mirror of
https://github.com/Doctorado-ML/FImdlp.git
synced 2025-08-17 16:35:52 +00:00
Fix entropy and information gain
This commit is contained in:
@@ -18,14 +18,16 @@ namespace CPPFImdlp
|
||||
std::vector<float> CPPFImdlp::cutPoints(std::vector<float> &X, std::vector<int> &y)
|
||||
{
|
||||
std::vector<float> cutPts;
|
||||
std::vector<int> cutIdx;
|
||||
float xPrev, cutPoint;
|
||||
int yPrev;
|
||||
int yPrev, idxPrev;
|
||||
std::vector<size_t> indices = sortIndices(X);
|
||||
xPrev = X.at(indices[0]);
|
||||
yPrev = y.at(indices[0]);
|
||||
idxPrev = indices[0];
|
||||
if (debug)
|
||||
{
|
||||
std::cout << "Entropy: " << Metrics::entropy(y, 0, y.size(), Metrics::numClasses(y)) << std::endl;
|
||||
std::cout << "Entropy: " << Metrics::entropy(y, indices, 0, y.size(), Metrics::numClasses(y, indices, 0, indices.size())) << std::endl;
|
||||
}
|
||||
for (auto index = indices.begin(); index != indices.end(); ++index)
|
||||
{
|
||||
@@ -37,12 +39,23 @@ namespace CPPFImdlp
|
||||
{
|
||||
std::cout << "Cut point: " << (xPrev + X.at(*index)) / 2 << " //";
|
||||
std::cout << X.at(*index) << " -> " << y.at(*index) << " yPrev= " << yPrev;
|
||||
std::cout << "* (" << X.at(*index) << ", " << xPrev << ")=" << ((X.at(*index) + xPrev) / 2) << std::endl;
|
||||
std::cout << "* (" << X.at(*index) << ", " << xPrev << ")="
|
||||
<< ((X.at(*index) + xPrev) / 2) << "idxPrev"
|
||||
<< idxPrev << std::endl;
|
||||
}
|
||||
cutPts.push_back(cutPoint);
|
||||
cutIdx.push_back(idxPrev);
|
||||
}
|
||||
xPrev = X.at(*index);
|
||||
yPrev = y.at(*index);
|
||||
idxPrev = *index;
|
||||
}
|
||||
std::cout << "Information Gain:" << std::endl;
|
||||
auto nc = Metrics::numClasses(y, indices, 0, indices.size());
|
||||
for (auto cutPoint = cutIdx.begin(); cutPoint != cutIdx.end(); ++cutPoint)
|
||||
{
|
||||
std::cout << *cutPoint << " -> " << Metrics::informationGain(y, indices, 0, indices.size(), *cutPoint, nc) << std::endl;
|
||||
// << Metrics::informationGain(y, 0, y.size(), *cutPoint, Metrics::numClasses(y, 0, y.size())) << std::endl;
|
||||
}
|
||||
return cutPts;
|
||||
}
|
||||
|
@@ -4,15 +4,29 @@ namespace CPPFImdlp
|
||||
Metrics::Metrics()
|
||||
{
|
||||
}
|
||||
float Metrics::entropy(std::vector<int> &y, int start, int end, int nClasses)
|
||||
int Metrics::numClasses(std::vector<int> &y, std::vector<size_t> indices, int start, int end)
|
||||
{
|
||||
int nClasses = 1;
|
||||
int yAnt = y.at(start);
|
||||
for (auto i = start; i < end; ++i)
|
||||
{
|
||||
if (y.at(i) != yAnt)
|
||||
{
|
||||
nClasses++;
|
||||
yAnt = y.at(i);
|
||||
}
|
||||
}
|
||||
return nClasses;
|
||||
}
|
||||
float Metrics::entropy(std::vector<int> &y, std::vector<size_t> &indices, int start, int end, int nClasses)
|
||||
{
|
||||
float entropy = 0;
|
||||
int nElements = end - start;
|
||||
std::vector<int>
|
||||
counts(nClasses, 0);
|
||||
for (auto i = start; i < end; i++)
|
||||
int nElements = 0;
|
||||
std::vector<int> counts(nClasses, 0);
|
||||
for (auto i = &indices[start]; i != &indices[end]; ++i)
|
||||
{
|
||||
counts[y[i]]++;
|
||||
counts[y[*i]]++;
|
||||
nElements++;
|
||||
}
|
||||
for (auto i = 0; i < nClasses; i++)
|
||||
{
|
||||
@@ -24,17 +38,20 @@ namespace CPPFImdlp
|
||||
}
|
||||
return entropy;
|
||||
}
|
||||
int Metrics::numClasses(std::vector<int> &y)
|
||||
float Metrics::informationGain(std::vector<int> &y, std::vector<size_t> &indices, int start, int end, int cutPoint, int nClasses)
|
||||
{
|
||||
int nClasses = 1;
|
||||
int yAnt = y.at(0);
|
||||
for (auto i = y.begin(); i != y.end(); ++i)
|
||||
{
|
||||
if (*i != yAnt)
|
||||
{
|
||||
nClasses++;
|
||||
}
|
||||
}
|
||||
return nClasses;
|
||||
float iGain = 0.0;
|
||||
float entropy, entropyLeft, entropyRight;
|
||||
int nClassesLeft, nClassesRight;
|
||||
int nElementsLeft = cutPoint - start, nElementsRight = end - cutPoint;
|
||||
int nElements = end - start;
|
||||
nClassesLeft = Metrics::numClasses(y, indices, start, cutPoint);
|
||||
nClassesRight = Metrics::numClasses(y, indices, cutPoint, end);
|
||||
entropy = Metrics::entropy(y, indices, start, end, nClasses);
|
||||
entropyLeft = Metrics::entropy(y, indices, start, cutPoint, nClassesLeft);
|
||||
entropyRight = Metrics::entropy(y, indices, cutPoint, end, nClassesRight);
|
||||
iGain = entropy - (float)nElementsLeft / nElements * entropyLeft - (float)nElementsRight / nElements * entropyRight;
|
||||
return iGain;
|
||||
}
|
||||
|
||||
}
|
||||
|
@@ -9,8 +9,9 @@ namespace CPPFImdlp
|
||||
{
|
||||
public:
|
||||
Metrics();
|
||||
static float entropy(std::vector<int> &, int, int, int);
|
||||
static int numClasses(std::vector<int> &);
|
||||
static int numClasses(std::vector<int> &, std::vector<size_t>, int, int);
|
||||
static float entropy(std::vector<int> &, std::vector<size_t> &, int, int, int);
|
||||
static float informationGain(std::vector<int> &y, std::vector<size_t> &indices, int start, int end, int cutPoint, int nClasses);
|
||||
};
|
||||
}
|
||||
#endif
|
Binary file not shown.
Reference in New Issue
Block a user