# I'd like to detect anomalies using the algorithm API listed in the algorithm API of the Nupic 1.0.1 documentation

**URL:** <https://discourse.numenta.org/t/id-like-to-detect-anomalies-using-the-algorithm-api-listed-in-the-algorithm-api-of-the-nupic-1-0-1-documentation/3008>\
**Category:** Numenta Theory\
**Created:** [November 1, 2017, 8:43am UTC](https://discourse.numenta.org/t/id-like-to-detect-anomalies-using-the-algorithm-api-listed-in-the-algorithm-api-of-the-nupic-1-0-1-documentation/3008 "2017-11-01T08:43:28Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![tokizaki](https://avatars.discourse-cdn.com/v4/letter/t/7bcc69/32.png) [@tokizaki](https://discourse.numenta.org/u/tokizaki)\
**Post date:** [November 1, 2017, 8:43am UTC](https://discourse.numenta.org/t/id-like-to-detect-anomalies-using-the-algorithm-api-listed-in-the-algorithm-api-of-the-nupic-1-0-1-documentation/3008/1 "2017-11-01T08:43:28Z")

</div>

Although I succeeded in detecting anomalies at [run.py](http://run.py) in the tutorial, I do not know how to detect anomalies in programs listed in the 1.0.1 Quick Start algorithm API.  
The imported nupic module is completely different from [run.py](http://run.py) and algorithm API program, so it can not be copied and pasted, and it seems that algorithm API does not refer to inferenceType of model\_params.  
The program of the algorithm API is modified not to read from the yaml file but to read the parameters from model\_params, so the prediction works.  
How do I become able to detect anomalies with 1.0.1 Quick Start program?

---

<div class="post-metadata">

**Author:** ![rhyolight](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/rhyolight/32/3922_2.png) [@rhyolight](https://discourse.numenta.org/u/rhyolight)\
**Post date:** [November 1, 2017, 1:15pm UTC](https://discourse.numenta.org/t/id-like-to-detect-anomalies-using-the-algorithm-api-listed-in-the-algorithm-api-of-the-nupic-1-0-1-documentation/3008/2 "2017-11-01T13:15:14Z")

</div>

Here is the complete running script from the docs you can start with:

> <https://github.com/numenta/nupic/blob/master/docs/examples/algo/complete-algo-example.py>

---

<div class="post-metadata">

**Author:** ![tokizaki](https://avatars.discourse-cdn.com/v4/letter/t/7bcc69/32.png) [@tokizaki](https://discourse.numenta.org/u/tokizaki)\
**Post date:** [November 1, 2017, 5:45pm UTC](https://discourse.numenta.org/t/id-like-to-detect-anomalies-using-the-algorithm-api-listed-in-the-algorithm-api-of-the-nupic-1-0-1-documentation/3008/3 "2017-11-01T17:45:24Z")

</div>

Yes. I have not seen inferenceType though I tried it.  
How can we detect anomalies with this program?

---

<div class="post-metadata">

**Author:** ![whereandtear](https://avatars.discourse-cdn.com/v4/letter/w/8edcca/32.png) [@whereandtear](https://discourse.numenta.org/u/whereandtear)\
**Post date:** [April 10, 2019, 3:29pm UTC](https://discourse.numenta.org/t/id-like-to-detect-anomalies-using-the-algorithm-api-listed-in-the-algorithm-api-of-the-nupic-1-0-1-documentation/3008/4 "2019-04-10T15:29:29Z")

</div>

Crossposting to my reply in [this relevant thread](https://discourse.numenta.org/t/anomaly-detection/2587/3).