Displaying 2 results from an estimated 2 matches for "giniinit".
Did you mean:
gic_init
2002 Jan 25
0
rpart subsets
...(i=0; i<numclass; i++) {
if (freq[i] == 0) freq[i] = 0.00000000001;
}
#endif
for (i=0; i<numclass; i++) {
prior[i] /= freq[i];
aprior[i] /= (temp * freq[i]); /* pi_i / n_i */
}
}
The calculation of the priors (existing code) above shows where I put the
fix in giniinit (in gini.c). However, at this point the rpart run will
complete but will have many NaN's in the rpart$frame for yval's. This is
because of an oversight in rpart.s when calculating the probabilities for
each node. The change to the function rpart in rpart.s is:
if (method.int ==3 ) {...
2002 Jan 28
0
rpart subset fix
...(i=0; i<numclass; i++) {
if (freq[i] == 0) freq[i] = 0.00000000001;
}
#endif
for (i=0; i<numclass; i++) {
prior[i] /= freq[i];
aprior[i] /= (temp * freq[i]); /* pi_i / n_i */
}
}
The calculation of the priors (existing code) above shows where I put the
fix in giniinit (in gini.c). However, at this point the rpart run will
complete but will have many NaN's in the rpart$frame for yval's. This is
because of an oversight in rpart.s when calculating the probabilities for
each node. The change to the function rpart in rpart.s is:
if (method.int ==3 ) {...