Random Forest Model Training

[vbramhadevi]

Description

Train a machine learning model using the prepared dataset to predict flight events. A Random Forest classifier will be used for this implementation. All outputs must be stored inside the inference/ folder.

Tasks

• Create training script train_model.py inside inference/
• Load processed dataset or labeled dataset
• Train a Random Forest model using: input: 8 flight parameters and output: event_label
• Configure model parameters (basic defaults are fine)
• Train model on training dataset
• Generate predictions on test dataset
• Evaluate model using: Accuracy, Precision, and Recall
• Print evaluation results clearly
• Save trained models as inference/models/bestModel.pkl & finalModel.pkl
• Document how to run the training script
• Push code and model file to inference/

Acceptance Criteria

• Random Forest model is successfully trained
• Model generates predictions on test data
• Evaluation metrics (accuracy, precision, recall) are computed
• Trained model files (bestModel.pkl & finalModel.pkl) is saved