search

yashasvini121 / predictive-calc

An interactive web application developed with Streamlit, designed for making predictions using various machine learning models. The app dynamically generates forms and pages from JSON configuration files. ⭐ If you found this helpful, consider starring the repo!
https://predictive-calc.streamlit.app/
MIT License
25 stars 72 forks source link

Issue: Implement Logging for Model Training and Predictions #6

Closed vibhorjoshi closed 1 month ago

vibhorjoshi commented 2 months ago

The code lacks a logging mechanism to track important events, such as when the model is trained, saved, or when a prediction is made. Logging would help in debugging and monitoring model performance.

Suggested Changes:

Add logging to track when models are saved or loaded. Log model training details, such as RMSE or other performance metrics. Log prediction inputs and outputs for traceability.

yashasvini121 commented 2 months ago

Sure, @vibhorjoshi, go ahead!

vibhorjoshi commented 2 months ago

@yashasvini121 but I given a mentor role

yashasvini121 commented 2 months ago

@vibhorjoshi, If you're a mentor in GSSOC Extended, you can either work on this personally without it counting toward program contributions or leave the issue for others. However, when creating future issues, do mention your role in the program (if any) beforehand.

Let me know how you plan to proceed.