PredictionServer Timeouts

I have a PredictionServer timeout when issuing a query for a non-existent user. We can only use a weeks worth of data so doing the db clean every day to drop events that are too old, without messing with $whatever events. Users are never created with $set. So we are asking for a list of event ty

Re: [VOTE] Release Apache PredictionIO 0.11.0 (incubating) RC2

+1 non-binding Next release we could exclude the doc site. Do build files like .sbt require licenses? I suppose it can be done in comments. But again can we push to next release? Can other binding voters have a look? I know everyone is busy but hey, tax day is past ;-) On Apr 18, 2017, at 1

Re: Cart/Complementary purchase recommendation with UR

gt; { > "name": "store_id", > "values": ["2"] > } > ] > }' http://10.10.10.2:8123/queries.json <http://10.10.10.2:8123/queries.json> It works without bias. But I don't think it's a valid way. I mea

Re: Dose v.011 support Spark ML, DataFrame and Pipeline

There is no restriction in templates for what they use of Spark. The ones you are looking at simply don’t need those interfaces. If you need them and are writing templates you can use them. In fact I maintain a template that does not use Spark for the Algorithm, only for IO. If you think some n

Re: Invalid app name INVALID_APP_NAME

Templates are not part of the PredictionIO, they are often supported by their authors. Check the Template gallery, there should be a support link for each Template, some are Apache, some are supported by their authors. Their may be a github issues link there for author support. Not all Template

Re: Similar product template

's say I trained the model and queried with the preference parameter, in that case is it using multi model for each preference? If you could describe a bit about this, it would be reall On Thu, Apr 13, 2017 at 9:15 PM, Pat Ferrel mailto:p...@occamsmachete.com>> wrote: I’m surpri

Re: Lambda and Kappa CCO

Would we need any new data > structures? Trevor and I were just discussing some of the troubles of > near real time matrix streaming. > ---------- > *From:* Pat Ferrel > *Sent:* Monday, March 27, 2017 2:42:55 PM > *To:* Ted Dunning; user@mahout.apache.org

Re: Use whitelist or blacklist in query

Using properties of items there are new exclusion rules is in the next release of v0.6.0, which will be released shortly after PIO v0.11.0 and Mahout v0.13.0, both are going release now. “Bias" in The Universal Recommender v0.6.0: 0: exclude items with properties specified (must_not in ES parla

Re: [VOTE] Apache PredictionIO (incubating) 0.11.0 Release (RC2)

+1 binding was able to build and run integration tests on the UR, which has special needs for ES1 On Apr 11, 2017, at 2:41 PM, Chan Lee wrote: [+1] binding accept On Mon, Apr 10, 2017 at 1:22 PM, Donald Szeto wrote: > Thanks! Just a reminder that PMC members should indicate whether the vote

Re: Similar product template

I’m surprised that ALS seemed clear because is is based on a complicated matrix factorization algorithm that transforms the user vectors into a smaller dimensional space that is composed of “important” features. These are not interactions with items like “buys”, they can only be described as def

Re: Terminology in event creation API

/detrevid/predictionio-template-classification-dl4j <https://github.com/detrevid/predictionio-template-classification-dl4j> it's on your templates but it not working anymore so ? ᐧ 2017-04-12 17:01 GMT+01:00 Pat Ferrel mailto:p...@occamsmachete.com>>: Which classification template? The

Re: Terminology in event creation API

: @Pat, I am using classification template. In this context, what is meaning of above terminology. On 12-Apr-2017 9:17 PM, "Pat Ferrel" mailto:p...@occamsmachete.com>> wrote: Actually each Template has different “event” interpretation. @Vaghawan is giving the interpretation of a re

Re: Terminology in event creation API

Actually each Template has different “event” interpretation. @Vaghawan is giving the interpretation of a recommender. Other Templates will use the event fields in different ways so we should backup to that a Template is and does and what the rest of PIO does. - Template: code that implements s

Re: classification template

We support the Universal Recommender here. See the PredictionIO mailing list for further support (CCed) On Apr 12, 2017, at 7:16 AM, YOUSSEF ASSATA wrote: hello everyone please can you suggest me a classification template or a tuto based on items and their probabilities thanks cordially --

Re: Errors please help

For PredicitonIO related questions ask the PredictionIO user group(CCed). This group is for the Universal Recommender and accompanying startup instructions. We do not support Postgres for the UR. On Apr 12, 2017, at 4:06 AM, gautamrbharad...@gmail.com wrote: Hi, I am trying to install pr

Re: How Can I count events In The Event Server?

As you may know from setting up other databases the storage in indexes for a DB define it’s performance so the EventServer is tuned for use with Templates. There are a few queries (thanks Marius) but they are not extensive. I suggest you keep them in your own DB along side the EventServer if you

Re: microsoft azure

ing/details/virtual-machines/linux/> On Apr 10, 2017, at 11:47 AM, YOUSSEF ASSATA wrote: well i did but where is azure here ?! ᐧ 2017-04-10 16:27 GMT+01:00 Pat Ferrel mailto:p...@occamsmachete.com>>: Get an Ubuntu instance and install PredictionIO On Apr 10, 2017, at 8:18 AM, YO

Re: Existing javascript SDK for predicitonIO (0.10) ?

:13 AM Pat Ferrel mailto:p...@occamsmachete.com>> wrote: using Javascript from the client is a problem because you will make it possible for some malicious agent to see your access key by examining your client code. Although PIO support SSL it does not have an authentication mechanis

Re: [PIO 0.10.0][Universtal Recommender 0.5] Exception when using remote Elasticsearch while training

immediate issue but just wanted to make that clear. On Apr 10, 2017, at 8:27 AM, Marius Rabenarivo wrote: Yes, I set the clustername in Elasticsearch config too. Thank you for your advices about fields. 2017-04-10 19:07 GMT+04:00 Pat Ferrel mailto:p...@occamsmachete.com>>: Do you ha

Re: microsoft azure

Get an Ubuntu instance and install PredictionIO On Apr 10, 2017, at 8:18 AM, YOUSSEF ASSATA wrote: ah :/ and so how ? please ? ᐧ 2017-04-10 16:17 GMT+01:00 Pat Ferrel mailto:p...@occamsmachete.com>>: I believe I said “and Azure supports this” On Apr 10, 2017, at 8:08 AM, YOUSSEF

Re: Existing javascript SDK for predicitonIO (0.10) ?

using Javascript from the client is a problem because you will make it possible for some malicious agent to see your access key by examining your client code. Although PIO support SSL it does not have an authentication mechanism so a malicious agent could use this access key to screw up your dat

Re: [PIO 0.10.0][Universtal Recommender 0.5] Exception when using remote Elasticsearch while training

Apr 9, 2017, at 10:43 PM, Marius Rabenarivo wrote: Hello, Find attached the pio-env.sh and engine.json that we are using. 2017-04-08 18:46 GMT+04:00 Marius Rabenarivo mailto:mariusrabenar...@gmail.com>>: I'll share them monday. 2017-04-07 22:23 GMT+04:00 Pat Ferr

Re: How Does The Score Works In UR

The limit depends on your data. I tell people to ignore the value as you do when searching (no one uses the score when doing searches do they?) Only the ranking/ordering makes any real difference. The score is the sum of dot products of all user history vector segments against the correlator fi

Re: [PIO 0.10.0][Universtal Recommender 0.5] Exception when using remote Elasticsearch while training

nreachable) exception 2017-04-07 9:18 GMT+04:00 Marius Rabenarivo mailto:mariusrabenar...@gmail.com>>: I tried using these configurations in the sparkConf section of engine.json It has the same effect as the code I mentioned below but I still getting the same exception. 2017-

Re: [PIO 0.10.0][Universtal Recommender 0.5] Exception when using remote Elasticsearch while training

