[
https://issues.apache.org/jira/browse/SOLR-9252?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15386382#comment-15386382
]
Joel Bernstein commented on SOLR-9252:
--------------------------------------
Yes the model can be saved as a document. The model contains the features that
were used to create the model. And the associated weights for each feature.
feature selection can be done as a separate step and stored in the index.
Feature selection takes time and it's likely users will want to view the
features that were extracted from the training data. Also, features could be
used for other purposes as they are really just a list of terms that provide
the most "information" about a training set. So it would be useful to store
them.
The training function reads the features as a stream, so they can either be a
stored feature set, or generated on the fly.
> Feature selection and logistic regression on text
> -------------------------------------------------
>
> Key: SOLR-9252
> URL: https://issues.apache.org/jira/browse/SOLR-9252
> Project: Solr
> Issue Type: Improvement
> Security Level: Public(Default Security Level. Issues are Public)
> Reporter: Cao Manh Dat
> Assignee: Joel Bernstein
> Attachments: SOLR-9252.patch, SOLR-9252.patch, SOLR-9252.patch,
> SOLR-9252.patch, SOLR-9252.patch, SOLR-9252.patch, enron1.zip
>
>
> SOLR-9186 come up with a challenges that for each iterative we have to
> rebuild the tf-idf vector for each documents. It is costly computation if we
> represent doc by a lot of terms. Features selection can help reducing the
> computation.
> Due to its computational efficiency and simple interpretation, information
> gain is one of the most popular feature selection methods. It is used to
> measure the dependence between features and labels and calculates the
> information gain between the i-th feature and the class labels
> (http://www.jiliang.xyz/publication/feature_selection_for_classification.pdf).
> I confirmed that by running logistics regressions on enron mail dataset (in
> which each email is represented by top 100 terms that have highest
> information gain) and got the accuracy by 92% and precision by 82%.
> This ticket will create two new streaming expression. Both of them use the
> same *parallel iterative framework* as SOLR-8492.
> {code}
> featuresSelection(collection1, q="*:*", field="tv_text", outcome="out_i",
> positiveLabel=1, numTerms=100)
> {code}
> featuresSelection will emit top terms that have highest information gain
> scores. It can be combined with new tlogit stream.
> {code}
> tlogit(collection1, q="*:*",
> featuresSelection(collection1,
> q="*:*",
> field="tv_text",
> outcome="out_i",
> positiveLabel=1,
> numTerms=100),
> field="tv_text",
> outcome="out_i",
> maxIterations=100)
> {code}
> In the iteration n, the text logistics regression will emit nth model, and
> compute the error of (n-1)th model. Because the error will be wrong if we
> compute the error dynamically in each iteration.
> In each iteration tlogit will change learning rate based on error of previous
> iteration. It will increase the learning rate by 5% if error is going down
> and It will decrease the learning rate by 50% if error is going up.
> This will support use cases such as building models for spam detection,
> sentiment analysis and threat detection.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
