Preprocessed AL data used in paper "Multi variables time series information bottleneck" with the GitHub code This dataset is created from a public available dataset of solar power data collected in Alabama by NREL. The npz file is a numpy (np) compressed data and can be loaded using np.load with allow_pickle=True Loaded data is then a python dict described bellow. Each sample 'data' is a np.ndarray with 2 dimensions: time (various length) and wavelength (length=137 representing 137 solar plants ordered like in NREL). Each sample is given a 'position' which is a list of length 4: position[1] is a string that gives the name of the event position[4] is a boolean vector that gives the time positionsof the corresponding sample in the original sequence of public IRIS level2 data Data file info : Type: .npz Size: 34.48MB *** Key: 'data_TR_AL' ndarray data of length 161 containing np.ndarray of shapes ['various', 137] *** Key: 'data_VAL_AL' ndarray data of length 11 containing np.ndarray of shapes ['various', 137] *** Key: 'data_TE_AL' ndarray data of length 57 containing np.ndarray of shapes ['various', 137] *** Key: 'data_TR' ndarray data of length 161 containing np.ndarray of shapes ['various', 137] *** Key: 'data_VAL' ndarray data of length 11 containing np.ndarray of shapes ['various', 137] *** Key: 'data_TE' ndarray data of length 57 containing np.ndarray of shapes ['various', 137] *** Key: 'position_TR_AL' ndarray data of length 161 containing ndarray data of length 4 containing mix of types {'str', 'ndarray', 'int'} *** Key: 'position_VAL_AL' ndarray data of length 11 containing ndarray data of length 4 containing mix of types {'str', 'ndarray', 'int'} *** Key: 'position_TE_AL' ndarray data of length 57 containing ndarray data of length 4 containing mix of types {'str', 'ndarray', 'int'} *** Key: 'position_TR' ndarray data of length 161 containing ndarray data of length 4 containing mix of types {'str', 'ndarray', 'int'} *** Key: 'position_VAL' ndarray data of length 11 containing ndarray data of length 4 containing mix of types {'str', 'ndarray', 'int'} *** Key: 'position_TE' ndarray data of length 57 containing ndarray data of length 4 containing mix of types {'str', 'ndarray', 'int'}