Open cryptocoinserver opened 2 years ago
Thanks for your valuable suggestions. We will try to add support for these features in the future version.
@cryptocoinserver Hi, thanks. Would you be able to help us add some of them?
Sadly, my time is pretty limited currently due to university and other project(s). If I'm not mistaken, you can just use the Volatility Features code from the kaggle notebook I linked: "This Notebook has been released under the Apache 2.0 open source license.".
And the seasonality stuff is easy, as pandas has those functions built in: https://pandas.pydata.org/docs/reference/api/pandas.Series.dt.dayofweek.html?highlight=dayofweek#pandas.Series.dt.dayofweek
I saw some people asking how to help on Slack. Maybe you could add some tasks to https://github.com/AI4Finance-Foundation/FinRL-Meta/projects for (those) contributors to work through?
Might be an interesting feature to test: https://www.kaggle.com/wptouxx/g-research-cointegration-analysis Cointegration tests for all asset pairs and obtaining their p-values.
Candle information (might help the model learning candlestick patterns):
def lower_shadow(df): return np.minimum(df['Close'], df['Open']) - df['Low']
def real_body(df):
maybe np.abs()
def full_length(df):
maybe np.abs()