BTW the docs for sparkConf are here: http://actionml.com/docs/ur_config#ur-spark-conf <http://actionml.com/docs/ur_config#ur-spark-conf> On Apr 6, 2017, at 4:52 PM, Pat Ferrel wrote: PIO in the past used the “transport client” of Elasticsearch, which is on port 9300 by default, The U

Re: [PIO 0.10.0][Universtal Recommender 0.5] Exception when using remote Elasticsearch while training

PIO in the past used the “transport client” of Elasticsearch, which is on port 9300 by default, The UR uses the REST client for some things like rapid writes to ES using Spark using a lib supplied by Elasticsearch. So, Spark needs to have config that the Elasticsearch library can read. This can

Re: Reg:-Integrating Mahout with Solr

also on the implementation part. Kindly guide me on the same. Thanks and Regards, Arun On Apr 3, 2017 12:40 AM, "Pat Ferrel" wrote: > Ted’s cautions still apply regarding interactions per item and per user. > Do not ignore this advice. > > Also doing behavioral boos

Re: Adding a new application is slow

Hmm, interesting. I have heard of this being a problem in PredictionIO but haven’t heard this explanation before IIRC. On Apr 6, 2017, at 9:47 AM, juha.syrj...@gmail.com wrote: Ah, I just found the problem: a fresh AWS instance takes a long time to generate enough entropy so that a random acce

Re: Cart/Complementary purchase recommendation with UR

Yes it can be done but support is not ideal so UR v0.6.0 coming just after the release of PIO-0.11.0 (in RC now) has some enhancements that give you better options and easier queries. To get truly complimentary purchases you need to train on shopping carts, not users purchases. So the primary i

Re: Empty result even though there are events

; wrote: Hi, Yes, I couldn't use different appName. Even when I changed the appName in engine.json and did pio build, the app name in pio app list still reamins the same. Something to do with the pio itself, I guess. Thank you very much for your support. On Mon, Apr 3, 2017 at 6:58 P

Re: Items blacklisted in the query made to Elasticsearch by UR

uot;body","blouse","estag_begin-moins-50-pour-cent-estag_end","estag_begin-primadonna-estag_end","estag_begin-taille-taille-unique-estag_end","moins-de-20-euros-intervalle-de-prix","maintien","estag_begin-simone-perele-

Re: Loading data from files - Samsara

Mahout-Samsara has a couple CLI drivers but these are mostly for examples. They read from csv files but may not do what you want. Mahout can also run in a Spark Shell or as a library to your app, which gives you all the data loading functions of Spark or Scala. For instance I use SimilarityAnal

Re: Items blacklisted in the query made to Elasticsearch by UR

uot;appName": "piourcluster", "indexName": "urindex", "typeName": "items", "eventNames": ["facet", "view"], "blacklistEvents": [], "maxEventsPerEventType": 5

Re: Error while pio status

0.4" }, "tagline" : "You Know, for Search" } Thanks Gaurav http://www.infoquestsolutions.com <http://www.infoquestsolutions.com/> Turning Imagination To Reality Skype:- infoquestsolutions Gtalk:- infoquestindia On Mon, Apr 3, 2017 at 10:34 PM, Pat Ferrel mailto:

Re: Error while pio status

http://actionml.com/docs/single_machine <http://actionml.com/docs/single_machine> Its all i have copied from. And it also suggest aml version of prediction which is also incorrect. On Mon, 3 Apr 2017 at 8:41 PM, Pat Ferrel mailto:p...@occamsmachete.com>> wrote: The data will come from

Re: Error while pio status

- infoquestsolutions Gtalk:- infoquestindia On Mon, Apr 3, 2017 at 6:52 PM, Pat Ferrel mailto:p...@occamsmachete.com>> wrote: If you are still using the UR you don’t need HDFS as a storage backend. In setup instructions, “some-master” is a placeholder where you actually enter the DNS name or

Re: Error while pio status

If you are still using the UR you don’t need HDFS as a storage backend. In setup instructions, “some-master” is a placeholder where you actually enter the DNS name or IP address of your actual master machine running Elasticsearch. This can be a list comma separated, no spaces. Can you share you

Re: Empty result even though there are events

must add eventsNames", "name": "ur", "params": { "appName": "handmade", "indexName": "urindex", "typeName": "items", "comment": "must have data

Re: Reg:-Integrating Mahout with Solr

s). I understood that in the above scenario,first step is to provide the Solr index to mahout to read and will generate a vector file from it. It will be helpful if I get guidance on the integration steps to follow for the same. Thanks and Regards, Arun On 1 April 2017 at 23:46, Pat Ferrel wrote:

Re: I m getting error in stage 33 while using pio train.

