This project is a easily reproducible Python/Docker project to create an API that predicts the price of BTC and ETH using OHLCV data. The API is defined using Zalando's connexion package, which leverages the Flask framework.
Current implementation smooths the raw close % change data (previous 72 hours). This data is fed into a 1D Convolutional Layer, which feeds into a dual-layer LSTM with linear activation function (network graph coming soon!).
Note: Anaconda is recommended to manage the project environment. Environment creation without Anaconda is untested
mv .env_template .env # Must have a .env file for some functions to find correct path
make create_environment
conda activate crypto_predict
make install_dev
make testcrypr-data --hours 10000
crypr-features
crypr-models --epochs 20make run_dockerNow find your prediction at http://localhost:5000/predict?coin=BTC
The Jupyter Notebooks in this project serve as rich visual examples of how data preprocessing and model training is done for the prediction API.
Run with
make run_jupyterNotebook server will be at http://localhost:8888
- More coins!
- More models (xgboost)
- Visualize price predictions in a web app based on the developed prediction api
- Use unstructured text data to calculate sentiment or other metrics to use in prediction
- Use transfer learning from financial markets and other crypto coins to enhance the RNN model
├── api/ # connexion pyfiles and config
│ ├── app.py
│ └── swagger.yaml
├── crypr/ # Python Package
│ ├── scripts/
│ │ ├── make_dataset.py
│ │ ├── make_features.py
│ │ └── make_train_models.py
│ ├── tests/
│ │ ├── data/
│ │ ├── test_app.py
│ │ ├── test_build.py
│ │ ├── test_cryptocompare.py
│ │ ├── test_model.py
│ │ └── test_transformers.py
│ ├── build.py
│ ├── cryptocompare.py
│ ├── models.py
│ ├── transformers.py
│ ├── types.py
│ ├── util.py
│ └── zoo.py
├── data/
│ ├── external/
│ ├── interim/
│ ├── processed/ # Data generated by crypr-features
│ └── raw/ # Data retrieved with crypr-data
├── docker/ # Deploy the API
│ ├── Dockerfile
│ └── wait_for_healthy.sh
├── models/ # DL models trained with crypr-models
├── notebooks/
│ ├── cwt_rnn_model_dev.ipynb
│ ├── data_exploration.ipynb
│ ├── jupyter_notebook_config.py
│ ├── model_dev.ipynb
│ ├── preprocessing.ipynb
│ ├── rnn_model_dev.ipynb
│ ├── self-attention-model-dev.ipynb
│ ├── statistical_model_dev.ipynb
│ ├── tree_model_dev.ipynb
│ ├── wt_multiple_preprocessing.ipynb
│ ├── wt_single_preprocessing.ipynb
│ ├── wt_smooth_preprocessing.ipynb
│ └── wt_smooth_rnn_model_dev.ipynb
├── references/
│ ├── bao2017.pdf
│ └── hsieh2011.pdf
├── Dockerfile.dockerhub # For hub.docker.com automated build hook
├── LICENSE
├── MANIFEST.in
├── Makefile
├── README.md
├── requirements.txt # Development Python packages
├── setup.cfg
├── setup.py
├── .coveragerc
├── .coveralls.yml
├── .dockerignore
├── .env # Copied from .env_template
├── .env_template
├── .gitignore
└── .travis.yml
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent