Time interval | ROI |
---|---|
1d (Human) | 2.74% |
1d (Model) | 304.96% |
4h (Human) | 36.86% |
4h (Model) | 405.03% |
1h (Human) | 37.55% |
1h (Model) | 290.01% |
Time interval | ROI |
---|---|
1d (Human) | 3.11% |
1d (Model) | 12.19% |
4h (Human) | 18.30% |
4h (Model) | 31.64% |
1h (Human) | 19.79% |
1h (Model) | 27.58% |
- Test OS: Ubuntu 16.04 LTS
- Python version: 3.8
- Create folders.
mkdir images
mkdir checkpoints
- Please run
pip install –r requirements.txt
to install the needed libraries.
- Clone the repo.
- Follow the instruction to download required data.
# ETHUSDT
python download-kline.py -s ETHUSDT -startDate 2017-08-01 -endDate 2021-12-01
# BTCUSDT
python download-kline.py -s BTCUSDT -startDate 2017-08-01 -endDate 2021-12-01
- It will download the required data as below. Unzip the zip files under the
1h
,4h
and1d
directories.
binance_prediction_pytorch
`-- binance-public-data
`-- data
`-- data
`-- spot
|-- daily
`-- monthly
`-- klines
|-- ETHUSDT
`-- BTCUSDT
- Then soft link the data directory to the repo root as below.
binance_prediction_pytorch
|-- binance-public-data
`-- data
`-- spot
|-- daily
`-- monthly
`-- klines
|-- ETHUSDT
`-- BTCUSDT
- Run training and evaluation on ETHUSDT. It will store the checkpoints under
checkpoints
with ticker name and time interval if don't specify the checkpoint path with--ckpt
.
# 1d
./run.sh ETHUSDT 1d
# 4h
./run.sh ETHUSDT 4h
# 1h
./run.sh ETHUSDT 1h
- Run training and evaluation on BTCUSDT
# 1d
./run.sh BTCUSDT 1d
# 4h
./run.sh BTCUSDT 4h
# 1h
./run.sh BTCUSDT 1h
- Specify the checkpoint path with
eval
mode to only do the inference.
./run.sh ETHUSDT 1h --ckpt ${YOUR_CHECKPOINT_PATH} --eval
- Directly try with jupyter notebook file Final.ipynb.