[
https://issues.apache.org/jira/browse/FLINK-1735?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14536825#comment-14536825
]
ASF GitHub Bot commented on FLINK-1735:
---------------------------------------
GitHub user ChristophAl opened a pull request:
https://github.com/apache/flink/pull/665
[FLINK-1735] Feature Hasher
The prototype of the feature hasher.
- The implementation is based on the scikit-learn feature hasher
- Test vectors have been generated by scikit-learn as well
- Currently the implementation only works on Seq[String]
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/ChristophAl/flink FLINK-1735_FeatureHasher
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/flink/pull/665.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 #665
----
commit e5ad7e842f443dd4b15fe21f3d1d89c238c882d1
Author: Christoph Alt <[email protected]>
Date: 2015-05-06T22:10:24Z
Initial commit Issue #1735
commit 1e9312fdc46b741faea6bdfb26fc4ce359cd1cfa
Author: Christoph Alt <[email protected]>
Date: 2015-05-08T13:54:53Z
Added basic testcase for FeatureHasher
commit a0c6ee6251edc4d0e556ba98886a783a072bd27b
Author: Christoph Alt <[email protected]>
Date: 2015-05-08T13:58:59Z
FeatureHasher prototype
- Added a prototype of Feature Hasher, currently accepts Seq[String] only
commit c55eb11fa21943dd8451256755bc707a59c3f5d3
Author: Christoph Alt <[email protected]>
Date: 2015-05-08T14:09:48Z
Corrected typos
commit 7002ab9e18a6cca5b55d700967accb375538faad
Author: Christoph Alt <[email protected]>
Date: 2015-05-09T14:25:42Z
Moved Featurehasher to feature.extraction package
commit 15b868f08806b375fff564f851f668122d363457
Author: Christoph Alt <[email protected]>
Date: 2015-05-09T14:31:19Z
Readded FeatureHasher.scala
commit 38e0650ebdec305c4a51e788699da0809a3b1973
Author: Christoph Alt <[email protected]>
Date: 2015-05-09T18:36:00Z
Reformated test vectors
----
> Add FeatureHasher to machine learning library
> ---------------------------------------------
>
> Key: FLINK-1735
> URL: https://issues.apache.org/jira/browse/FLINK-1735
> Project: Flink
> Issue Type: New Feature
> Components: Machine Learning Library
> Reporter: Till Rohrmann
> Assignee: Felix Neutatz
> Labels: ML
>
> Using the hashing trick [1,2] is a common way to vectorize arbitrary feature
> values. The hash of the feature value is used to calculate its index for a
> vector entry. In order to mitigate possible collisions, a second hashing
> function is used to calculate the sign for the update value which is added to
> the vector entry. This way, it is likely that collision will simply cancel
> out.
> A feature hasher would also be helpful for NLP problems where it could be
> used to vectorize bag of words or ngrams feature vectors.
> Resources:
> [1] [https://en.wikipedia.org/wiki/Feature_hashing]
> [2]
> [http://scikit-learn.org/stable/modules/feature_extraction.html#feature-extraction]
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
