HTM for IT

I see a great document “the Science of anomaly detect”
In this document, the author talk about the HTM for IT as an example with many advantages compare to all other methods/algorithms . does anyone know about this app source code ( HTM for IT) ???

Thank you very much

Maybe you are looking for GROK?
https://grokstream.com/

2 Likes

thank you very much . But now i can not find grok code in the link below https://github.com/numenta/numenta-apps. Do you know where it is now ?

I believe GROK is a partner with Numenta. So it is a closed source application. Maybe @rhyolight knows more.

1 Like

Blockquote
thank you very much @marty1885, i will contact @rhyolight and ask for help.

I was pinging him so he knows we need his support here. He’ll see the ping once he get back to work.

2 Likes

great. thank you @marty1885 very much, thank @rhyolight, @sheiser1 in advance, . First feel, all of you and orther members in this forum are so kind, ready to help and very friendly. I hope i will be able to support you all soon if possible.

2 Likes

You are in the right place at https://github.com/numenta/numenta-apps. Look for the word “taurus”, which is the codeword for the HTM for Analytics demos. In this example, we’re analyzing stock volume instead of server stats.

This code is old and no longer maintained. It is also Python 2.7. We are not planning to continue working with it.

2 Likes

thank you @rhyolight @marty1885 , i found https://github.com/numenta/numenta-apps-archived-htm.it-grokcli-htmitmobile as an archive of HTM IT. Can i use it for study and easily to evaluate HTM with my real time data ( CPU, RAM, HDD servers…)

Pls advice

Thank you very much.

2 Likes

Study and evaluate, kinda. The repo is in Python 2 and it will be EOLed in 3.5 months.
However you should not deploy the repository. You’ll either need to migrate the repo to Python 3 or built your own in Python 3.

2 Likes

thank you @marty1885, so you means that i shouldn’t use that source code to study and evaluate ?

best reagrds

You can use that code for study and evaluation. But be quick, Python 2 is going EOL very soon.

And don’t deploy it.

2 Likes

thank you @marty1885. But so far NUPIC python is still in version 2 right ? and most of example applications is in python 2.7 right ? https://github.com/numenta/nupic

1 Like

So much code to maintain, so little time!

3 Likes

Yes, so please use HTM.core, the community fork of NuPIC.
Or use Etaler, my HTM implementation aimed for HPC applications (It’s C++ only for now, Python wrapper will come later).

2 Likes

For some context, read NuPIC & Python 2 end of life.

1 Like

Thank you very much

1 Like

Thank you so much

1 Like

Dear @rhyolight, @marty1885 @sheiser1 and all

I can understand SP, TM through QuickStart below ( very good quick start)

http://nupic.docs.numenta.org/1.0.3/quick-start/algorithms.html

But after them SP, TM they use the SDR Prediction Classifier like this

Get the bucket info for this input value for classification.

  bucketIdx = scalarEncoder.getBucketIndices(consumption)[0]

  # Run classifier to translate active cells back to scalar value.
  classifierResult = classifier.compute(
    recordNum=count,
    patternNZ=activeCells,
    classification={
      "bucketIdx": bucketIdx,
      "actValue": consumption
    },
    learn=True,
    infer=True
  )

  # Print the best prediction for 1 step out.
  oneStepConfidence, oneStep = sorted(
    zip(classifierResult[1], classifierResult["actualValues"]),
    reverse=True
  )[0]
  print("1-step: {:16} ({:4.4}%)".format(oneStep, oneStepConfidence * 100))
  results.append([oneStep, oneStepConfidence * 100, None, None])

return results

It make me confuse because:

  1. My First Goal is “anomaly detection” .
  2. SDR Classifier is new for me.

In your advice, if my goal is anomaly detection then do i need to do the SDR Predictionn Classifier or not ? Or bypass thisn( SDR Classifier) and go to anomaly detection branch ? Classifier Prediction and Anomaly detection are different branches ?

Thank you very much .

As I understand the Classifier is only needed for forecasting, and can be skipped if your sole purpose is anomaly detection. From the TM you get the raw anomaly scores, which you can then use to get the anomaly likelihoods.

3 Likes