[
https://issues.apache.org/jira/browse/MAHOUT-242?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12803944#action_12803944
]
Drew Farris commented on MAHOUT-242:
------------------------------------
Decoupling the tokenization logic from the ngrammer is a great idea. I think
Ted sort of alluded to this in a recent post on another subject as well. Here,
the input would really be a stream of tokens. It makes a great deal of sense to
do the analysis offline.
I'll take a shot a providing a SequenceFile<Doc ID, Document> ->
SequenceFile<DocId, TokenStream> utility and update this code to take input
from there. I suspect it would also be handy to be able to easily string a
bunch of these processing steps (Document files > Sequence file<Doc Id, Doc> ->
Sequence File<DocId, TokenStream together into a chain, but that's a larger
issue. What does anyone else think?
Also, I wanted to ask: does it make more sense to emit a sequence file
<longwritable, text> (or gram) instead of a text file? There had been some
recent traffic on this list about this wrt line endings and I suspect it may be
more reasonable to provide the former as output (or both!?)
> LLR Collocation Identifier
> --------------------------
>
> Key: MAHOUT-242
> URL: https://issues.apache.org/jira/browse/MAHOUT-242
> Project: Mahout
> Issue Type: New Feature
> Affects Versions: 0.3
> Reporter: Drew Farris
> Priority: Minor
> Attachments: MAHOUT-242.patch, MAHOUT-242.patch,
> mahout-colloc.tar.gz, mahout-colloc.tar.gz
>
>
> Identifies interesting Collocations in text using ngrams scored via the
> LogLikelihoodRatio calculation.
> As discussed in:
> *
> http://www.lucidimagination.com/search/document/d051123800ab6ce7/collocations_in_mahout#26634d6364c2c0d2
> *
> http://www.lucidimagination.com/search/document/b8d5bb0745eef6e8/n_grams_for_terms#f16fa54417697d8e
> Current form is a tar of a maven project that depends on mahout. Build as
> usual with 'mvn clean install', can be executed using:
> {noformat}
> mvn -e exec:java -Dexec.mainClass="org.apache.mahout.colloc.CollocDriver"
> -Dexec.args="--input src/test/resources/article --colloc target/colloc
> --output target/output -w"
> {noformat}
> Output will be placed in target/output and can be viewed nicely using:
> {noformat}
> sort -rn -k1 target/output/part-00000
> {noformat}
> Includes rudimentary unit tests. Please review and comment. Needs more work
> to get this into patch state and integrate with Robin's document vectorizer
> work in MAHOUT-237
> Some basic TODO/FIXME's include:
> * use mahout math's ObjectInt map implementation when available
> * make the analyzer configurable
> * better input validation + negative unit tests.
> * more flexible ways to generate units of analysis (n-1)grams.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
