Question

我为用户提供了数据集，点击了一个在线网站的每个会话的模式。我想使用Markov chain＆amp; amp;它的概率。

Following is the my Code:

library(clickstream);
cls2<-readClickstreams(file.choose(),sep = ',',header = TRUE);
mc2<-fitMarkovChain(clickstreamList = cls2,order = 2,control = list(optimizer= "linear"));
pattern <- new("Pattern", sequence = c("/clsisGre/PersonalDetailForm.jsp","/clsisGre/PersonalDetail.jsp"),                                         absorbingProbabilities = data.frame(NULL = 0.9, Success = 0.1));
> resultPattern <- predict(mc2, startPattern = pattern, dist = 1);

Error Message is :

Error in if (nextState %in% object@absorbingStates) { : 
  argument is of length zero
In addition: Warning message:
In max(cp, na.rm = T) : no non-missing arguments to max; returning -Inf

需要帮助来处理此错误/异常。提前谢谢。

Answer 1

对于迟到的更新感到抱歉，但我能够解决这个问题，所以我发布了可能对其他人有帮助的相同解决方案。在代码中（a，b，c，d，e，f，g，h，l，m）是我想构建马尔可夫链的序列输入。下面的代码将有助于处理上面提到的错误。

  pattern <- new("Pattern", sequence = c(a,b,c,d,e,f,g,h,l,m),
                   absorbingProbabilities = data.frame(NULL = 0.9, Success = 0.1));
    possibleError <- tryCatch(
      suppressWarnings( predict(mc2, startPattern = pattern, dist = 1)),
      error=function(e) e
    );

    if(inherits(possibleError, "error")) next
    resultPattern <- predict(mc2, startPattern = pattern, dist = 1);

    aa<-attributes(resultPattern)$absorbingProbabilities;
    success_mat10[i,2]<-aa$Success;
    success_mat10[i,1]<-as.vector(url_mat10[i,1]);

使用＆＃34;预测＆＃34;时出错用点击流包在R中进行马尔可夫链实现的方法

1 个答案: