Hi,

I am using iknow text categorization to classify texts. I have 11 medical articles as my training set. Here is part of the source code:

ListerAndLoader
  SET domId=domoref.Id
  SET flister=##class(%iKnow.Source.File.Lister).%New(domId)
  SET myloader=##class(%iKnow.Source.Loader).%New(domId)
UseLister
  SET dirpath = "D:\iKnowTestCase\SmallDataBase\Medical"
  SET stat = myloader.SetLister(flister)
  SET stat = myloader.ProcessList(dirpath,$LB("txt"),0,"")
  IF stat '= 1 {WRITE "The lister failed: ",$System.Status.DisplayError(stat) QUIT } 
TrainingSet
  SET tTrainingSet = ##class(%iKnow.Filters.RandomFilter).%New(domId, 0.7)
  SET tTestSet = ##class(%iKnow.Filters.GroupFilter).%New(domId, "AND", 1) // NOT filter
  DO tTestSet.AddSubFilter(tTrainingSet)
  SET numSrcFD=##class(%iKnow.Queries.SourceAPI).GetCountByDomain(domId,tTrainingSet)
  WRITE "The training set includes ",numSrcFD," sources",!
  SET numSrcTD=##class(%iKnow.Queries.SourceAPI).GetCountByDomain(domId,tTestSet)
  WRITE "The test set includes ",numSrcTD," sources",!
TextClassifier
  SET tBuilder = ##class(%iKnow.Classification.IKnowBuilder).%New("MIT",tTrainingSet)
  SET tBuilder.ClassificationMethod = "naiveBayes"
  
  SET mstat = tBuilder.%AddCategory("Medical","",5)
  SET stat = tBuilder.%GetCategoryInfo(.pcategories)
  WRITE $LISTTOSTRING(pcategories(1)),!
  SET stat = tBuilder.%CreateClassifierClass("MIT.Classifier",1,1,1,1)
  
Optimizer
  WRITE "In the Optimizer",!
  SET tOpt = ##class(%iKnow.Classification.Optimizer).%New(domId,tBuilder)
  WRITE "optimizer is ",tOpt,!
  SET tOpt.ScoreMetric="MicroPrecision"
  WRITE "ScoreMetric is ",tOpt.ScoreMetric,!
  DO ##class(%iKnow.Queries.EntityAPI).GetTop(.result,domId,1,50)
  WRITE "load terms ",tOpt.LoadTermsArray(.result),!
  SET optstat=tOpt.Optimize(5)
  WRITE "Optimize status: ",optstat,!
  WRITE "End of Optimizer",!!
  DO ##class(%iKnow.Classification.Utils).%RunModelFromDomain(.r,
    "MIT.Classifier",domId,"helicopter",tTestSet)
  SET i=1
  WHILE $DATA(r(i)) {
       WRITE $LISTTOSTRING(r(i),",")
       SET i=i+1 }
TestClassifier
  WRITE tBuilder.%TestClassifier(tTestSet,.testresult,.accuracy),!
  WRITE "model accuracy: ",$FNUMBER(accuracy*100,"L",2)," percent",!
  SET n=1
  SET wrongcnt=0
  WHILE $DATA(testresult(n)) {
    IF $LISTGET(testresult(n),2) '= $LISTGET(testresult(n),3) {
     SET wrongcnt=wrongcnt+1
     WRITE "WRONG: ",$LISTGET(testresult(n),1)
     WRITE " actual ",$LISTGET(testresult(n),2)
     WRITE " pred. ",$LISTGET(testresult(n),3),! }
  SET n=n+1 }
  WRITE wrongcnt," out of ",n-1,!

When I run the function: tBuilder.%CreateClassFierClass("MIT.Classfier", 1,1,1,1)

I got the error: category 1 covers the whole data. I can not find this in the documentation.

Thank you.