Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

test,train and val .npy files are corrupted #2

Open
Navneetsajith1 opened this issue May 2, 2024 · 8 comments
Open

test,train and val .npy files are corrupted #2

Navneetsajith1 opened this issue May 2, 2024 · 8 comments

Comments

@Navneetsajith1
Copy link

Navneetsajith1 commented May 2, 2024

could you check the tes, train and val.npy files. they seem to be corrupted

@maoxiaowei97
Copy link
Owner

41401714651979_ pic
Thanks for you question, I downloaded the files from this github and loaded the datasets. Maybe you can download again and try to load them. The dataset here provides a sample for running the algorithm. You can obtain the raw data and preprocess files from https://github.com/wenhaomin/LaDe.

@Navneetsajith1
Copy link
Author

Navneetsajith1 commented May 2, 2024 via email

@maoxiaowei97
Copy link
Owner

import pickle
with open('train.pickle', 'rb') as f:
    loaded_data_train = pickle.load(f)

data.zip
Please try to load the files saved by pickle, thanks~

@Navneetsajith1
Copy link
Author

Navneetsajith1 commented May 6, 2024 via email

@Navneetsajith1
Copy link
Author

Navneetsajith1 commented May 23, 2024 via email

@Navneetsajith1
Copy link
Author

Navneetsajith1 commented May 23, 2024 via email

@maoxiaowei97
Copy link
Owner

Thanks for your question~

  1. V_len denotes the number of couriers' finished and unfinished tasks/packages in a sample.

  2. Each row in the raw dataset contains information on an order, such as accept time, location, and promised pickup time of a package. First, we get a set of orders for each courier finished at a period by preprocess.py. This process aims to obtain the trajectories of each courier in the pickup process. Then, we treat each trajectory as a sample to construct inputs and outputs for the route and time prediction model by dataset.py. Specifically, the input mainly contains information on the finished and unfinished tasks and the courier's information. The route label is a permutation of the index of the unfinished tasks.

3.Please describe your dataset and your problem, and I would be happy if I could provide some suggestions.

@Navneetsajith1
Copy link
Author

Navneetsajith1 commented Aug 21, 2024 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants