search

yahoo / egads

A Java package to automatically detect anomalies in large scale time-series data
Other
1.17k stars 331 forks source link

StackOverflowError on AutoForecastModel #31

Open funtion opened 8 years ago

funtion commented 8 years ago

When I change the TS_MODEL to AutoForecastModel in config and run it on my data, it got stack overflow like this:

Exception in thread "main" java.lang.StackOverflowError
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.forecast(TripleExponentialSmoothingModel.java:673)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.initForecastValue(AbstractTimeBasedModel.java:261)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.getForecastValue(AbstractTimeBasedModel.java:361)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.getSeasonalIndex(TripleExponentialSmoothingModel.java:817)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.getBase(TripleExponentialSmoothingModel.java:734)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.forecast(TripleExponentialSmoothingModel.java:673)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.initForecastValue(AbstractTimeBasedModel.java:261)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.getForecastValue(AbstractTimeBasedModel.java:361)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.getSeasonalIndex(TripleExponentialSmoothingModel.java:817)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.getBase(TripleExponentialSmoothingModel.java:734)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.forecast(TripleExponentialSmoothingModel.java:673)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.initForecastValue(AbstractTimeBasedModel.java:261)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.getForecastValue(AbstractTimeBasedModel.java:361)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.getSeasonalIndex(TripleExponentialSmoothingModel.java:817)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.getBase(TripleExponentialSmoothingModel.java:734)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.forecast(TripleExponentialSmoothingModel.java:673)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.initForecastValue(AbstractTimeBasedModel.java:261)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.getForecastValue(AbstractTimeBasedModel.java:361)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.getSeasonalIndex(TripleExponentialSmoothingModel.java:817)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.getBase(TripleExponentialSmoothingModel.java:734)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.forecast(TripleExponentialSmoothingModel.java:673)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.initForecastValue(AbstractTimeBasedModel.java:261)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.getForecastValue(AbstractTimeBasedModel.java:361)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.getSeasonalIndex(TripleExponentialSmoothingModel.java:817)

.... 

at net.sourceforge.openforecast.models.AbstractTimeBasedModel.initForecastValue(AbstractTimeBasedModel.java:261)
    at net.sourceforge.openforecast.models.AbstractTimeBasedModel.getForecastValue(AbstractTimeBasedModel.java:361)
    at net.sourceforge.openforecast.models.TripleExponentialSmoothingModel.getSeasonalIndex(TripleExponentialSmoothingModel.java:817)

And it works correctly on other models.

naayaaa commented 7 years ago

i have the same error... looks like a bug on openforecast

fudazhumeng commented 5 years ago

hello, I also encountered this problem. Is there any solution?

igaoliang commented 4 years ago

in my test data , the TripleExponentialSmoothingModel cause this error. but the sample_input.csv do not cause the error.