https://github.com/rikcav/api-ml-model

This project implements a simple Flask API for predicting BMI (Body Mass Index) categories based on input data. The API uses a RandomForestClassifier model trained on a dataset containing BMI information.
https://github.com/rikcav/api-ml-model

api bmi flask ml random-forest-classifier

Last synced: 3 months ago
JSON representation

This project implements a simple Flask API for predicting BMI (Body Mass Index) categories based on input data. The API uses a RandomForestClassifier model trained on a dataset containing BMI information.

• Host: GitHub
• URL: https://github.com/rikcav/api-ml-model
• Owner: rikcav
• Created: 2024-02-11T02:28:16.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-03-20T11:07:14.000Z (about 1 year ago)
• Last Synced: 2025-01-21T11:30:33.828Z (5 months ago)
• Topics: api, bmi, flask, ml, random-forest-classifier
• Language: Python
• Homepage:
• Size: 841 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# BMI Prediction API

This project implements a simple Flask API for predicting BMI (Body Mass Index) categories based on input data. The API uses a RandomForestClassifier model trained on a dataset containing BMI information.

## Files in the Project

- **app.py**: Contains the Flask API implementation with two endpoints, one for testing the API (`/`) and another for getting the BMI prediction output (`/getPredictionOutput`).

- **model.py**: Contains the code for loading the dataset, preprocessing the data, training the RandomForestClassifier model using Grid Search for hyperparameter tuning, and saving the best model to a file.

- **prediction.py**: Contains a function for loading the trained model and making predictions based on input data.

## Usage

1. Clone this repository to your local machine.

2. Install the required dependencies using `pip install -r requirements.txt`.

3. Run the Flask API using `python app.py`. The API will be available at `http://localhost:5000`.

4. Use a tool like Postman or curl to test the API endpoints. You can send a POST request to `/getPredictionOutput` with JSON data containing the features required for prediction.

## Example Request

```json

{

    "Gender": 1,

    "Height": 170,

    "Weight": 70,

    "Age": 25

}

```

## Example Response

```json

{

    "predict": "Normal"

}

```