Skip to content

Conversation

surbhigoel77
Copy link
Collaborator

@surbhigoel77 surbhigoel77 commented Aug 5, 2024

Rebasing the current net with main

Closes #19

In order to accomodate data coming from multiple sources, we need to replace the hardcoded inputs with variables whose values are extracted from the dataset during the code run.

Files updated:

  1. loaddata.py
  2. Model.py
  3. train.py

Files Removed:

  1. 'NN_pred.py'

Files Added:

  1. main.py

In train.py, the .nc data files are read and the variables are extracted and normalised. This part should be taken out of train.py and be kept in a separate preprocessing.py file, to keep train.py common for different data sources. train.py can be converted into a module instead. We can also have a test notebook in the repo.

@surbhigoel77 surbhigoel77 requested review from jatkinson1000 and removed request for jatkinson1000 August 5, 2024 11:30
@omarjamil omarjamil self-requested a review November 19, 2024 13:48
@omarjamil omarjamil mentioned this pull request Apr 24, 2025
@omarjamil
Copy link
Member

This should be resolved by PR #34

@omarjamil
Copy link
Member

This is too out-of-sync and not tested properly.

@omarjamil omarjamil closed this Apr 24, 2025
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

Successfully merging this pull request may close these issues.

Generalise the training module

2 participants