Structure learning is running.
Forwarding to the network diagram when done…
If the diagram does not open, click here.
%s;\n",$ii,$j);
}
//fprintf($fouttemp,"%s -> %s;\n",$row_name,$col_name);
}
}
}
if ($fout !== false) {
fwrite($fout,"$endstring");
fclose($fout);
}
runTerminalCommand([realpath(__DIR__.'/run_scripts/run_octave'), $keyval]);
} catch (Exception $e) {
$bnw_error = $e->getMessage();
}
if(!is_null($bnw_error))
{
// Structure learning failed: show it on the status page instead of
// a blank fatal error page with no forward.
$bnw_hint = "";
// Plain-English hints for the recurring octave failure modes
if (preg_match("/toposort|sources\\(0\\)/", $bnw_error)
|| preg_match("/subscripts must be .* integers/", $bnw_error))
$bnw_hint = "Hint: the learned network could not be laid out. This can happen when variables are identical or mirror each other (e.g. the same trait measured repeatedly), which produces a network that cannot be drawn as a directed graph. Try removing duplicate/similar variables or changing the structure learning settings.";
elseif (preg_match("/out of memory|memory exhausted/i", $bnw_error))
$bnw_hint = "Hint: the data set is too large for the available memory. Remove variables or use fewer samples.";
elseif (preg_match("/Could not open .* for input/", $bnw_error))
$bnw_hint = "Hint: the data preparation step did not produce the expected files. Check that the data is complete and try again.";
?>