This project is about predicting the future closing prices of tokens in the blockchain space using a sequence model implemented in Python.
A sequence model is a type of machine learning model that's great for making predictions based on a series of data points. In this project, we use it to analyze historical token prices and predict future ones.
To run the project, you need to have python 3.11 or higher installed on your machine. You can download it from the official website.
After installing python, you can clone the project repository and navigate to the project directory in your terminal. Then, run the following command to install the required dependencies:
pip install -r requirements.txtOnce the dependencies are installed, you can run the project using the following command:
jupyter notebook model.ipynbThis will open the Jupyter notebook in your browser, where you can see the code and run it to make predictions.
- An AWS account
- The AWS CLI installed and configured (configure it with your AWS credentials by running
aws configure) - Docker
- Terraform
-
Create an ECR repository to store the Docker image
aws ecr create-repository --repository-name your-repository-name --image-scanning-configuration scanOnPush=true --region your-region
-
Build the Docker image
docker build -t your-aws-account-id.dkr.ecr.your-region.amazonaws.com/your-repository-name:latest . -
Authenticate Docker to your ECR repository
aws ecr get-login-password --region your-region | docker login --username AWS --password-stdin your-aws-account-id.dkr.ecr.your-region.amazonaws.com -
Push the Docker image to your ECR repository
docker push your-aws-account-id.dkr.ecr.your-region.amazonaws.com/your-repository-name:latest
-
Fill in all variables in
fargate.tf -
Deploy the Fargate service
terraform init terraform apply
The endpoint of the model should be
http://ecs-task-public-ip:8501/v1/models/TokenPricePredictionModel:predict.