ML-Telemetry

This project serves as a platform for telemetry data analysis using machine learning. The application is containerized with Docker, allowing for easy deployment and hot-reloading during development.

Table of Contents

• Getting Started
  • Download Elysia's Telemetry Data
  • Running Locally with Docker Compose
  • Starting the Server for Hot Reloading
• Accessing the Application
• Docker Hub Repository

---

Getting Started

To begin working with the app, clone this repository and ensure you have Docker installed.

Download Elysia's Telemetry Data

Download historical telemetry data for Elysia from Google Drive:

• Google Drive - Telemetry Data
• S3 - Elysia.Laps.feather Save the data files locally in the training_data folder to ensure they are accessible when running the app.
• S3 - Elysia.Packet.feather

Save the data files locally in the training_data folder to ensure they are accessible when running the app.

Running Locally with Docker Compose

To run the app in a Docker container:

docker-compose up --build

This will build and start the containerized application, exposing it on http://localhost:8000.

Starting the Server for Hot Reloading

Alternatively, to run the app with hot reloading support, use:

python -m uvicorn app:app --reload --host 0.0.0.0 --port 8000

This is particularly useful during development, as it reloads the application automatically when changes are detected.

---

Accessing the Application

Once the app is running, you can access it by navigating to:

• http://localhost:8000

---

Docker Hub Repository

You can pull the application image directly from Docker Hub if you prefer not to build locally:

• Docker Hub - ML Telemetry