[GitHub] incubator-predictionio pull request #377: Update analytics-ipynb.html.md.erb
GitHub user vaghawan opened a pull request: https://github.com/apache/incubator-predictionio/pull/377 Update analytics-ipynb.html.md.erb While running the spark console in ipython, the current commands gives error, so to mitigate that I've added %pylab inline instead of pylab inline which seems to give the problem. This has been checked in my case. You can merge this pull request into a Git repository by running: $ git pull https://github.com/vaghawan/incubator-predictionio patch-1 Alternatively you can review and apply these changes as the patch at: https://github.com/apache/incubator-predictionio/pull/377.patch To close this pull request, make a commit to your master/trunk branch with (at least) the following in the commit message: This closes #377 commit f37e1f2aa9a16a92c47fbef66c8e77debcd02b06 Author: vaghawan <vaghawan...@gmail.com> Date: 2017-05-02T04:52:18Z Update analytics-ipynb.html.md.erb While running the spark console in ipython, the current commands gives error, so to mitigate that I've added %pylab inline instead of pylab inline which seems to give the problem. This has been checked in my case. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---
[GitHub] incubator-predictionio-template-recommender issue #14: I experienced a bug i...
GitHub user vaghawan opened an issue: https://github.com/apache/incubator-predictionio-template-recommender/issues/14 I experienced a bug in the recommendation engine when I train 1 gb of data Hi, When I train 5 data the template is Ok, it recommend different item to different users. But when I train 30 of events, the template ends up recommending the same items for all the users but with a bit different score matrix. What's wrong, I don't know but it looks like a big bug, probably should only with me. I'm using the default codes with buy events. In small dataset its working all good, but with large data it's not. Can you please tell me why this is happening --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---
[GitHub] incubator-predictionio-template-ecom-recommender issue #11: How Would I load...
GitHub user vaghawan opened an issue: https://github.com/apache/incubator-predictionio-template-ecom-recommender/issues/11 How Would I load json data for training the model? Hi, there seems no example in the documentation regarding what kind of data can be imported and trained. I've data that comes in json format which are like this: ``` [ { bill_no: "CM/00038646/16", bill_date: "2016-12-01 07:19:45", icode: "BM55423", customer_code: "00041077" }, { bill_no: "CM/00038646/16", bill_date: "2016-12-01 07:19:45", icode: "BM49665", customer_code: "00041077" }, { bill_no: "CM/00038646/16", bill_date: "2016-12-01 07:19:45", icode: "BM60574", customer_code: "00041077" }, { bill_no: "CM/00038647/16", bill_date: "2016-12-01 07:21:26", icode: "BM67206", customer_code: "00041272" }, ] ``` I'm not even sure if I can load such data, all the events are 'buy' so there is no events like view or anything else. I just need to train the model for buy event. First I want to know if this template supports this kind of data, and second I only work with one event which is 'buy' in that case do I need to modify my json file, like appending 'buy' event in each json string? --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---