The shape of traj_{user_id}.npy in stmm_dataset.py

[UTBigdata]

Dear Jinmeng,

I hope this message finds you well. First of all, thank you for sharing this excellent project. It has been incredibly insightful and valuable for my work.

I am currently exploring your implementation. While reviewing the code, I noticed the following line:

real_points = np.load(f'{self.traj_path}/traj_{user_id}.npy').astype(np.float)

However, I am a bit unclear about the expected shape of the traj_{user_id}.npy file. Based on the dataset documentation and the context of its usage, my understanding is that it could be a 2D array with shape [trajectory_length, 2], where 2 represents [latitude, longitude] for each trajectory point.

Could you kindly confirm if this understanding is correct? Additionally, if the shape differs or has specific conventions, I would appreciate it if you could provide further details or examples.

Thank you very much for your time and assistance. I look forward to your response.

Best regards,
Fern