Supported Indicators

Time Series Forecast

Introduction

This indicator represents an indicator capable of predicting new values given previous data from a window. source

To view the implementation of this indicator, see the LEAN GitHub repository.

Using TSF Indicator

To create an automatic indicator for TimeSeriesForecast, call the TSFtsf helper method from the QCAlgorithm class. The TSFtsf method creates a TimeSeriesForecast object, hooks it up for automatic updates, and returns it so you can used it in your algorithm. In most cases, you should call the helper method in the Initializeinitialize method.

public class TimeSeriesForecastAlgorithm : QCAlgorithm
{
    private Symbol _symbol;
    private TimeSeriesForecast _tsf;

    public override void Initialize()
    {
        _symbol = AddEquity("SPY", Resolution.Daily).Symbol;
        _tsf = TSF(_symbol, 3);
    }

    public override void OnData(Slice data)
    {

        if (_tsf.IsReady)
        {
            // The current value of _tsf is represented by itself (_tsf)
            // or _tsf.Current.Value
            Plot("TimeSeriesForecast", "tsf", _tsf);
        }
    }
}
class TimeSeriesForecastAlgorithm(QCAlgorithm):
    def initialize(self) -> None:
        self._symbol = self.add_equity("SPY", Resolution.DAILY).symbol
        self._tsf = self.tsf(self._symbol, 3)

    def on_data(self, slice: Slice) -> None:

        if self._tsf.is_ready:
            # The current value of self._tsf is represented by self._tsf.current.value
            self.plot("TimeSeriesForecast", "tsf", self._tsf.current.value)

For more information about this method, see the QCAlgorithm classQCAlgorithm class.

You can manually create a TimeSeriesForecast indicator, so it doesn't automatically update. Manual indicators let you update their values with any data you choose.

Updating your indicator manually enables you to control when the indicator is updated and what data you use to update it. To manually update the indicator, call the Updateupdate method. The indicator will only be ready after you prime it with enough data.

public class TimeSeriesForecastAlgorithm : QCAlgorithm
{
    private Symbol _symbol;
    private TimeSeriesForecast _timeseriesforecast;

    public override void Initialize()
    {
        _symbol = AddEquity("SPY", Resolution.Daily).Symbol;
        _timeseriesforecast = new TimeSeriesForecast(3);
    }

    public override void OnData(Slice data)
    {
        if (data.Bars.TryGetValue(_symbol, out var bar))
            _timeseriesforecast.Update(bar.EndTime, bar.Close);

        if (_timeseriesforecast.IsReady)
        {
            // The current value of _timeseriesforecast is represented by itself (_timeseriesforecast)
            // or _timeseriesforecast.Current.Value
            Plot("TimeSeriesForecast", "timeseriesforecast", _timeseriesforecast);
        }
    }
}
class TimeSeriesForecastAlgorithm(QCAlgorithm):
    def initialize(self) -> None:
        self._symbol = self.add_equity("SPY", Resolution.DAILY).symbol
        self._timeseriesforecast = TimeSeriesForecast(3)

    def on_data(self, slice: Slice) -> None:
        bar = slice.bars.get(self._symbol)
        if bar:
            self._timeseriesforecast.update(bar.end_time, bar.close)

        if self._timeseriesforecast.is_ready:
            # The current value of self._timeseriesforecast is represented by self._timeseriesforecast.current.value
            self.plot("TimeSeriesForecast", "timeseriesforecast", self._timeseriesforecast.current.value)

For more information about this indicator, see its referencereference.

Visualization

The following plot shows values for some of the TimeSeriesForecast indicator properties:

TimeSeriesForecast line plot.

Indicator History

To get the historical data of the TimeSeriesForecast indicator, call the IndicatorHistoryself.indicator_history method. This method resets your indicator, makes a history request, and updates the indicator with the historical data. Just like with regular history requests, the IndicatorHistoryindicator_history method supports time periods based on a trailing number of bars, a trailing period of time, or a defined period of time. If you don't provide a resolution argument, it defaults to match the resolution of the security subscription. 

public class TimeSeriesForecastAlgorithm : QCAlgorithm
{
    private Symbol _symbol;
    private TimeSeriesForecast _tsf;

    public override void Initialize()
    {
        _symbol = AddEquity("SPY", Resolution.Daily).Symbol;
        _tsf = TSF(_symbol, 3);

        var indicatorHistory = IndicatorHistory(_tsf, _symbol, 100, Resolution.Minute);
        var timeSpanIndicatorHistory = IndicatorHistory(_tsf, _symbol, TimeSpan.FromDays(10), Resolution.Minute);
        var timePeriodIndicatorHistory = IndicatorHistory(_tsf, _symbol, new DateTime(2024, 7, 1), new DateTime(2024, 7, 5), Resolution.Minute);
    }
}
class TimeSeriesForecastAlgorithm(QCAlgorithm):
    def initialize(self) -> None:
        self._symbol = self.add_equity("SPY", Resolution.DAILY).symbol
        self._tsf = self.tsf(self._symbol, 3)

        indicator_history = self.indicator_history(self._tsf, self._symbol, 100, Resolution.MINUTE)
        timedelta_indicator_history = self.indicator_history(self._tsf, self._symbol, timedelta(days=10), Resolution.MINUTE)
        time_period_indicator_history = self.indicator_history(self._tsf, self._symbol, datetime(2024, 7, 1), datetime(2024, 7, 5), Resolution.MINUTE)

You can also see our Videos. You can also get in touch with us via Discord.

Did you find this page helpful?

Contribute to the documentation: