Share New Research 
I'm trying to use machine learning to scalp crypto using current and previous period data: quotebar and indicator data rsi, atr, aroon. I developed the model in the research environment but now trying to implement it in a backtest. I need the quotebars and indicator values to be saved in rolling windows. I can't get the data to save so I can use it. Any suggestions?
class CryptoAIScapping(QCAlgorithm):
def initialize(self):
self.set_warm_up(100, Resolution.DAILY)
self.set_start_date(2024, 10, 28)
self.set_end_date(2024, 10, 30)
self.set_cash(10000)
self.crypto_symbol = self.add_crypto("BTCUSD", Resolution.MINUTE).Symbol
self.quote_bar_window = RollingWindow[QuoteBar](3)
self.rsi = self.rsi(self.crypto_symbol, 14, Resolution.DAILY)
self.rsi_current = RollingWindow[IndicatorDataPoint](2)
self.atr = self.atr(self.crypto_symbol, 20, MovingAverageType.SIMPLE, Resolution.DAILY)
self.atr_current = RollingWindow[IndicatorDataPoint](2)
self.aroon = self.aroon(self.crypto_symbol, 10, Resolution.DAILY)
self.aroon_current = RollingWindow[IndicatorDataPoint](2)
def on_data(self, data):
if self.is_warming_up:
return
if data.quote_bars.contains_key(self.crypto_symbol):
self.quote_bar_window.add(data.quote_bars[self.crypto_symbol])
if self.std.is_ready:
self.std_current.add(self.std.current)
if self.rsi.is_ready:
self.rsi_current.add(self.rsi.current)
if self.atr.is_ready:
self.atr_current.add(self.atr.current)
if self.aroon.is_ready:
self.aroon_current.add(self.aroon.current)
if self.macd.is_ready:
self.macd_current.add(self.macd.current)
if not self.quote_bar_window.is_ready:
return
if not all([self.rsi.IsReady, self.rsiCurrent.IsReady, self.atr.IsReady, self.aroon.IsReady, self.macd.IsReady ]):
return
Bar0 = self.quoteBarWindow[0] # Current bar has index zero.
Bar1 = self.quoteBarWindow[1] # Previous bar has index one.
Bar2 = self.quoteBarWindow[2] # Bar from two periods ago
# Compute the difference between the current close and the previous close
close_diff0 = Bar0.close - Bar1.close
close_diff1 = Bar1.close - Bar2.close
# Compute the difference between the current volume and the previous volume
volume_diff0 = Bar0.volume - Bar1.volume
volume_diff1 = Bar1.volume - Bar2.volume
close_spread_AB0 = Bar0.ask.close - Bar1.bid.close
close_spread_AB1 = Bar1.ask.close - Bar2.bid.close
size_spread_AB0 = Bar0.last_ask_size - Bar1.last_bid_size
size_spread_AB1 = Bar1.last_ask_size - Bar2.last_bid_size
rsi_0 = self.rsiCurrent[0]
rsiAL_0 = self.rsiAverage_loss[0]
rsiAG_0 = self.rsiAverage_gain[0]
rsi_1 = self.rsiCurrent[1].current.value
rsiAL_1 = self.rsiAverage_loss[1]
rsiAG_1 = self.rsiAverage_gain[1]
atr_0 = self.atrCurrent[0]
atrTR_0 = self.atrTrue_range[0]
atr_1 = self.atrCurrent[1]
atrTR_1 = self.atrTrue_range[1]
Mia Alissi
Key Changes:
RSI,ATR,AROON) and corrected the parameters.IsReady,Current) for checking readiness and accessing current values of indicators.RollingWindowis correctly initialized with the desired type and size.Sources: Rolling Window Algorithm, Bybit Crypto Futures Regression Algorithm, Talib Indicators Algorithm, Bybit Custom Data Crypto Regression Algorithm, Momentum Effect In Commodities Futures
The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.
Douglas McWilliams
The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.
To unlock posting to the community forums please complete at least 30% of Boot Camp.
You can continue your Boot Camp training progress from the terminal. We hope to see you in the community soon!