You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by "Robin Swezey (JIRA)" <ji...@apache.org> on 2011/02/03 13:48:29 UTC
[jira] Created: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
-------------------------------------------------------------------------------------------------
Key: MAHOUT-605
URL: https://issues.apache.org/jira/browse/MAHOUT-605
Project: Mahout
Issue Type: Bug
Components: Classification
Affects Versions: 0.4
Environment: Linux
Reporter: Robin Swezey
Priority: Minor
Fix For: 0.4
The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
Ex:
{quote}
47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
ClassifierResult\{category='愛知県', score=32.487981016587796\},
ClassifierResult\{category='東京都', score=32.49189358054859\},
ClassifierResult\{category='北海道', score=32.49811200756193\}]
{quote}
(classification of documents for Japanese prefectures)
Inside the classifyDocument method, just before the return statement we found this line:
{quote}
Collections.reverse(result);
{quote}
Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Swezey (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12994030#comment-12994030 ]
Robin Swezey commented on MAHOUT-605:
-------------------------------------
Robin, Sean
This is Robin S.
We thank you for your quick answer and your reactivity.
Let me detail why my professor asked this question. In org.apache.mahout.classifier.bayes.algorithm.CBayesAlgorithm, which we use to output a class scalar for the most probable prefecture given a news article, the following code is written under public ClassifierResult[] classifyDocument(String[] document, Datastore datastore, String defaultCategory, int numResults):
for (String category : categories) {
double prob = documentWeight(datastore, category, document);
However, we conducted a diff on the documentWeight method called, between the CNB version and its NB counterpart, and they are identical. This is also the case for public ClassifierResult[] classifyDocument(String[] document, Datastore datastore, String defaultCategory, int numResults).
The methods to sort documents are identical in the NB and CNB Algorithm classes, the Collections.reverse(result); line is present in both versions.
Are the weights different types of weights? One of the drivers for NB/CNB training seems to differ in the case of CNB training (Complementary Bayes Theta Normalizer Driver), is there some relation to this? Then why the need to sort it ascendant? (which is done in both cases)
This portion of the code looks a little confusing, hence our question.
We thank you again for your reactivity.
Robin S.
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Reopened: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Swezey (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Robin Swezey reopened MAHOUT-605:
---------------------------------
I have provided some more details on the matter
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Swezey (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12994046#comment-12994046 ]
Robin Swezey commented on MAHOUT-605:
-------------------------------------
Robin
Thank you for your very quick answer. As stated in the example of the very first post, we have 47 classes (Japanese prefectures). But we want to use it on more than 1700 classes (Japanese cities), hence the need for CNB because the Ja Wikipedia corpus does not give a lot of information on small cities.
I have a paper in review which uses this feature of Mahout and explains in more detail, in case you need it.
If there is a mistake in the code, this could help explain the current efficiency of our classifier, which is not really good as of the moment.
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Anil (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12991975#comment-12991975 ]
Robin Anil commented on MAHOUT-605:
-----------------------------------
Cbayes has scores which is decreasing with increase in class affinity. You can guess rom the definition . Is it for that classifier you are seeingn this
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Anil (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12994047#comment-12994047 ]
Robin Anil commented on MAHOUT-605:
-----------------------------------
At >2 classes. I dont see an issue. I have to verify whether the values are coming same for NB and CNB. Btw. a mpdel trained for CNB can be used for NB. but not vice versa. Are you training with cbayes option?
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Issue Comment Edited: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Swezey (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12994030#comment-12994030 ]
Robin Swezey edited comment on MAHOUT-605 at 2/13/11 8:39 AM:
--------------------------------------------------------------
Robin, Sean
This is Robin S.
We thank you for your quick answer and your reactivity.
Let me detail why my professor asked this question. In org.apache.mahout.classifier.bayes.algorithm.CBayesAlgorithm, which we use to output a class scalar or class aray for the most probable prefecture given a news article, the following code is written under public ClassifierResult[] classifyDocument(String[] document, Datastore datastore, String defaultCategory, int numResults):
for (String category : categories) {
double prob = documentWeight(datastore, category, document);
However, we conducted a diff on the documentWeight method called, between the CNB version and its NB counterpart, and they are identical. This is also the case for public ClassifierResult[] classifyDocument(String[] document, Datastore datastore, String defaultCategory, int numResults).
