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

Custom dataset #1

Open
k-nayak opened this issue Apr 7, 2022 · 1 comment
Open

Custom dataset #1

k-nayak opened this issue Apr 7, 2022 · 1 comment

Comments

@k-nayak
Copy link

k-nayak commented Apr 7, 2022

Can i use this on smaller custom datasets? If yes what sort of changes do you advice i should consider before trying it ?

Thanks in advance.

@bharathraja
Copy link

You can change the lines in the preprocess,py file to the names of the data you are training for. Use "Date" for the date entries, and the prediction value column as "Close". You have to clean-up the date to get good accuracy, like use percentage change instead of absolute values.

    # subset data
    train_df = train_df[['day',<ENTER CUSTOM VARIABLE NAMES HERE>]]
    test_df = test_df[['day',<ENTER CUSTOM VARIABLE NAMES HERE>]]

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