# Predictive Maintenance Model – RandomForest

This model predicts **Engine Condition** using multiple engine sensor parameters.

## Model Information
- **Best Model:** RandomForest
- **Algorithm:** Tuned RandomForest Classifier
- **Training Method:** GridSearchCV + Cross Validation
- **Task Type:** Classification

## Evaluation Metrics
|                  |   F1-Score |
|:-----------------|-----------:|
| RandomForest     |   0.963115 |
| GradientBoosting |   0.775914 |
| AdaBoost         |   0.76212  |

## Dataset
Dataset used is hosted in the Hugging Face dataset hub:
- https://huggingface.co/datasets/MohammedSohail/engine_maintenance_data

## How to Use

```python
from huggingface_hub import hf_hub_download
import joblib
import pandas as pd

model_path = hf_hub_download(
    repo_id="MohammedSohail/engine_maintenance_model",
    filename="models/best_model.pkl" 
)

model = joblib.load(model_path)

# new_data = pd.DataFrame([
#     [750, 3.5, 6.0, 2.5, 80.0, 75.0] # Example sensor values
# ], columns=['Engine rpm', 'Lub oil pressure', 'Fuel pressure', 'Coolant pressure', 'lub oil temp', 'Coolant temp'])
# prediction = model.predict(new_data)
# print(f"Predicted Engine Condition: {prediction[0]} (0=Normal, 1=Faulty)")
```