Pages: [1]
  Print  
Author Topic: READ BEFORE POSTING: Frequently Asked Questions  (Read 9525 times)
Marius
Administrator
Hero Member
*****
Posts: 1794



WWW
« on: June 27, 2012, 09:57:27 AM »

This topic collects the most frequently asked questions in this forum. It is based on the feedback of our users, that is you. Keep on rocking!

I am a beginner with data mining and/or RapidMiner, where should I get started?
Answer: Checkout the documentation page on our website. Especially the video tutorials are a good entry point.

Attribute X is not shown in the drop-down list of Select Attributes (Set Role, Sort, ...), but I'm sure it is in my data
Short answer: Instead of searching the attribute in the list, just type it in the textfield on top. That's possible even if the attribute is not contained in the list.
Long answer: RapidMiner compiles the attribute list without actually running the process, but just guesses them from the input data and the operators which are applied on the data. However, there are some operations where the output of the operator cannot be determined without running it or looking at the complete data. Think of the Pivot operator, wordlists from text mining and alike. In this case, the selection list does not list all attributes which will be present on the actual processed data.

Why does my Decision Tree contain only one node?
RapidMiner's decision tree has a "minimal gain" parameter. If a new node would not result in at least that increase of model performance, the algorithm stops. Try to decrease the parameter value if you want deeper trees. But you should carefully evaluate your models and compare different parameter settings. For that you should have a look at the Optimize Parameters operator.

How do I visualize my data?
Please have a look at this post: http://rapid-i.com/rapidforum/index.php/topic,6141.msg21562.html#msg21562

Generate Attributes does not work with attributes like sum(a1)
Generate Attributes can't handle parentheses and spaces in attribute names. Please have a look at this thread for further information: Aggregation and generate Attribute

I want to cluster my texts (webfeeds, blogposts) or I want to count words
Answer: Check out our Text Mining Extension and watch the videos about data mining with RapidMiner in general and about text mining by Neil McGuigan: click here

I have unbalanced data,but I want an equal number of examples for each class
Please read the following two threads:
 - Stratification: How to get the same number of examples for each class?
 - Unbalanced Dataset ...need help!

Which version of libSVM does RapidMiner use?
libSVM version 2.84.

How is a ROC plot generated?
Please read this post by wessel.

My Extension does not compile because of locked .metadata\.lock file
If your extension does not compile because of a locked .metadata\.lock file
Code:
BUILD FAILED
E:\eclipse\workspace\RapidMiner_Unuk\build_extension.xml:129: The following error occurred while executing this line:
E:\eclipse\workspace\RapidMiner_Unuk\build_extension.xml:181: The following error occurred while executing this line:
E:\eclipse\workspace\RapidMiner_Unuk\build_extension.xml:186: The following error occurred while executing this line:
Error reading project file E:\eclipse\workspace\.metadata\.lock: The process cannot access the file because another process has locked a portion of the file
Change the build.xml of your extension to look like this:
Code:
<fileset id="build.dependentExtensions" dir="..">
<exclude name="**/*" />
</fileset>

I still have questions!
Answer: Feel free to post any questions or comments you have in the appropriate category of our forum. The RapidMiner team and the community do their best to answer all concerns from absolute beginners as well as questions on sophisticated topics from the most advanced users. Please read this post before asking any questions!

My question is not answered on the forum or The response times are too high
This forum is driven maintained by RapidMiner users in their free time, and also the RapidMiner team peeks in from time to time. But we are also busy with maintaining RapidMiner and improving our software. That means that depending on our workload we are not able to answer forum posts. For the impatient and for business clients RapidMiner offers professional support for all of our products with guaranteed response times. Please feel free to contact us for more information.

I want to be part of the team! Does RapidMiner offer jobs?
Answer: Yes, we are hiring! Please find our job offers on our website.


Last edit: updated URLs
« Last Edit: March 03, 2014, 09:12:54 AM by Marco Boeck » Logged

Please add [SOLVED] to the topic title when your problem has been solved! (do so by editing the first post in the thread and modifying the title)
Please click here before posting.
Pages: [1]
  Print  
 
Jump to: