Don't swarm for Anomaly models

[rhyolight]

@Pegasus

what’s difference between ‘tmImplementation = “cpp”’ and ‘tmImplementation = “cpp”’? which is better for anomaly detection? my data is minutely~ thanks.

I think you mean py vs cpp. We have versions of HTM algorithms in both python and C++. This specifies with version you want to use. C++ is faster. They both will return exactly the same results.

@Pegasus

the function you mentioned: ‘getScalarMetricWithTimeOfDayAnomalyParams’, if this function could be used for minutely data?

Yes.

@Pegasus

just a moment ago, I ran example codes in the project nupic.workshop . However ,there are some errors, such as ModelFactory received unsupported Model type: CLA, No module named modelfactory. from the type of errors, I wonder if there codes in wokshop are out of date?

I noticed, the date updated is a year ago, comparing with other resources or projects of htm, it could be seen as a more recent version. So… why?

We recently introduced breaking changes to NuPIC. Those are the errors you’re seeing. Thanks for pointing this out, we’ll be fixing this example codebase soon.

@Pegasus

I saw the details in model params, I found no matter how fine the granularity of time ( daily, hourly or minutely) the ‘timestamp_timeOfDay’ dict are the same… is it means the encoding for time have no or little influence on AD or prediction?

If you have daily data points, there should be no time-of-day encoding included. The params returned by getScalarMetricWithTimeOfDayAnomalyParams won’t handle daily inputs well. Hourly or minutely, sure. Best would be every 10-15 minutes.

@Pegasus

what if i want to turn off ‘learning’ when i think the model are trained well enough to meet I need?

That is a good idea if you want the model to lock into recently seen patterns and not learn anything new.

@Pegasus

What if I want to continue train the model from where i stop ‘learning’?

You just re-enable learning again.

@Pegasus

what if i want manually to label a anomaly which is not seen as anomaly points by htm?

You’ll have to do this outside of NuPIC.

@Pegasus

In the docs for AD, there provides a url: https://github.com/subutai/nupic.subutai/tree/master/swarm_examples

with the sentence: ‘swarming with anomaly detection models’. So I don’t know… I… I am confused…

You’ll have to explain what you are confused about. Swarming returns model params that could be used for prediction or anomaly detection. So the statement makes sense to me.

@Pegasus

and change the data head to (‘c0’,‘c1’)

but there stil has the error:

You will either need to change these labels to match the names of of your input file field names, or change the input file field names to match the model params.