The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
"visualize .ass and GSP error"
olandesino
Member Posts: 19 Maven
Hi,
I'm a beginner data miner, hope that someone still can help me.
1. How can I visualize outputs from learners, example how can visualize W-Apriori output (.ass)?
2. When i use GSP algorithm and appears GeneralizedSequentialPatterns: Cannot handle missing values!
i don't understad because there are absolute no missing values in my data set, i tried even with preprocessing missing value operation. How can I solve this problem?
Thanks in advance
A.Florio
I'm a beginner data miner, hope that someone still can help me.
1. How can I visualize outputs from learners, example how can visualize W-Apriori output (.ass)?
2. When i use GSP algorithm and appears GeneralizedSequentialPatterns: Cannot handle missing values!
i don't understad because there are absolute no missing values in my data set, i tried even with preprocessing missing value operation. How can I solve this problem?
Thanks in advance
A.Florio
Tagged:
0
Answers
In short you probably are in the wrong place for good answers to your questions, as both of your questions relate to WEKA operators. However, missing values are there if the learner says so, so if you are certain there are no missing values you will need to understand why the learner doesn't like the input example set. What exactly have you done to check the values?
By the way, i check personally all 385 rows of my dataset and it says the cannot handle missing values.
Besides i putted also the MissingValueReplenishment operator.
This is the simple process
<operator name="Root" class="Process" expanded="yes">
<operator name="ExampleSource" class="ExampleSource">
<parameter key="attributes" value="~/dataset.aml"/>
</operator>
<operator name="MissingValueReplenishment" class="MissingValueReplenishment">
<list key="columns">
</list>
</operator>
<operator name="W-GeneralizedSequentialPatterns" class="W-GeneralizedSequentialPatterns">
</operator>
</operator>
I really appreciate your help.
Thanks
A.Florio
By the way, the missing value operator is currently set to do nothing, but we can come to that later.
I run the process till the example source(break) and the output window shows me the data (385 rows and 3 regular attributes) in 3 ways (Meta data, data and plot). Even here there are no missing values or '?'. :-\
If so we have to think again, as the missing value fixer won't help. In that case I think you'd be better off to check with WEKA on the input formats required, perhaps that is being read wrongly. I trust that you put all the right things in you AML file but I'm not familiar with this operator so I can't tell, sorry.
I have noticed that you can turn up the debug level on this operator, and of course you can do the same with RM; that might point you to what is clogging the system.
I hope there is (somewhere) a solution for this problem.
A.Florio