Skip to content

Black_lodge model/Production model template#37

Open
sarakallis wants to merge 29 commits intoproductionfrom
prod-model-template
Open

Black_lodge model/Production model template#37
sarakallis wants to merge 29 commits intoproductionfrom
prod-model-template

Conversation

@sarakallis
Copy link
Collaborator

[Not ready to be merged]
Let's use this PR to clean up the CM model code for replicating the production ensemble

To-dos are in the model readme

@sarakallis sarakallis added the help wanted Extra attention is needed label Jun 20, 2024
"steps": [*range(1, 36 + 1, 1)],
"deployment_status": "production",
"creator": "Sara",
"preprocessing": "float_it", #new
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

where is the float_it function?

month_first = partitioner_dict['train'][0]

if partition == 'forecasting':
month_last = partitioner_dict['train'][1] + 1 # no need to get the predict months as these are empty
Copy link
Collaborator

@xiaolong0728 xiaolong0728 Jul 1, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

To make the current stepshifter work, we still need the predict months even if they are empty (otherwise the predictions might have some problems)

from config_hyperparameters import get_hp_config


def train(model_config, para_config):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You can refer to my new training function (I haven't merged the main so it's branch more_model and you can check orange_pasta). In short, we don't train three models together but train a specific one based on the arguments instead.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

help wanted Extra attention is needed

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants