rmontanana/mdlp
1
1
Fork 0
mirror of https://github.com/rmontanana/mdlp.git synced 2025-08-16 07:55:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove unneeded loop in sortIndices

Browse Source 
Add some static casts
This commit is contained in:
Ricardo Montañana Gómez
2023-03-19 19:13:37 +01:00
parent f0845c5bd1
commit cfade7a556
9 changed files with 210 additions and 146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
CPPFImdlp.cpp
View File

@@ -5,20 +5,22 @@
#include <limits>
#include "CPPFImdlp.h"
#include "Metrics.h"
namespace mdlp {
CPPFImdlp::CPPFImdlp(size_t min_length_, int max_depth_, float proposed): min_length(min_length_),
max_depth(max_depth_), proposed_cuts(proposed)
{
CPPFImdlp::CPPFImdlp(size_t min_length_, int max_depth_, float proposed) : min_length(min_length_),
max_depth(max_depth_),
proposed_cuts(proposed) {
}
CPPFImdlp::CPPFImdlp() = default;
CPPFImdlp::~CPPFImdlp() = default;
size_t CPPFImdlp::compute_max_num_cut_points() const
{
size_t CPPFImdlp::compute_max_num_cut_points() const {
// Set the actual maximum number of cut points as a number or as a percentage of the number of samples
if (proposed_cuts == 0) {
return numeric_limits<size_t>::max();
return numeric_limits<size_t>::max();
}
if (proposed_cuts < 0 || proposed_cuts > static_cast<float>(X.size())) {
throw invalid_argument("wrong proposed num_cuts value");
@@ -28,8 +30,7 @@ namespace mdlp {
return static_cast<size_t>(proposed_cuts);
}
void CPPFImdlp::fit(samples_t& X_, labels_t& y_)
{
void CPPFImdlp::fit(samples_t &X_, labels_t &y_) {
X = X_;
y = y_;
num_cut_points = compute_max_num_cut_points();
@@ -52,12 +53,15 @@ namespace mdlp {
computeCutPoints(0, X.size(), 1);
}
pair<precision_t, size_t> CPPFImdlp::valueCutPoint(size_t start, size_t cut, size_t end)
{
size_t n, m, idxPrev = cut - 1 >= start ? cut - 1 : cut;
pair<precision_t, size_t> CPPFImdlp::valueCutPoint(size_t start, size_t cut, size_t end) {
size_t n;
size_t m;
size_t idxPrev = cut - 1 >= start ? cut - 1 : cut;
size_t idxNext = cut + 1 < end ? cut + 1 : cut;
bool backWall; // true if duplicates reach begining of the interval
precision_t previous, actual, next;
precision_t previous;
precision_t actual;
precision_t next;
previous = X[indices[idxPrev]];
actual = X[indices[cut]];
next = X[indices[idxNext]];
@@ -78,11 +82,10 @@ namespace mdlp {
// Decide which values to use
cut = cut + (backWall ? m + 1 : -n);
actual = X[indices[cut]];
return { (actual + previous) / 2, cut };
return {(actual + previous) / 2, cut};
}
void CPPFImdlp::computeCutPoints(size_t start, size_t end, int depth_)
{
void CPPFImdlp::computeCutPoints(size_t start, size_t end, int depth_) {
size_t cut;
pair<precision_t, size_t> result;
if (cutPoints.size() == num_cut_points)
@@ -103,13 +106,15 @@ namespace mdlp {
}
}
size_t CPPFImdlp::getCandidate(size_t start, size_t end)
{
size_t CPPFImdlp::getCandidate(size_t start, size_t end) {
/* Definition 1: A binary discretization for A is determined by selecting the cut point TA for which
E(A, TA; S) is minimal amongst all the candidate cut points. */
size_t candidate = numeric_limits<size_t>::max(), elements = end - start;
size_t candidate = numeric_limits<size_t>::max();
size_t elements = end - start;
bool sameValues = true;
precision_t entropy_left, entropy_right, minEntropy;
precision_t entropy_left;
precision_t entropy_right;
precision_t minEntropy;
// Check if all the values of the variable in the interval are the same
for (size_t idx = start + 1; idx < end; idx++) {
if (X[indices[idx]] != X[indices[start]]) {
@@ -134,11 +139,15 @@ namespace mdlp {
return candidate;
}
bool CPPFImdlp::mdlp(size_t start, size_t cut, size_t end)
{
int k, k1, k2;
precision_t ig, delta;
precision_t ent, ent1, ent2;
bool CPPFImdlp::mdlp(size_t start, size_t cut, size_t end) {
int k;
int k1;
int k2;
precision_t ig;
precision_t delta;
precision_t ent;
precision_t ent1;
precision_t ent2;
auto N = precision_t(end - start);
k = metrics.computeNumClasses(start, end);
k1 = metrics.computeNumClasses(start, cut);
@@ -148,33 +157,30 @@ namespace mdlp {
ent2 = metrics.entropy(cut, end);
ig = metrics.informationGain(start, cut, end);
delta = static_cast<float>(log2(pow(3, precision_t(k)) - 2) -
(precision_t(k) * ent - precision_t(k1) * ent1 - precision_t(k2) * ent2));
(precision_t(k) * ent - precision_t(k1) * ent1 - precision_t(k2) * ent2));
precision_t term = 1 / N * (log2(N - 1) + delta);
return ig > term;
}
// Argsort from https://stackoverflow.com/questions/1577475/c-sorting-and-keeping-track-of-indexes
indices_t CPPFImdlp::sortIndices(samples_t& X_, labels_t& y_)
{
indices_t CPPFImdlp::sortIndices(samples_t &X_, labels_t &y_) {
indices_t idx(X_.size());
iota(idx.begin(), idx.end(), 0);
for (size_t i = 0; i < X_.size(); i++)
stable_sort(idx.begin(), idx.end(), [&X_, &y_](size_t i1, size_t i2) {
stable_sort(idx.begin(), idx.end(), [&X_, &y_](size_t i1, size_t i2) {
if (X_[i1] == X_[i2])
return y_[i1] < y_[i2];
else
return X_[i1] < X_[i2];
});
});
return idx;
}
cutPoints_t CPPFImdlp::getCutPoints()
{
cutPoints_t CPPFImdlp::getCutPoints() {
sort(cutPoints.begin(), cutPoints.end());
return cutPoints;
}
int CPPFImdlp::get_depth() const
{
int CPPFImdlp::get_depth() const {
return depth;
}
}