Databases
StackOverflow2013
Postsdbo
POhow to use classwt in randomForest of R?
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POhow to use classwt in randomForest of R?
    primarykey
    data
    text
    <p>I have a highly imbalanced data set with target class instances in the following ratio <em>(edit:)</em> <s>60000:1000:1000:1000</s> <code>60000:1000:1000:50</code>(i.e. a total of 4 classes). I want to use <code>randomForest</code> for making predictions of the target class.</p> <p>So, to reduce the class imbalance, I played with <code>sampsize</code> parameter, setting it to <em>(edit:)</em> <s><code>c(5000, 1000, 1000, 1000)</code></s> <code>c(5000, 1000, 1000, 50)</code> and some other values, but there was not much use of it. Actually, the accuracy of the 1st class decreased while I played with <code>sampsize</code>, though the improvement in other class predictions was very minute.</p> <p>While digging through the archives, I came across two more features of <code>randomForest()</code>, which are <code>strata</code> and <code>classwt</code> that are used to offset class imbalance issue. </p> <p>All the documents upon <code>classwt</code> were old (generally belonging to the 2007, 2008 years), which all suggested not the use the <code>classwt</code> feature of <code>randomForest</code> package in <code>R</code> as it does not completely implement its complete functionality like it does in <code>fortran</code>. So the first question is:<br> <strong>Is <code>classwt</code> completely implemented now in <code>randomForest</code> package of R? If yes, what does passing <code>c(1, 10, 10, 10)</code> to the <code>classwt</code> argument represent?</strong> (Assuming the above case of 4 classes in the target variable)</p> <p>Another argument which is said to offset class imbalance issue is stratified sampling, which is always used in conjunction with <code>sampsize</code>. I understand what <code>sampsize</code> is from the documentation, but there is not enough documentation or examples which gave a clear insight into using <code>strata</code> for overcoming class imbalance issue. So the second question is:<br> <strong>What type of arguments have to be passed to <code>strata</code>in <code>randomForest</code> and what does it represent?</strong></p> <p>I guess the word <strong><em>weight</em></strong> which I have not explicitly mentioned in the question should play a major role in the answer.</p>
    singulars
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. PTQuestion
    1. This table or related slice is empty.
    1. USStrikeR
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. COI would run a forest on only the three smaller classes. That will give you a sense of how well a rf model could possibly distinguish those three classes without the dominant class at all. If the accuracy is still fairly low, then class imbalance is probably not your real problem, rather those three classes are just not easily distinguished with the features you have.
      singulars
      1. POhow to use classwt in randomForest of R?
      1. USjoran
    2. COThanks @joran . Sorry for a little confusion, here is the actual class instance ratio which I also have changed in the question: 60000:1000:1000:50. Do you think omitting the first class in this case is going to help? Because when I run RF with all 4 classes I get the accuracy in the following order for each class: c(90%, 70%, 70%, less than 10%). I'm more concerned about improving the accuracy of 4th class which is less than 10%. And one more thing is, is the `classwt` correctly implemented in `randomForest` of R as of now?
      singulars
      1. POhow to use classwt in randomForest of R?
      1. USStrikeR
    3. COAs for `classwt` implementation - I suppose it isn't implemented, because http://cran.r-project.org/web/packages/randomForest/NEWS you can read that "* Implement the new scheme of handling classwt in classification." is in wishlist.
      singulars
      1. POhow to use classwt in randomForest of R?
      1. USBartekCh
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload