# Swarming Nupic Data

**URL:** <https://discourse.numenta.org/t/swarming-nupic-data/5125>\
**Category:** NuPIC\
**Tags:** question\
**Created:** [December 31, 2018, 6:07am UTC](https://discourse.numenta.org/t/swarming-nupic-data/5125 "2018-12-31T06:07:19Z")\
**Posts on this page:** 8\
**Page:** 1

<div class="post-metadata">

**Author:** ![Prabal\_Kumar](https://avatars.discourse-cdn.com/v4/letter/p/e5b9ba/32.png) [@Prabal\_Kumar](https://discourse.numenta.org/u/Prabal_Kumar)\
**Post date:** [December 31, 2018, 6:07am UTC](https://discourse.numenta.org/t/swarming-nupic-data/5125/1 "2018-12-31T06:07:19Z")

</div>

After swarming the hot gym why do we get u’timestamp\_dayOfWeek’: None even when i swarm my data some feature are depicted as none can anyone please tell what could be the issue.

---

<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:** [December 31, 2018, 3:44pm UTC](https://discourse.numenta.org/t/swarming-nupic-data/5125/2 "2018-12-31T15:44:40Z")

</div>

Swarming finds that there is a weekly pattern, so it is using a date encoder that differentiates the days of the week differently. Does that make sense? Can you ask your question another way?

---

<div class="post-metadata">

**Author:** ![Prabal\_Kumar](https://avatars.discourse-cdn.com/v4/letter/p/e5b9ba/32.png) [@Prabal\_Kumar](https://discourse.numenta.org/u/Prabal_Kumar)\
**Post date:** [January 1, 2019, 5:46am UTC](https://discourse.numenta.org/t/swarming-nupic-data/5125/3 "2019-01-01T05:46:20Z")

</div>

Hi Rhyolight,

Actually I swarm the input hot gym data the model params file contains

u’kw\_energy\_consumption’: { ‘clipInput’: True,  
‘fieldname’: ‘kw\_energy\_consumption’,  
‘maxval’: 53.0,  
‘minval’: 0.0,  
‘n’: 29,  
‘name’: ‘kw\_energy\_consumption’,  
‘type’: ‘ScalarEncoder’,  
‘w’: 21},  
u’timestamp\_dayOfWeek’: None,  
u’timestamp\_timeOfDay’: { ‘fieldname’: ‘timestamp’,  
‘name’: ‘timestamp’,  
‘timeOfDay’: ( 21,  
6.090344152692538),  
‘type’: ‘DateEncoder’},  
u’timestamp\_weekend’: { ‘fieldname’: ‘timestamp’,  
‘name’: ‘timestamp’,  
‘type’: ‘DateEncoder’,  
‘weekend’: ( 21,  
1)}

As u can see that timestamp\_dayOfWeek has None so i just wanted to confirm what could be the problem due to which the feature timestamp\_dayOfWeek is having None as encoding

---

<div class="post-metadata">

**Author:** ![Prabal\_Kumar](https://avatars.discourse-cdn.com/v4/letter/p/e5b9ba/32.png) [@Prabal\_Kumar](https://discourse.numenta.org/u/Prabal_Kumar)\
**Post date:** [January 1, 2019, 5:48am UTC](https://discourse.numenta.org/t/swarming-nupic-data/5125/4 "2019-01-01T05:48:55Z")

</div>

Hi Rhyo,

In the similar fashion when i swarm my server data.I get

u’cpu\_user\_pct’: None,  
u’load\_1min’: { ‘clipInput’: True,  
‘fieldname’: ‘load\_1min’,  
‘maxval’: 0.0525,  
‘minval’: 0.0025,  
‘n’: 380,  
‘name’: ‘load\_1min’,  
‘type’: ‘ScalarEncoder’,  
‘w’: 21},  
u’memory\_actual\_used\_pct’: { ‘clipInput’: True,  
‘fieldname’: ‘memory\_actual\_used\_pct’,  
‘maxval’: 0.649,  
‘minval’: 0.0847,  
‘n’: 22,  
‘name’: ‘memory\_actual\_used\_pct’,  
‘type’: ‘ScalarEncoder’,  
‘w’: 21},  
u’process\_summary\_total’: None  
As you can see process\_summary\_total feature and cpu\_user\_pct have None as their encoding value so just wanted to confirm what could be problem because of which None is coming

---

<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:** [January 1, 2019, 4:13pm UTC](https://discourse.numenta.org/t/swarming-nupic-data/5125/5 "2019-01-01T16:13:49Z")

</div>

Sorry I think I misunderstood your question. When one of these encoder fields is `None` that means the swarm found that encoding that input did not help improve prediction accuracy, so the field is simply not encoded.

Swarming is a brute-force solution to generate model Paramus. Look at your data, and if you see it has weekly patterns, add in the proper encoder.

If you are doing anomaly detection, we suggest you use the [`getScalarMetricWithTimeOfDayAnomalyParams()`](http://nupic.docs.numenta.org/1.0.3/api/opf/utils.html#nupic.frameworks.opf.common_models.cluster_params.getScalarMetricWithTimeOfDayAnomalyParams) function to generate model parameters. I think this includes day of week encoding.

---

<div class="post-metadata">

**Author:** ![way-sal](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/way-sal/32/3028_2.png) [@way-sal](https://discourse.numenta.org/u/way-sal)\
**Post date:** [January 1, 2019, 5:29pm UTC](https://discourse.numenta.org/t/swarming-nupic-data/5125/6 "2019-01-01T17:29:01Z")

</div>

@rhyolight , mee too I used [getScalarMetricWithTimeOfDayAnomalyParams()](http://nupic.docs.numenta.org/1.0.3/api/opf/utils.html#nupic.frameworks.opf.common_models.cluster_params.getScalarMetricWithTimeOfDayAnomalyParams) but this function work only on numeric data isn’t ?  
It’s ture this function generate a model param but not the perfect model, I mean after you get your model you must make some updates ( spParams and tmParams ) and seen the best result isn’t.

---

<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:** [January 1, 2019, 11:33pm UTC](https://discourse.numenta.org/t/swarming-nupic-data/5125/7 "2019-01-01T23:33:58Z")

</div>

Yes, it only works on a single numeric field. But you can modify the model parameters it creates to your liking.

---

<div class="post-metadata">

**Author:** ![Prabal\_Kumar](https://avatars.discourse-cdn.com/v4/letter/p/e5b9ba/32.png) [@Prabal\_Kumar](https://discourse.numenta.org/u/Prabal_Kumar)\
**Post date:** [January 2, 2019, 7:37am UTC](https://discourse.numenta.org/t/swarming-nupic-data/5125/8 "2019-01-02T07:37:54Z")

</div>

Thank You for the help