PB preprocessed data used in paper "Multi variables time series information bottleneck"

<p>Preprocessed PB data&nbsp;used in&nbsp;paper &quot;Multi variables time series information bottleneck&quot; with the&nbsp;<a href="https://github.com/DenisUllmann/IB-MTS">GitHub</a>&nbsp;code</p> <p>This dataset is created from a public available dataset of solar power data collected in Alabama by <a href="https://www.nrel.gov/grid/solar-power-data.html">C</a><a href="https://pems.dot.ca.gov/">alTrans</a>.</p> <p>The npz file is a numpy (np) compressed data and can be loaded using np.load with allow_pickle=True<br> Loaded data is then a python dict described bellow.</p> <p>Each sample &#39;data&#39; is a np.ndarray with 2 dimensions: time (various length) and wavelength (length=325&nbsp;representing 325 traffic detectors ordered like in <a href="https://www.nrel.gov/grid/solar-power-data.html">C</a><a href="https://pems.dot.ca.gov/">alTrans</a>).</p> <p>Each sample is given a &#39;position&#39; which is a list of length 4:<br> position[1] is a string that gives the name of the event<br> position[4] is a boolean vector that gives the time positionsof the corresponding sample&nbsp;in the original sequence of public IRIS level2 data</p> <p>Data file info :<br> Type: .npz<br> Size: 114.23MB<br> *** Key: &#39;data_TR_PB&#39;<br> ndarray data of length 3<br> containing np.ndarray of shapes [12160, 325]</p> <p>*** Key: &#39;data_VAL_PB&#39;<br> ndarray data of length 3<br> containing np.ndarray of shapes [868, 325]</p> <p>*** Key: &#39;data_TE_PB&#39;<br> ndarray data of length 3<br> containing np.ndarray of shapes [4343, 325]</p> <p>*** Key: &#39;data_TR&#39;<br> ndarray data of length 3<br> containing np.ndarray of shapes [12160, 325]</p> <p>*** Key: &#39;data_VAL&#39;<br> ndarray data of length 3<br> containing np.ndarray of shapes [868, 325]</p> <p>*** Key: &#39;data_TE&#39;<br> ndarray data of length 3<br> containing np.ndarray of shapes [4343, 325]</p> <p>*** Key: &#39;position_TR_PB&#39;<br> ndarray data of length 3<br> containing ndarray data of length 4<br> containing mix of types {&#39;str&#39;, &#39;ndarray&#39;, &#39;int&#39;}</p> <p>*** Key: &#39;position_VAL_PB&#39;<br> ndarray data of length 3<br> containing ndarray data of length 4<br> containing mix of types {&#39;str&#39;, &#39;ndarray&#39;, &#39;int&#39;}</p> <p>*** Key: &#39;position_TE_PB&#39;<br> ndarray data of length 3<br> containing ndarray data of length 4<br> containing mix of types {&#39;str&#39;, &#39;ndarray&#39;, &#39;int&#39;}</p> <p>*** Key: &#39;position_TR&#39;<br> ndarray data of length 3<br> containing ndarray data of length 4<br> containing mix of types {&#39;str&#39;, &#39;ndarray&#39;, &#39;int&#39;}</p> <p>*** Key: &#39;position_VAL&#39;<br> ndarray data of length 3<br> containing ndarray data of length 4<br> containing mix of types {&#39;str&#39;, &#39;ndarray&#39;, &#39;int&#39;}</p> <p>*** Key: &#39;position_TE&#39;<br> ndarray data of length 3<br> containing ndarray data of length 4<br> containing mix of types {&#39;str&#39;, &#39;ndarray&#39;, &#39;int&#39;}</p>