The methods to sort documents are identical in the NB and CNB Algorithm classes, the Collections.reverse(result); line is present in both versions.
Are the weights different types of weights? One of the drivers for NB/CNB training seems to differ in the case of CNB training (Complementary Bayes Theta Normalizer Driver), is there some relation to this? Then why the need to sort it ascendant? (which is done in both cases)
This portion of the code looks a little confusing, hence our question.
We thank you again for your reactivity.
Robin S.
was (Author: mizudera):
Robin, Sean
This is Robin S.
We thank you for your quick answer and your reactivity.
Let me detail why my professor asked this question. In org.apache.mahout.classifier.bayes.algorithm.CBayesAlgorithm, which we use to output a class scalar for the most probable prefecture given a news article, the following code is written under public ClassifierResult[] classifyDocument(String[] document, Datastore datastore, String defaultCategory, int numResults):
for (String category : categories) {
double prob = documentWeight(datastore, category, document);
However, we conducted a diff on the documentWeight method called, between the CNB version and its NB counterpart, and they are identical. This is also the case for public ClassifierResult[] classifyDocument(String[] document, Datastore datastore, String defaultCategory, int numResults).
The methods to sort documents are identical in the NB and CNB Algorithm classes, the Collections.reverse(result); line is present in both versions.
Are the weights different types of weights? One of the drivers for NB/CNB training seems to differ in the case of CNB training (Complementary Bayes Theta Normalizer Driver), is there some relation to this? Then why the need to sort it ascendant? (which is done in both cases)
This portion of the code looks a little confusing, hence our question.
We thank you again for your reactivity.
Robin S.
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Resolved] (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Anil (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Robin Anil resolved MAHOUT-605.
-------------------------------
Resolution: Not A Problem
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Ted Dunning (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12994048#comment-12994048 ]
Ted Dunning commented on MAHOUT-605:
------------------------------------
Robin S.
Remember that CNB is computing a score that indicates whether the document belongs to the complementary class while the NB score indicates whether the document belongs to the class. Thus, the code may be the same, but the origin of the weights is different.
As Robin A mentioned for 2 classes CNB and NB are equivalent, although reversed.
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Updated: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Sean Owen (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sean Owen updated MAHOUT-605:
-----------------------------
Due Date: 11/Feb/11
Fix Version/s: (was: 0.4)
0.5
Assignee: Robin Anil
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Anil (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12994042#comment-12994042 ]
Robin Anil commented on MAHOUT-605:
-----------------------------------
I think there might be a problem. How many classes are you trying. I am guessing two. In which case NB = CNB. the need to reverse the array may not exist. Again I will have to confirm this.
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Swezey (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13003114#comment-13003114 ]
Robin Swezey commented on MAHOUT-605:
-------------------------------------
Hello
On the mailing-list Robin A said that the weights are to be considered as negative numbers so this solves the issue of knowing if we have CNB or not, this is CNB alright.
I have 2 very quick questions before the issue is resolved:
1/ This implementation is a TWCNB, am I not mistaken?
2/ If we re-run the SinglyClassifier2 example of my previous post (http://pastebin.com/VMUVGmUd lines 57-61), but limit the number of results to 3 like this:
bq. String[] doc = {"mspublisher", "parallax", "polaroid", "corel", "illustrator", "coreldraw"};
bq. SinglyClassifier2 sc = new SinglyClassifier2();
bq. List<ClassifierResult> results = sc.classifyDocument(doc, "comp.graphics", 3);
Then we get as output:
bq. [ClassifierResult{category='sci.med', score=71.12823038989241}, ClassifierResult{category='talk.politics.mideast', score=71.12905966433597}, ClassifierResult{category='sci.crypt', score=71.13190725486677}]
So this is not a N-best output, but actually a N-worst. Hence, there still might be a problem with this line in CBayesAlgorithm.classifyDocument(String[] document, Datastore datastore, String defaultCategory, int numResults):
bq. Collections.reverse(result);
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Swezey (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13000854#comment-13000854 ]
Robin Swezey commented on MAHOUT-605:
-------------------------------------
Robin A
We're launching SinglyClassifier2 simply by Eclipse on Hadoop environment, if this was your question. The Mahout source that we use was checked out not long ago. Mahout is packaged with our SinglyClassifier2 and then thrown at our cluster to run directly through SinglyClassifier2's main()
http://screencast.com/t/XcYPHwPM82Zw
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Swezey (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12994054#comment-12994054 ]
Robin Swezey commented on MAHOUT-605:
-------------------------------------
Ted: Yes, this is my question. If the weights are indeed normal weight and complementary weight, then this means in terms of design that we need to reverse the array again when we use CNB? To obtain the _real_ most probable class (not a class weighed by its complementary) first and then the others.
