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

Feature/forecast auto select #825

Merged
merged 10 commits into from
May 20, 2024
Merged

Feature/forecast auto select #825

merged 10 commits into from
May 20, 2024

Conversation

prasankh
Copy link
Member

@prasankh prasankh commented May 8, 2024

ODSC-54590

  • Added the feature to automatically choose the most effective forecast model on backtests with the auto-select option.
  • Used sampling to train across all models for K backtest iterations.
  • Added performance graph for backtest in the report

@oracle-contributor-agreement oracle-contributor-agreement bot added the OCA Verified All contributors have signed the Oracle Contributor Agreement. label May 8, 2024
ahosler
ahosler previously approved these changes May 14, 2024
Copy link
Member

@ahosler ahosler left a comment

Choose a reason for hiding this comment

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

Great work!

darenr
darenr previously approved these changes May 14, 2024
@@ -250,6 +247,23 @@ def generate_report(self):
sec9 = rc.DataTable(self.eval_metrics, index=True)
train_metrics_sections = [sec9_text, sec9]

backtest_sections = []
if self.spec.model == "auto-select":
Copy link
Member

Choose a reason for hiding this comment

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

NIT: i would recommend move it to the consts.

Copy link
Member Author

Choose a reason for hiding this comment

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

Done

str
The type of the model.
"""
from ..model_evaluator import ModelEvaluator
Copy link
Member

Choose a reason for hiding this comment

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

Why do we need this import here, can it be move on top?

Copy link
Member Author

Choose a reason for hiding this comment

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

Done

from .operator_config import ForecastOperatorConfig


class ModelEvaluator:
Copy link
Member

Choose a reason for hiding this comment

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

I noticed that there are no comments and pydocs at all :) Could you add them. I also noticed that somewhere we use typing but somewhere not, for the consistency could you add typing evarywhere?

Copy link
Member Author

Choose a reason for hiding this comment

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

Updated

name=column,
))

import report_creator as rc
Copy link
Member

Choose a reason for hiding this comment

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

why do we need this import here? Can it be moved on top?

Copy link
Member Author

Choose a reason for hiding this comment

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

Done

@@ -187,7 +187,7 @@ def run_yaml(tmpdirname, yaml_i, output_data_path, test_metrics_check=True):

def populate_yaml(
tmpdirname=None,
model="auto",
model="auto-select",
Copy link
Member

Choose a reason for hiding this comment

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

What would be the difference between auto and auto-select options?

Copy link
Member Author

Choose a reason for hiding this comment

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

To avoid the confusion, we replaced 'auto' with auto-select. auto was ambiguous a bit as we have automlx models. auto-select indicates that the system automatically chooses the best framework or model more clearly.

@prasankh prasankh dismissed stale reviews from ahosler and darenr via c2d1416 May 15, 2024 06:03
@ahosler ahosler self-requested a review May 20, 2024 08:02
@ahosler ahosler merged commit 2a625ed into main May 20, 2024
6 checks passed
@ahosler ahosler deleted the feature/forecast-auto-select branch May 20, 2024 18:30
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
OCA Verified All contributors have signed the Oracle Contributor Agreement.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants