---
license: apache-2.0
datasets:
- codesignal/wine-quality
metrics:
- accuracy
pipeline_tag: tabular-classification
---

# Random Forest Model for Wine-Quality Prediction

This repository contains a Random Forest model trained on wine-quality data for wine quality prediction. The model has been trained to classify wine quality into six classes. During training, it achieved a 100% accuracy on the training dataset and a 66% accuracy on the validation dataset.

## Model Details
- **Algorithm**: Random Forest
- **Dataset**: Wine-Quality Data
- **Objective**: Wine quality prediction (Six classes) - (3,4,5,6,7,8) and prediction above 5 is good quality wine. 
- **Dataset Size**: 320 samples with 11 features. 
- **Target Variable**: Wine Quality
- **Data Split**: 80% for training, 20% for validation
- **Training Accuracy**: 100%
- **Validation Accuracy**: 66%

## Usage
You can use this model to predict wine quality based on the provided features. Below are some code snippets to help you get started:

```python
# Load the model and perform predictions
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
import joblib

# Load the trained Random Forest model (assuming 'model.pkl' is your model file)
model = joblib.load('model/random_forest_model.pkl')

# Prepare your data for prediction (assuming 'data' is your input data)
# Ensure that your input data has the same features as the training data

# Perform predictions
predictions = model.predict(data)

# Get the predicted wine quality class
# The predicted class will be an integer between 0 and 5