deep learning bitcoin
1.0.0
透過深度學習利用比特幣價格模式。與 OpenAI 一樣,我們根據原始像素資料訓練模型。這正是經驗豐富的人如何看待曲線並採取行動的方式。
到目前為止,我們實現了:
5 分鐘價格資料訓練(Coinbase USD)
訓練集的一些例子
price_open price_high price_low price_close volume close_price_returns close_price_returns_bins close_price_returns_labels
DateTime_UTC
2017-05-29 11:55:00 2158.86 2160.06 2155.78 2156.00 21.034283 0.000000 (-0.334, 0.015] 5
2017-05-29 12:00:00 2155.98 2170.88 2155.79 2158.53 47.772555 0.117347 (0.015, 0.364] 6
2017-05-29 12:05:00 2158.49 2158.79 2141.12 2141.92 122.332090 -0.769505 (-1.0322, -0.683] 3
2017-05-29 12:10:00 2141.87 2165.90 2141.86 2162.44 87.253402 0.958019 (0.713, 1.0623] 8
git clone https://github.com/philipperemy/deep-learning-bitcoin.git
cd deep-learning-bitcoin
./data_download.sh # will download it to /tmp/
python3 data_generator.py /tmp/btc-trading-patterns/ /tmp/coinbaseUSD.csv 1 # 1 means we want to use quantiles on returns. 0 would mean we are interested if the bitcoin goes UP or DOWN only.
如果您有興趣建立一個巨大的資料集(coinbase.csv 包含大約 18M 行),最好在背景模式下執行該程式:
nohup python3 -u data_generator.py /tmp/btc-trading-patterns/ /tmp/coinbaseUSD.csv 1 > /tmp/btc.out 2>&1 &
tail -f /tmp/btc.out
如果您看到此錯誤:
_tkinter.TclError: no display name and no $DISPLAY environment variable
請參考此解決方案:https://stackoverflow.com/questions/37604289/tkinter-tclerror-no-display-name-and-no-display-environment-variable
要建置 docker 映像,只需執行
docker build -t dlb .
從存儲庫資料夾中,然後運行容器
docker run -it --name dlb -v $PWD:/app dlb /bin/bash
目前資料夾將被安裝到/app
中。若要驗證正確的安裝,請在容器內執行
root@c11ef702a6d6:/app# mount| grep app
/dev/sda2 on /app type ext4 (rw,relatime,errors=remount-ro,data=ordered)