Also for example, in public ClassifierResult classifyDocument(String[] document, Datastore datastore, String defaultCategory), this would imply:
-- if (max < prob) {
++ if (max > prob) {
if I catch you right on what you say.
Robin A: Yes, we are using the cbayes option. If the values are indeed coming different for NB and CNB then I think the matter is solved.
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Swezey (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13000838#comment-13000838 ]
Robin Swezey commented on MAHOUT-605:
-------------------------------------
Hello, this is Robin S.
I am sorry, it looks like that I was not really clear in my post and comments.
I will reformulate in this comment with a more understandable example, to state the problem we believe we are seeing.
We have uploaded all the files and logs of this example there:
1. Training CBayes tutorial log http://pastebin.com/5N7cQsKU
2. Testing Bayes tutorial log http://pastebin.com/Q4XscCgz
3. Testing CBayes tutorial log http://pastebin.com/F7rBReag
4. Our testing class for weights http://pastebin.com/VMUVGmUd
5. Output of the testing class http://pastebin.com/LPLZ6LRA
A/
Using the tutorial on https://cwiki.apache.org/MAHOUT/twenty-newsgroups.html we have:
- generated train and test datasets for the 20 newsgroups example
- trained them on a Hadoop cluster (8 nodes) with the following command: (see file 1)
{quote}
$MAHOUT_HOME/bin/mahout trainclassifier -i scope/run_24/train-input -o scope/run_24/model -type cbayes -ng 1 -source hdfs &> ../logs/run_24/train_output.txt
{quote}
- tested them twice locally with the following commands: (see file 2) (see file 3)
{quote}
hadoop dfs -get scope/run_24/model ./
export HADOOP_HOME=""
$MAHOUT_HOME/bin/mahout testclassifier -m model -d test-input -type bayes -ng 1 -source hdfs -method sequential &> ../logs/run_24/test_output.txt
{quote}
(this is a Bayes test, which according to our own Mahout tests and what Robin A was saying, can be done with a CBayes model)
{quote}
$MAHOUT_HOME/bin/mahout testclassifier -m model -d test-input -type cbayes -ng 1 -source hdfs -method sequential &> ../logs/run_25/test_output.txt
{quote}
(a CBayes test, we use the same trained model and test input as run_24 just above)
Here are the outputs:
{quote}
Bayes-test of CBayes-trained classifier on 20-newsgroups: (see file 2)
Correctly Classified Instances : 6003 79.6999%
Incorrectly Classified Instances : 1529 20.3001%
Total Classified Instances : 7532
{quote}
{quote}
CBayes-test of CBayes-trained classifier on 20-newsgroups: (see file 3)
Correctly Classified Instances : 6401 84.9841%
Incorrectly Classified Instances : 1131 15.0159%
Total Classified Instances : 7532
{quote}
B/
Then, we made a testing class (see file 4) which tests a sample document which obviously has most affinity with comp.graphics: (file 4) (lines 57-61)
{quote}
String[] doc = \{"mspublisher", "parallax", "polaroid", "corel", "illustrator", "coreldraw"\};
SinglyClassifier2 sc = new SinglyClassifier2();
List<ClassifierResult> results = sc.classifyDocument(doc, "comp.graphics", 47);
System.out.println(results);
{quote}
But when we run this test we can see that the weight increases with class affinity, since comp.graphics is the last class: (file 5)
bq. [ClassifierResult{category='sci.med', score=71.12823038989241}, ClassifierResult{category='talk.politics.mideast', score=71.12905966433597}, ClassifierResult{category='sci.crypt', score=71.13190725486677}, ClassifierResult{category='soc.religion.christian', score=71.133650306131}, ClassifierResult{category='talk.politics.guns', score=71.13395246918788}, ClassifierResult{category='rec.sport.hockey', score=71.135412697019}, ClassifierResult{category='rec.motorcycles', score=71.13588019314241}, ClassifierResult{category='talk.politics.misc', score=71.13646012313777}, ClassifierResult{category='rec.autos', score=71.13665909470443}, ClassifierResult{category='rec.sport.baseball', score=71.14030022524815}, ClassifierResult{category='comp.sys.mac.hardware', score=71.14259436929609}, ClassifierResult{category='alt.atheism', score=71.14375467011567}, ClassifierResult{category='talk.religion.misc', score=71.14396375715604}, ClassifierResult{category='misc.forsale', score=71.15726130106582}, ClassifierResult{category='comp.sys.ibm.pc.hardware', score=71.23220093257258}, ClassifierResult{category='sci.space', score=71.2370437832205}, ClassifierResult{category='comp.windows.x', score=71.48765607132557}, ClassifierResult{category='sci.electronics', score=71.50156901557527}, ClassifierResult{category='comp.os.ms-windows.misc', score=71.79695095091601}, ClassifierResult{category='comp.graphics', score=73.46107190566988}]
So there is obviously increase of the weight with increase of class affinity. No complementary weight seems to be used.