I was not able to find much on this error. Sir i wanted to ask one more question how to run pio build behind a proxy server with authentication On Sun, Apr 2, 2017 at 2:59 AM, Pat Ferrel mailto:p...@actionml.com>> wrote: That is an old template that does not work with Apache PIO Look o

Re: I m getting error in stage 33 while using pio train.

o-elasticsearch-can-t-handle-type-exception>. I am unable to understand where(i mean which files) i have to add the said classes in the link. Sir i am also unable to understand how to upgrade spark in the docker image. On Sat, Apr 1, 2017 at 11:30 PM, Pat Ferrel mailto:p...@actionml.com>

Re: Reg:-Integrating Mahout with Solr

You want to create “Behavioral Search”? This is where you boost items that have the search terms in them more likely to be favored by the individual user? You want to use the CCO algorithm in Mahout. You need to collect behavioral information like conversions, detailed page views, etc. Run each

Re: Items blacklisted in the query made to Elasticsearch by UR

universal-recommendation>) 2017-03-30 20:00 GMT+02:00 Pat Ferrel mailto:p...@occamsmachete.com>>: "blacklistEvents": [[]], should be "blacklistEvents": [], On Mar 30, 2017, at 8:57 AM, Bruno LEBON mailto:b.le...@redfakir.fr>> wrote: Hello, We test the univ

Re: Empty result even though there are events

You have active date range filters and no dates in your data. This is because you are using the engine.json from the integration test, which uses that config. Start form engine.json.minimum and set the appName for your data and the eventNames you will use. On Mar 31, 2017, at 12:52 AM, Vagha

Re: Universal Recommender is recommending example data even after training the real data

Training never changed the model. Did you change the appName in engine.json to use you new app from `pio app list` ? You should have imported data into a new app, right? If you didn’t get a new appName you are just adding to the old integration test “handmade” app data. please share your engin

Re: Can I train and deploy on different machine

io-env.sh even if we use remote ES and Haddop clulsters? 2017-03-30 21:58 GMT+04:00 Pat Ferrel mailto:p...@occamsmachete.com>>: To run locally in the same process as pio delete those files and do not launch Spark as a daemon, only use PIO commands. We do not “re-deploy” we hot-swap the mod

Re: Items blacklisted in the query made to Elasticsearch by UR

"blacklistEvents": [[]], should be "blacklistEvents": [], On Mar 30, 2017, at 8:57 AM, Bruno LEBON wrote: Hello, We test the universal recommender on a cluster made following the tutorial from actionML. Once the build/train/deploy is done we send PIO a request to get recommendation. For exam

Re: Can I train and deploy on different machine

loyed, is that so? In the template Ecommerce recommendation ,the log was explicitly telling that the model was being deployed, whereas in Universal Recommender the log doesnt mention an eventual automatic deploy right after the train is done. 2017-03-29 21:25 GMT+02:00 Pat Ferrel mailto:p...@o

Re: Need Help setting up Universal Recommended with PIO

When pio became part of Apache we (ActionML) merged our fork and ALL previous templates were obsoleted because they require code from the io.prediction namespace, instead of the new org.apache.predictionio namespace. This means that you should install PredictionIO as described on http://predict

Re: pio train error java.lang.NegativeArraySizeException

Do you know an item is in NY? or are you trying to find what is preferred by New Yorkers? If the latter send events (user-id, location-preference, location-id) as secondary events. The location-id should be chosen to include some people but not too many so there is variation in what New Yorkers

