Force mutual information methods to be at least 0
There were cases where a tiny negative number was returned (less than -1e-7) Fix mst glass test that is affected with this change
This commit is contained in:
@@ -155,7 +155,7 @@ namespace bayesnet {
|
||||
}
|
||||
}
|
||||
if (pairSelection.size() > 0) {
|
||||
notes.push_back("Used pairs not used in train: " + std::to_string(pairSelection.size()));
|
||||
notes.push_back("Pairs not used in train: " + std::to_string(pairSelection.size()));
|
||||
status = WARNING;
|
||||
}
|
||||
notes.push_back("Number of models: " + std::to_string(n_models));
|
||||
|
@@ -198,24 +198,20 @@ namespace bayesnet {
|
||||
}
|
||||
return entropyValue;
|
||||
}
|
||||
// H(Y|X,C) = sum_{x in X, c in C} p(x,c) H(Y|X=x,C=c)
|
||||
// H(X|Y,C) = sum_{y in Y, c in C} p(x,c) H(X|Y=y,C=c)
|
||||
double Metrics::conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& labels, const torch::Tensor& weights)
|
||||
{
|
||||
// Ensure the tensors are of the same length
|
||||
assert(firstFeature.size(0) == secondFeature.size(0) && firstFeature.size(0) == labels.size(0) && firstFeature.size(0) == weights.size(0));
|
||||
|
||||
// Convert tensors to vectors for easier processing
|
||||
auto firstFeatureData = firstFeature.accessor<int, 1>();
|
||||
auto secondFeatureData = secondFeature.accessor<int, 1>();
|
||||
auto labelsData = labels.accessor<int, 1>();
|
||||
auto weightsData = weights.accessor<double, 1>();
|
||||
|
||||
int numSamples = firstFeature.size(0);
|
||||
|
||||
// Maps for joint and marginal probabilities
|
||||
std::map<std::tuple<int, int, int>, double> jointCount;
|
||||
std::map<std::tuple<int, int>, double> marginalCount;
|
||||
|
||||
// Compute joint and marginal counts
|
||||
for (int i = 0; i < numSamples; ++i) {
|
||||
auto keyJoint = std::make_tuple(firstFeatureData[i], labelsData[i], secondFeatureData[i]);
|
||||
@@ -224,34 +220,29 @@ namespace bayesnet {
|
||||
jointCount[keyJoint] += weightsData[i];
|
||||
marginalCount[keyMarginal] += weightsData[i];
|
||||
}
|
||||
|
||||
// Total weight sum
|
||||
double totalWeight = torch::sum(weights).item<double>();
|
||||
if (totalWeight == 0)
|
||||
return 0;
|
||||
|
||||
// Compute the conditional entropy
|
||||
double conditionalEntropy = 0.0;
|
||||
|
||||
for (const auto& [keyJoint, jointFreq] : jointCount) {
|
||||
auto [x, c, y] = keyJoint;
|
||||
auto keyMarginal = std::make_tuple(x, c);
|
||||
|
||||
//double p_xc = marginalCount[keyMarginal] / totalWeight;
|
||||
double p_y_given_xc = jointFreq / marginalCount[keyMarginal];
|
||||
|
||||
if (p_y_given_xc > 0) {
|
||||
conditionalEntropy -= (jointFreq / totalWeight) * std::log(p_y_given_xc);
|
||||
}
|
||||
}
|
||||
return conditionalEntropy;
|
||||
}
|
||||
// I(X;Y) = H(Y) - H(Y|X)
|
||||
// I(X;Y) = H(Y) - H(Y|X) ; I(X;Y) >= 0
|
||||
double Metrics::mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights)
|
||||
{
|
||||
return entropy(firstFeature, weights) - conditionalEntropy(firstFeature, secondFeature, weights);
|
||||
return std::max(entropy(firstFeature, weights) - conditionalEntropy(firstFeature, secondFeature, weights), 0.0);
|
||||
}
|
||||
// I(X;Y|C) = H(Y|C) - H(Y|X,C)
|
||||
// I(X;Y|C) = H(X|C) - H(X|Y,C) >= 0
|
||||
double Metrics::conditionalMutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& labels, const torch::Tensor& weights)
|
||||
{
|
||||
return std::max(conditionalEntropy(firstFeature, labels, weights) - conditionalEntropy(firstFeature, secondFeature, labels, weights), 0.0);
|
||||
|
Reference in New Issue
Block a user