However, when looking at files 2 and 3, we can see that the CNB testing performs better than the NB testing. But we are unsure if what we are having is _really_ a CNB, without relation to the better performance of whatever algorithm is run in the case of file 3.
We believe there is a problem somewhere, either in
- the CBayesThetaNormalizer?
- the InMemoryBayesDataStore?
- the way we are using the classifier or following the tutorial?
Is the training really CNB? Or is it a problem with the CNB testing?
(I hope this comment was more clear than the last ones. We have an accepted paper which makes use of Mahout, and we need to clarify this matter before submitting the revised version.)
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Swezey (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13000848#comment-13000848 ]
Robin Swezey commented on MAHOUT-605:
-------------------------------------
Robin A
Thank you for your quick reply.
The source code of the test class SinglyClassifier is in pastebin file 4:
http://pastebin.com/VMUVGmUd
Please tell me if you need any more info.
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Anil (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13000839#comment-13000839 ]
Robin Anil commented on MAHOUT-605:
-----------------------------------
Can you give a little bit more info about SinglyClassifer, the way its initializing the classifier internally
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Commented: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Robin Anil (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12991987#comment-12991987 ]
Robin Anil commented on MAHOUT-605:
-----------------------------------
Sorry about the typos, was typing from my phone
CBayes is about finding the probability of belonging to the complement class. The one with the least score will be most likely not belong to the complement class.. and hence
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] Resolved: (MAHOUT-605) Array returned by
classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted
ascendant
Posted by "Sean Owen (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAHOUT-605?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sean Owen resolved MAHOUT-605.
------------------------------
Resolution: Not A Problem
Yes, the title suggests this is for CBayes. You are saying that lower scores mean higher affinity, so, sorting from score low to high is sorting from high affinity to low, and that is the intended (and likely expected) behavior, right? Provisionally closing this, but, let's reopen if we've missed the point here.
> Array returned by classifier.bayes.algorithm.CBayesAlgorithm.classifyDocument is sorted ascendant
> -------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-605
> URL: https://issues.apache.org/jira/browse/MAHOUT-605
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.4
> Environment: Linux
> Reporter: Robin Swezey
> Assignee: Robin Anil
> Priority: Minor
> Labels: bayesian, classification
> Fix For: 0.5
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The array returned for a n-best call to classifyDocument is sorted ascendant instead of descendant.
> Ex:
> {quote}
> 47-best: [ClassifierResult\{category='香川県', score=32.28281232047167\},
> ClassifierResult\{category='宮崎県', score=32.28969992600906\}, ......,
> ClassifierResult\{category='愛知県', score=32.487981016587796\},
> ClassifierResult\{category='東京都', score=32.49189358054859\},
> ClassifierResult\{category='北海道', score=32.49811200756193\}]
> {quote}
> (classification of documents for Japanese prefectures)
> Inside the classifyDocument method, just before the return statement we found this line:
> {quote}
> Collections.reverse(result);
> {quote}
> Is this a mistake or a design choice? (we are not sure, hence the "Minor" priority)
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira