Check for OHLC and indicator values everyday. Values dont seem accurate

Sure, I can help you with that. The RollingWindow in QuantConnect is a fixed-size array that holds trailing data. It's more efficient to use RollingWindow objects to hold periods of data than to make multiple historical data requests. With a RollingWindow, you just update the latest data point while a History call fetches all of the data over the period you request.

Here is an example of how to create a RollingWindow and add data to it:

self.close_window = RollingWindow[float](4)
self.trade_bar_window = RollingWindow[TradeBar](2)
self.quote_bar_window = RollingWindow[QuoteBar](2)

self.close_window.Add(data["SPY"].Close)
self.trade_bar_window.Add(data["SPY"])
self.quote_bar_window.Add(data["EURUSD"])

You can also track historical indicator values using a RollingWindow. Indicators emit an Updated event when they update. To create a RollingWindow of indicator points, attach an event handler function to the Updated member that adds the last value of the indicator to the RollingWindow. The value is an IndicatorDataPoint object that represents a piece of data at a specific time.

Here is an example of how to do this:

self.sma_window = RollingWindow[IndicatorDataPoint](5)
self.SMA("SPY", 5).Updated += (lambda sender, updated: self.sma_window.Add(updated))

If you're seeing discrepancies in the data, it might be due to how you're accessing the data in the RollingWindow. The most recent data is at index 0, the previous data is at index 1, and so on. Here is how you can access the data:

current_sma = self.sma_window[0]
previous_sma = self.sma_window[1]
oldest_sma = self.sma_window[sma_window.Count - 1]

If you're still having issues, it would be helpful to see the specific code you're using to access the data in the RollingWindow.

here's the code

from AlgorithmImports import *
# endregion

from datetime import timedelta
from QuantConnect import *


class MyAlgorithm(QCAlgorithm):
    
    def Initialize(self):


        self.SetStartDate(2020, 1, 1)  # Set the start date for the backtest
        self.SetEndDate(2020, 3, 1)  # Set the end date for the backtest
        self.SetCash(100000)  # Set an initial cash balance
        # self.mult = 0.04

        self.AddEquity("SPY")  # Add the SPY equity
        # self.option = self.AddOption("SPY", Resolution.Minute)

        # self.option.SetFilter(timedelta(1), timedelta(15))

        self.ohlc_window = RollingWindow[TradeBar](3)

        self.sto14_window = RollingWindow[IndicatorDataPoint](3)
        self.STO("SPY", 14, 3, 3).Updated += (lambda sender, updated: self.sto14_window.Add(updated))
        
        self.sto70_window = RollingWindow[IndicatorDataPoint](3)
        self.STO("SPY", 70, 15, 7).Updated += (lambda sender, updated: self.sto70_window.Add(updated))

        self.adx_window = RollingWindow[IndicatorDataPoint](3)
        self.ADX("SPY", 14, Resolution.Daily).Updated += (lambda sender, updated: self.adx_window.Add(updated))

        self.plusdi_window = RollingWindow[IndicatorDataPoint](3)
        self.ADX("SPY", 14).PositiveDirectionalIndex.Updated += (lambda sender, updated: self.plusdi_window.Add(updated))

        self.minusdi_window = RollingWindow[IndicatorDataPoint](3)
        self.ADX("SPY", 14).NegativeDirectionalIndex.Updated += (lambda sender, updated: self.minusdi_window.Add(updated))

        self.bb_u = RollingWindow[IndicatorDataPoint](3)
        self.BB("SPY", 20, 2.1).UpperBand.Updated += (lambda sender, updated: self.bb_u.Add(updated))

        self.bb_l = RollingWindow[IndicatorDataPoint](3)
        self.BB("SPY", 20, 2.1).LowerBand.Updated += (lambda sender, updated: self.bb_l.Add(updated))


        self.Schedule.On(self.DateRules.EveryDay("SPY"), self.TimeRules.BeforeMarketClose("SPY", 1), self.atm)
        # self.SetWarmUp(30, Resolution.Daily)

        self.SetWarmUp(3, Resolution.Daily)

    def OnData(self, data):
        if data.ContainsKey("SPY"):
            self.ohlc_window.Add(data["SPY"])

    def atm(self):

        if self.ohlc_window.Size < 3:
            return
        if(self.plusdi_window[0]):
            self.Debug(f"low {self.ohlc_window[0].Low}")
            self.Debug(f"close {self.ohlc_window[0].Close}")
            self.Debug(f"sto14 {self.sto14_window[0].Value}")
            self.Debug(f"DI+ {self.plusdi_window[0].Value}")
            self.Debug(f"DI- {self.minusdi_window[0].Value}")
            self.Debug(f"ADX {self.adx_window[0].Value}")

    

Based on the code you've shared, it seems like you're using the RollingWindow correctly. You're initializing the RollingWindow objects for different indicators and OHLC values, and you're adding data to them in the correct manner.

However, the issue you're facing might be related to how you're accessing the data in the RollingWindow. Remember that RollingWindow objects operate on a first-in, first-out process to allow for reverse list access semantics. This means that index 0 refers to the most recent item in the window and the largest index refers to the last item in the window.

Here is how you can access the data:

current_sma = self.sma_window[0]
previous_sma = self.sma_window[1]
oldest_sma = self.sma_window[self.sma_window.Count - 1]

In your code, you're accessing the data correctly. For example, self.ohlc_window[0].Low correctly refers to the most recent low price.

If the Low and Close values are always very close, it might be due to the nature of the data itself. You might want to check the raw data to see if this is the case.

If you're still facing issues, please share more details or the specific part of the code that's causing the problem.