features. Three of those are not meaningful as model input (IMO):'seg_id_nat', 'model_idx', 'date'
which leaves 21 total variables. So my question is, which one of these did Xiaowei not include? Or are we working from a different dataset?