Parking occupancy for prediction in Guangzhou city
There are 30 parking lots in the downtown area of Guangzhou city in this dataset, including 10 commercial building parking lots, 3 hospital parking lots, 5 office parking lot, 3 sport and recreational facilities parking lots, 4 tourist parking lots, and 5 residential parking lots. The data is from june 1 to june 30, 2018. Time step is 5min.
Steps to reproduce
# Meta TSD-GRU is proposed for city-scale real-time parking occupancy prediction in medium term. Step to reproduce The proposed method is implemented on PyTorch. Please install relevant modules first. Step 0: Data preprocessing (optional) Run Fourier.py, output the Cycle term, create a new column FS in origin data. Then compute the Effect term and create another new column INDICATOR in data file. This step has been pre-completed. Step 1: Input data Open 'Meta TSD-GRU.py', task0 is the target task for testing, other tasks are used to pre-training, please type in the right Path and Filename. Step 2: Set hyperparameter task_num is the number of pre-training tasks. period_length: n * 5min, (such as n=6 for 30min prediction) Step 3: Run and output Run 'Meta TSD-GRU.py', the prediction will be conducted with 10 times, output: an average MAPE, the fine-tuning time and epoch. If you have any questions, please send an email to the following mailbox. Thanks for using. Author: quhaoh Mail: firstname.lastname@example.org