You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@systemml.apache.org by GitBox <gi...@apache.org> on 2020/06/07 16:52:27 UTC

[GitHub] [systemml] t201 opened a new pull request #961: Documentation for Multinomial Logistic Regression using Trust Region method

t201 opened a new pull request #961:
URL: https://github.com/apache/systemml/pull/961


   This Documentation is for Multinomial Logistic Regression using Trust Region method.
   #  Introduction
   The DML (Declarative Machine Learning) language has built-in functions which enable access to both low- and high-level function
   
   
   
   ## `Multinomial Logistic Regression` -Function
   The Multinomial Logistic Regression Model is is used to link and provide an estimate of category label probabilities ( y, having multiple rows single column ) which are a response to the numerical vector of explanatory (feature) variables (x, having multiple rows and multiple columns) . The number of links can be 3 or greater unlike binomial regression.
   
   ### Usage
   ```
   mulLogisticRegression = function( Matrix X, Matrix Y,  intercept_scaling ,  max_iter , tolerance ,
      max1 ,  maxi2 ,  verbose )
     return(Matrix A)
   
   ### Arguments
   
   | Name             | Type            | Default  | Description |
   | :----            | :-------------  | -------- | :------------------------------- |
   | X                | Matrix[Double]  | --       | Matrix of numerical vector of explanatory  variables|
   | Y                | Matrix[Double]  | --       | Matrix of  a categorical response variable|
   | intercept_scaling| Int             | 0        | intercept for shifting and rescaling X columns|
   | reg_para         | Double          | 0        | regularization parameter|
   | tolerance        | Double          | 0.00001  | tolerance ("epsilon")|
   | max1             | Int             | 100      | max. no. of outer newton interations|
   | max2             | Int             | 0        | max. no. of inner (conjugate gradient) iterations|
   
   ### Returns
   | Type                   | Description |
   | :-------------         | :---------- |
   | Matrix[Double]         | probability regression as output |
   ### Example
   
   
   
   
   
   
   
   
   
   
   
   


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



[GitHub] [systemml] asfgit closed pull request #961: Documentation for Multinomial Logistic Regression using Trust Region method

Posted by GitBox <gi...@apache.org>.
asfgit closed pull request #961:
URL: https://github.com/apache/systemml/pull/961


   


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



[GitHub] [systemml] t201 commented on pull request #961: Documentation for Multinomial Logistic Regression using Trust Region method

Posted by GitBox <gi...@apache.org>.
t201 commented on pull request #961:
URL: https://github.com/apache/systemml/pull/961#issuecomment-640247518


   Working on forming an example.Some of the things i'm not able to comprehend in the example given for reference-
   -cbind
   -scaling and shifting of columns to mean 0 and variance 1
   -converting Y into indicator matrix
   -! converge and ! innerconverge 


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



[GitHub] [systemml] t201 commented on pull request #961: Documentation for Multinomial Logistic Regression using Trust Region method

Posted by GitBox <gi...@apache.org>.
t201 commented on pull request #961:
URL: https://github.com/apache/systemml/pull/961#issuecomment-640333050


   Alright 


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



[GitHub] [systemml] j143 edited a comment on pull request #961: Documentation for Multinomial Logistic Regression using Trust Region method

Posted by GitBox <gi...@apache.org>.
j143 edited a comment on pull request #961:
URL: https://github.com/apache/systemml/pull/961#issuecomment-643718317


   Thank you, @t201 - LGTM. 👍 
   🎉 🚀


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



[GitHub] [systemml] t201 commented on pull request #961: Documentation for Multinomial Logistic Regression using Trust Region method

Posted by GitBox <gi...@apache.org>.
t201 commented on pull request #961:
URL: https://github.com/apache/systemml/pull/961#issuecomment-640477596


   Updated the file with example .


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



[GitHub] [systemml] j143 commented on pull request #961: Documentation for Multinomial Logistic Regression using Trust Region method

Posted by GitBox <gi...@apache.org>.
j143 commented on pull request #961:
URL: https://github.com/apache/systemml/pull/961#issuecomment-640322731


   That's an improvement!
   Now, let us work on example.


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



[GitHub] [systemml] j143 commented on pull request #961: Documentation for Multinomial Logistic Regression using Trust Region method

Posted by GitBox <gi...@apache.org>.
j143 commented on pull request #961:
URL: https://github.com/apache/systemml/pull/961#issuecomment-643718317


   Thank you, @h0901 - LGTM. 👍 
   🎉 🚀


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org