R中随机森林模型的进度条

Question

I am using randomForest model in R .

For large numbers of trees my program takes a long time to complete .

In "randomForest" function i can use "do.trace=TRUE" to see the real time progress . Sample out put in real time on R console is as follows

ntree    OOB      1      2      3      4      5      6      7      8      9 
100:   2.31%  7.14%  2.08%  0.00%  2.25% 10.81%  0.90%  0.00%  0.00%  1.72% 
200:   1.95%  7.14%  2.08%  0.00%  2.25%  8.11%  0.00%  0.00%  0.00%  1.72% 
300:   1.78%  7.14%  2.08%  0.00%  1.69%  8.11%  0.00%  0.00%  0.00%  1.72% 
400:   1.95%  7.14%  2.08%  0.00%  1.69%  8.11%  0.00%  0.00%  0.00%  3.45% 
500:   1.78%  7.14%  2.08%  0.00%  1.69%  8.11%  0.00%  0.00%  0.00%  1.72% 
600:   1.78%  7.14%  2.08%  0.00%  1.69%  8.11%  0.00%  0.00%  0.00%  1.72% 
700:   1.78%  7.14%  2.08%  0.00%  1.69%  8.11%  0.00%  0.00%  0.00%  1.72% 
800:   1.78%  7.14%  2.08%  0.00%  1.69%  8.11%  0.00%  0.00%  0.00%  1.72% 
900:   1.78%  7.14%  2.08%  0.00%  1.69%  8.11%  0.00%  0.00%  0.00%  1.72% 
1000:  1.78%  7.14%  2.08%  0.00%  1.69%  8.11%  0.00%  0.00%  0.00%  1.72% 

The first row (100: 2.31% ....) comes first. After 1 second it comes 2nd row and so on. I would like to modify this output .

When 1st row will come , I need to grab only "100" from the whole line and show only "100" on R console instead of showing the whole line. Similarly for rest of the rows.

[ I tried sink(). but it will not work as sink writes the complete output to output file ]

[I searched for do.trace option in randomForest function. but I lost myself as I suspect it calls come C program; although I am not sure.]

I would like to grab the real time output on R console.

Note : I have seen the following issues .

1. https://github.com/jni/ray/issues/33
2. Problematic Random Forest training runtime when using formula interface

Answer 1

Downloaded: https://cran.r-project.org/src/contrib/randomForest_4.6-10.tar.gz

When looking at the C code for refRF.C (and I suspect classRF.C which is also called with do.trace when it's a classification problem) and then following the 'jprint' flag which is what is received by the do.trace -flag in the surrounding R code, we see:

/* print header for running output */
    if (*jprint <= *nTree) {
    Rprintf("     |      Out-of-bag   ");
    if (*testdat) Rprintf("|       Test set    ");
    Rprintf("|\n");
    Rprintf("Tree |      MSE  %%Var(y) ");
    if (*testdat) Rprintf("|      MSE  %%Var(y) ");
    Rprintf("|\n");
    }

And:

 /* Print running output. */
    if ((j + 1) % *jprint == 0) {
        Rprintf("%4d |", j + 1);
        Rprintf(" %8.4g %8.2f ", errb, 100 * errb / varY);
        if(*labelts == 1) Rprintf("| %8.4g %8.2f ",
                                  errts, 100.0 * errts / varYts);
        Rprintf("|\n");
    }
    mse[j] = errb;
    if (*labelts) msets[j] = errts;

It should not be particularly difficult to trim that code to the point where it is only emitting the hundredth tree notification in a form you desire.