Re: Can I train and deploy on different machine

age. 2017-03-29 22:18 GMT+04:00 Pat Ferrel mailto:p...@occamsmachete.com>>: yes My answer below was needlessly verbose. On Mar 28, 2017, at 8:41 AM, Marius Rabenarivo mailto:mariusrabenar...@gmail.com>> wrote: But I want to run the driver outside the server where I'll run the

Re: ERROR: Remote Elastic search cluster

no spaces are allowed in the hosts. it should be: PIO_STORAGE_SOURCES_ELASTICSEARCH_HOSTS=aabbcc174,aabbcc175,aabbcc176 On Mar 28, 2017, at 12:17 AM, Malay Tripathi wrote: Hi, I have setup 3 node cluster for ES - aabbcc174, aabbcc175, aabbcc176. In my spark edge node, I have installed Predicti

Re: pio train error java.lang.NegativeArraySizeException

yes There is very little validation of events done by PredictionIO since they are Template specific and the EventSever is not. Any usage event that does not have "entityType": “user” is ignored so ti the UR you have not data. Also user properties encoded in this way are ignored. User data shoul

Re: Can I train and deploy on different machine

where I'll deploy the engine? I mean for deploying I'm reading documentation about Spark right now for having insight on how I can do it but I want to know if someone has tried to do something similar. 2017-03-28 19:34 GMT+04:00 Pat Ferrel mailto:p...@occamsmachete.com>>: Spark must

Re: Samsara's learning curve

While I agree with D and T, I’ll add a few things to watch out for. One of the hardest things to learn is the new model of execution, it’s not quite Spark or any other compute engine. You need to create contexts that have virtualized the actual compute engine. But you will probably need to use t

[jira] [Commented] (PIO-49) Add support for Elasticsearch 5.x

[ https://issues.apache.org/jira/browse/PIO-49?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15945799#comment-15945799 ] Pat Ferrel commented on PIO-49: --- I've got the UR without any code changes working wit

Re: Can I train and deploy on different machine

Spark must be installed locally (so spark-submit will work) but Spark is only used to launch the PredictionServer. No job is run on Spark for the UR during query serving. We typically train on a Spark driver machine that is like part of the Spark cluster and deploy on a server separate from the

Re: Lambda and Kappa CCO

to change. This becomes feasible if you include the effect of down-sampling, but that has to be in the algorithm. From: Pat Ferrel Sent: Saturday, March 25, 2017 12:01:00 PM To: Trevor Grant; user@mahout.apache.org Cc: Ted Dunning; s...@apache.org Subject: Lambda and Kappa CCO This is an

Re: Marketing

rg Cc: Mahout Dev List Subject: Re: Marketing On Fri, Mar 24, 2017 at 8:27 AM, Pat Ferrel wrote: > maybe we should drop the name Mahout altogether. I have been told that there is a cool secondary interpretation of Mahout as well. I think that the Hebrew word is pronounced roughly like Mahout.

Re: Marketing

rg Cc: Mahout Dev List Subject: Re: Marketing On Fri, Mar 24, 2017 at 8:27 AM, Pat Ferrel wrote: > maybe we should drop the name Mahout altogether. I have been told that there is a cool secondary interpretation of Mahout as well. I think that the Hebrew word is pronounced roughly like Mahout.

Lambda and Kappa CCO

This is an overview and proposal for turning the multi-modal Correlated Cross-Occurrence (CCO) recommender from Lambda-style into an online streaming incrementally updated Kappa-style learner. # The CCO Recommender: Lambda-style We have largely solved the problems of calculating the multi-modal

Re: Marketing

Friday, March 24, 2017 11:13 AM > To: mahout > Cc: user@mahout.apache.org > Subject: Re: Marketing > > On Fri, Mar 24, 2017 at 12:09 PM, Dmitriy Lyubimov > wrote: > >> On Fri, Mar 24, 2017 at 8:27 AM, Pat Ferrel > wrote: >> >>> The multiple backend support is

Re: Marketing

nt: Friday, March 24, 2017 11:13 AM > To: mahout > Cc: u...@mahout.apache.org > Subject: Re: Marketing > > On Fri, Mar 24, 2017 at 12:09 PM, Dmitriy Lyubimov > wrote: > >> On Fri, Mar 24, 2017 at 8:27 AM, Pat Ferrel > wrote: >> >>> The multiple backend support is

Re: Marketing

ry, eat. When tired, sleep." Sounds like the honey badger to me... Trevor Grant Data Scientist https://github.com/rawkintrevo http://stackexchange.com/users/3002022/rawkintrevo http://trevorgrant.org *"Fortunate is he, who is able to know the causes of things." -Virgil* On Thu, M

Re: Marketing

ry, eat. When tired, sleep." Sounds like the honey badger to me... Trevor Grant Data Scientist https://github.com/rawkintrevo http://stackexchange.com/users/3002022/rawkintrevo http://trevorgrant.org *"Fortunate is he, who is able to know the causes of things." -Virgil* On Thu, M

Re: [VOTE] Apache Mahout 0.13.0 Release Candidate

I can’t +1 because of system integration errors that have to do with scoring that could be in Mahout. I doubt it is but don’t have time in the allotted vote period to track it down. My close looking tests of Mahout including the previous driver issues pass. Not sure if we use this style of vote

Re: Marketing

The little blue man (the mahout) was reborn (samsara) as a honey-badger? He must be close indeed to reaching true enlightenment, or is that Buddhism? On Mar 23, 2017, at 12:42 PM, Andrew Palumbo wrote: +1 on revamp. Sent from my Verizon Wireless 4G LTE smartphone Original message

Re: Marketing

The little blue man (the mahout) was reborn (samsara) as a honey-badger? He must be close indeed to reaching true enlightenment, or is that Buddhism? On Mar 23, 2017, at 12:42 PM, Andrew Palumbo wrote: +1 on revamp. Sent from my Verizon Wireless 4G LTE smartphone Original message

Re: [VOTE] Apache Mahout 0.13.0 Release Candidate

Before voting I’d like to run down the integration errors, which are different recs scores and could theoretically be because of different math results. On Mar 23, 2017, at 3:34 PM, Pat Ferrel wrote: BTW I’m getting bad integration test results, which are probably not related to what Mahout

Re: [VOTE] Apache Mahout 0.13.0 Release Candidate

BTW I’m getting bad integration test results, which are probably not related to what Mahout does since the math is tested in unit tests too. But the test runs with no runtime errors, Mahout as a Lib and drivers On Mar 23, 2017, at 3:32 PM, Pat Ferrel wrote: Come to think of it, I’m probably

Re: [VOTE] Apache Mahout 0.13.0 Release Candidate

, Andrew Musselman wrote: Those are probably expected INFOs; are you not getting that from a source build? On Thu, Mar 23, 2017 at 3:04 PM, Pat Ferrel wrote: > using the repo build of mahout I get all sorts of errors like this: > > [INFO] [RootSolverFactory$] Unable to create clas

Re: [VOTE] Apache Mahout 0.13.0 Release Candidate

phone Original message From: Pat Ferrel Date: 03/23/2017 3:05 PM (GMT-08:00) To: dev@mahout.apache.org Subject: Re: [VOTE] Apache Mahout 0.13.0 Release Candidate using the repo build of mahout I get all sorts of errors like this: [INFO] [RootSolverFactory$] Unable to create class GP

Re: [VOTE] Apache Mahout 0.13.0 Release Candidate

using the repo build of mahout I get all sorts of errors like this: [INFO] [RootSolverFactory$] Unable to create class GPUMMul: attempting OpenMP version [INFO] [RootSolverFactory$] Creating org.apache.mahout.viennacl.openmp.OMPMMul solver [INFO] [RootSolverFactory$] org.apache.mahout.viennacl.o

Re: Need a Suggessations

use PIO and UR to do the hard work, and get back the result either like an API which I think already works in PIO or saved somewhere in database like mysql or something like that. Thanks On Fri, Mar 24, 2017 at 1:03 AM, Pat Ferrel mailto:p...@occamsmachete.com>> wrote: The UR uses Elas

Re: Need a Suggessations

y wanaa use prediction.io <http://prediction.io/> in my production shortly after I implemented in local. Please help me, thank you very much for your help, I appreciate it so much. Vaghawan On Thu, Mar 23, 2017 at 9:27 PM, Pat Ferrel mailto:p...@occamsmachete.com>> wrote: Since PIO ha

Re: Need a Suggessations

Actually it is very easy to mix item and user recs, just put both item and user ids in the query. You can also boost item over user or user over item since they both allow special boosts in the query. No need to consult the EventServer. Note here: http://actionml.com/docs/ur_queries

Re: Need a Suggessations

Since PIO has moved to Apache, the namespace of PIO code changed and so all templates need to be updated. None of the ones in https://github.com/PredictionIO/ will work with Apache PIO. For the upgraded UR see:

Re: E-commerce recommender, recommendations for users who are not logged in?

Yes, you can filter by category if they are attached to items as properties. In 0.6.0, soon to be released, there are inclusion, exclusion, and boosts by any property that can be attached to items. Blacklists are for item-ids only, either items that have gotten certain events or just ids. The bu

Re: New RC?

Makes sense to me, I can’t test the 2 GPU versions. If 0.13.0 that is java only do we have an RC or code freeze to test? On Mar 18, 2017, at 1:43 PM, Andrew Palumbo wrote: Or rather if you're both in favor of it.. get the source/java only version out as 0.13.0 and follow up with automated bu

Re: UR: connection between entities and properties

understanding of user preference the better the recommendations On Mar 17, 2017, at 9:56 AM, Pat Ferrel wrote: Yes, I call this method a “trainer”. However in other apps we have done we pick popular videos from several clusters based on similarity of usage. This reaults in a list of video (music in your

Re: UR: connection between entities and properties

Yes, I call this method a “trainer”. However in other apps we have done we pick popular videos from several clusters based on similarity of usage. This reaults in a list of video (music in your case). Then allow the user to pick or like/dislike the music. After this training, which can go on as

Re: [VOTE] Apache Mahout 0.13.0 Release Candidate

OK, my tests passed including the last blocker, will test again on the new RC. On Mar 16, 2017, at 8:56 AM, Andrew Musselman wrote: Cancelling vote due to https://issues.apache.org/jira/browse/MAHOUT-1955 On Wed, Mar 15, 2017 at 8:55 AM, Andrew Musselman < andrew.mussel...@gmail.com> wrote:

Re: [VOTE] Apache Mahout 0.13.0 Release Candidate

OK, my tests passed including the last blocker, will test again on the new RC. On Mar 16, 2017, at 8:56 AM, Andrew Musselman wrote: Cancelling vote due to https://issues.apache.org/jira/browse/MAHOUT-1955 On Wed, Mar 15, 2017 at 8:55 AM, Andrew Musselman < andrew.mussel...@gmail.com> wrote:

Re: [VOTE] Apache Mahout 0.13.0 Release Candidate

The release was not made due to broken drivers, now fixed. I assume a new RC will come shortly? On Mar 11, 2017, at 9:54 PM, Andrew Musselman wrote: This is the vote for release 0.13.0 of Apache Mahout. The vote will be going for at least 72 hours and will be closed on Friday, March 3rd, 2017

Re: [VOTE] Apache Mahout 0.13.0 Release Candidate

The release was not made due to broken drivers, now fixed. I assume a new RC will come shortly? On Mar 11, 2017, at 9:54 PM, Andrew Musselman wrote: This is the vote for release 0.13.0 of Apache Mahout. The vote will be going for at least 72 hours and will be closed on Friday, March 3rd, 2017

Re: [training error] ElasticsearchIllegalArgumentException

as attached. > Thank you for helping! > > Best regards, > Amy > > Pat Ferrel mailto:p...@occamsmachete.com>> 於 > 2017年3月14日 週二 上午1:30寫道： > If you are running pio-start-all you must be running everything on a single > machine. This is called vertical scaling and is very

