virtual void reset_data_for_test(const AzOut &out,
const AzSmat *m_data) {
bool doSparse = false;
if (m_data->rowNum()*m_data->colNum() > Az_max_test_entries) { /* large data */
/*--- dense is faster but uses up more memory if data is sparse ---*/
double nz_ratio;
m_data->nonZeroNum(&nz_ratio);
if (nz_ratio < 0.6) { /* relatively sparse */
doSparse = true;
AzBytArr s; s.c("Large and sparse test data (nonzero ratio=", nz_ratio);
s.c("); treated as sparse data.");
AzPrint::writeln(out, s);
}
}
data_num = m_data->colNum();
m_tran_dense.reset();
m_tran_sparse.reset();
if (doSparse) {
m_data->transpose(&m_tran_sparse);
}
else {
m_tran_dense.transpose_from(m_data);
}
sorted_arr.reset();
feat.reset(m_data->rowNum());
}
virtual void reset_data(const AzOut &out,
const AzSmat *m_data,
AzParam &p,
bool beTight,
const AzSvFeatInfo *inp_feat=NULL)
{
resetParam(p);
printParam(out);
/*--- count nonzero components ---*/
double nz_ratio;
m_data->nonZeroNum(&nz_ratio);
AzBytArr s("Training data: ");
s.cn(m_data->rowNum());s.c("x");s.cn(m_data->colNum());
s.c(", nonzero_ratio=", nz_ratio, 4);
/*--- decide sparse or dense ---*/
AzBytArr s_dp("; managed as dense data");
bool doSparse = false;
if (dataproc == dataproc_Auto &&
nz_ratio < Az_nz_ratio_threshold ||
dataproc == dataproc_Sparse) {
doSparse = true;
s_dp.reset("; managed as sparse data");
}
if (dataproc != dataproc_Auto) s_dp.concat(" as requested.");
else s_dp.concat(".");
AzPrint::writeln(out, "-------------");
AzPrint::writeln(out, s, s_dp);
AzPrint::writeln(out, "-------------");
/*--- pre-sort data ---*/
m_tran_sparse.reset();
m_tran_dense.unlock();
m_tran_dense.reset();
data_num = m_data->colNum();
if (doSparse) {
m_data->transpose(&m_tran_sparse);
sorted_arr.reset_sparse(&m_tran_sparse, beTight);
}
else {
m_tran_dense.transpose_from(m_data);
sorted_arr.reset_dense(&m_tran_dense, beTight);
/* prohibit any action to change the pointers to the column vectors */
m_tran_dense.lock();
}
if (inp_feat != NULL) {
feat.reset(inp_feat);
if (feat.featNum() != m_data->rowNum()) {
throw new AzException(AzInputError, "AzDataForTrTree::reset", "#feat mismatch");
}
}
else {
feat.reset(m_data->rowNum());
}
}
