Fix model hyperparameter tuning inconsistencies for Elastic Net, Support Vector Regressor, and Random Forest Regressor

[sohampirale]

Summary

This PR addresses the bug where multiple machine learning models had hyperparameter configurations defined but were not utilizing them for optimization.

Fixes : #60

Changes Made

• Fixed the condition in gaze_tracker.py to properly handle Random Forest Regressor instead of incorrectly handling Elastic Net and Support Vector Regressor
• Removed incorrect conditional branches for Elastic Net and Support Vector Regressor that were not using their defined hyperparameters
• Ensured Random Forest Regressor is handled correctly to prevent runtime errors

Files Modified

• app/services/gaze_tracker.py - Updated model selection logic to properly handle hyperparameter configurations

Impact

This resolves the inconsistency where models with defined hyperparameter configurations weren't using them for optimization, leading to suboptimal performance and potential runtime errors.

Screenshots

Tested all the models

• Elastic Net

• Support Vector Regressor

• Random Forest Regressor