Re: [training error] ElasticsearchIllegalArgumentException

If you are running pio-start-all you must be running everything on a single machine. This is called vertical scaling and is very prone to running out of resources, either compute cores, or memory. If it has been running for some time you may have finally hit the limit if what you can do on the m

Re: [PredictionIO Error] Running Hbase

We will also release a Template that trims, compacts and optionally de-duplicates the DB using the SelfCleaningDataSource. As a template you can schedule it separately from `pio train`. The SelfCleaningDataSource method is pretty slow so we run it on some clients daily to maintain a moving time

[jira] [Updated] (PIO-49) Add support for Elasticsearch 5.x

[ https://issues.apache.org/jira/browse/PIO-49?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Pat Ferrel updated PIO-49: -- Priority: Blocker (was: Major) > Add support for Elasticsearch

[jira] [Commented] (PIO-49) Add support for Elasticsearch 5.x

[ https://issues.apache.org/jira/browse/PIO-49?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15906585#comment-15906585 ] Pat Ferrel commented on PIO-49: --- Going through the commit diff for clues, this should b

[jira] [Assigned] (PIO-49) Add support for Elasticsearch 5.x

[ https://issues.apache.org/jira/browse/PIO-49?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Pat Ferrel reassigned PIO-49: - Assignee: Donald Szeto > Add support for Elasticsearch

[jira] [Reopened] (PIO-49) Add support for Elasticsearch 5.x

[ https://issues.apache.org/jira/browse/PIO-49?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Pat Ferrel reopened PIO-49: --- Does not work > Add support for Elasticsearch 5.x > - > >

[jira] [Commented] (PIO-49) Add support for Elasticsearch 5.x

[ https://issues.apache.org/jira/browse/PIO-49?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15906580#comment-15906580 ] Pat Ferrel commented on PIO-49: --- The integration with the develop branch does not work

Re: Testing DataSource

Unit tests? I tend to test it with integration tests since that finds more problems than simple unit tests. There is a new Python integration test framework but I’m still using bash scripts On Mar 9, 2017, at 11:30 AM, Mars Hall wrote: Have any of you ever written tests for DataSource? Any r

[jira] [Commented] (MAHOUT-1951) Drivers don't run with remote Spark

[ https://issues.apache.org/jira/browse/MAHOUT-1951?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15903739#comment-15903739 ] Pat Ferrel commented on MAHOUT-1951: Oops misnamed the commit message for MA

[jira] [Resolved] (MAHOUT-1951) Drivers don't run with remote Spark

[ https://issues.apache.org/jira/browse/MAHOUT-1951?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Pat Ferrel resolved MAHOUT-1951. Resolution: Fixed Test thoroughly, not sure of side effects of the fix > Drivers don't

[jira] [Commented] (MAHOUT-1951) Drivers don't run with remote Spark

[ https://issues.apache.org/jira/browse/MAHOUT-1951?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15903327#comment-15903327 ] Pat Ferrel commented on MAHOUT-1951: [~Andrew_Palumbo] [~smarthi] There seems t

[jira] [Commented] (MAHOUT-1951) Drivers don't run with remote Spark

[ https://issues.apache.org/jira/browse/MAHOUT-1951?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15903320#comment-15903320 ] Pat Ferrel commented on MAHOUT-1951: A quick way to test this is: 1) get Spark

[jira] [Commented] (MAHOUT-1951) Drivers don't run with remote Spark

[ https://issues.apache.org/jira/browse/MAHOUT-1951?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15903315#comment-15903315 ] Pat Ferrel commented on MAHOUT-1951: scratch that PR. We do not have a fix for

Re: LLR thresholds

Wed, Mar 8, 2017 at 8:18 AM, Pat Ferrel wrote: > The CCO algorithm now supports a couple ways to limit indicators by > “quality". The new way is by the value of LLR. We built a t-digest > mechanism to look at the overall density produced with different > thresholds. The higher t

<    1   2   3   4   5   6   7   8   9   10   >