README.md

---
library_name: scikit-learn
tags:
- classification
- tabular-data
metrics:
  accuracy: 0.6629
  precision: 0.6890
  recall: 0.8482
  f1: 0.7603
params: {"max_depth": 10, "min_samples_leaf": 1, "min_samples_split": 10, "n_estimators": 200}
---
# Random Forest Classifier for Engine Condition Prediction

This repository contains a trained `RandomForestClassifier` model for predicting engine condition (Normal vs. Faulty) based on various engine parameters.

## Model Details

-   **Algorithm**: RandomForestClassifier
-   **Framework**: scikit-learn

## Performance Metrics (on Test Set)

-   **Accuracy**: 0.6629
-   **Precision**: 0.6890
-   **Recall**: 0.8482
-   **F1-Score**: 0.7603

## Hyperparameters

```json
{
  "max_depth": 10,
  "min_samples_leaf": 1,
  "min_samples_split": 10,
  "n_estimators": 200
}
```

## Usage

To load and use this model:

```python
import joblib
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="HumanMachine74/engine-performance-data-model", filename="random_forest_model.joblib")
model = joblib.load(model_path)

# Example prediction (assuming X_new is your new data)
# predictions = model.predict(X_new)
```