26 KiB
26 KiB
<html lang="en">
<head>
</head>
</html>
| LCOV - code coverage report | |||||||||||||||||||||||||
 | |||||||||||||||||||||||||
|
|||||||||||||||||||||||||
|
Line data Source code 1 : // *************************************************************** 2 : // SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez 3 : // SPDX-FileType: SOURCE 4 : // SPDX-License-Identifier: MIT 5 : // *************************************************************** 6 : 7 : #include "Mst.h" 8 : #include "BayesMetrics.h" 9 : namespace bayesnet { 10 : //samples is n+1xm tensor used to fit the model 11 2123 : Metrics::Metrics(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int classNumStates) 12 2123 : : samples(samples) 13 2123 : , className(className) 14 2123 : , features(features) 15 2123 : , classNumStates(classNumStates) 16 : { 17 2123 : } 18 : //samples is n+1xm std::vector used to fit the model 19 96 : Metrics::Metrics(const std::vector<std::vector<int>>& vsamples, const std::vector<int>& labels, const std::vector<std::string>& features, const std::string& className, const int classNumStates) 20 96 : : samples(torch::zeros({ static_cast<int>(vsamples.size() + 1), static_cast<int>(vsamples[0].size()) }, torch::kInt32)) 21 96 : , className(className) 22 96 : , features(features) 23 96 : , classNumStates(classNumStates) 24 : { 25 768 : for (int i = 0; i < vsamples.size(); ++i) { 26 2688 : samples.index_put_({ i, "..." }, torch::tensor(vsamples[i], torch::kInt32)); 27 : } 28 384 : samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32)); 29 864 : } 30 478 : std::vector<int> Metrics::SelectKBestWeighted(const torch::Tensor& weights, bool ascending, unsigned k) 31 : { 32 : // Return the K Best features 33 478 : auto n = features.size(); 34 478 : if (k == 0) { 35 6 : k = n; 36 : } 37 : // compute scores 38 478 : scoresKBest.clear(); 39 478 : featuresKBest.clear(); 40 1434 : auto label = samples.index({ -1, "..." }); 41 10522 : for (int i = 0; i < n; ++i) { 42 30132 : scoresKBest.push_back(mutualInformation(label, samples.index({ i, "..." }), weights)); 43 10044 : featuresKBest.push_back(i); 44 : } 45 : // sort & reduce scores and features 46 478 : if (ascending) { 47 94 : sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j) 48 2088 : { return scoresKBest[i] < scoresKBest[j]; }); 49 94 : sort(scoresKBest.begin(), scoresKBest.end(), std::less<double>()); 50 94 : if (k < n) { 51 154 : for (int i = 0; i < n - k; ++i) { 52 110 : featuresKBest.erase(featuresKBest.begin()); 53 110 : scoresKBest.erase(scoresKBest.begin()); 54 : } 55 : } 56 : } else { 57 384 : sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j) 58 64808 : { return scoresKBest[i] > scoresKBest[j]; }); 59 384 : sort(scoresKBest.begin(), scoresKBest.end(), std::greater<double>()); 60 384 : featuresKBest.resize(k); 61 384 : scoresKBest.resize(k); 62 : } 63 956 : return featuresKBest; 64 11000 : } 65 48 : std::vector<double> Metrics::getScoresKBest() const 66 : { 67 48 : return scoresKBest; 68 : } 69 : 70 152 : torch::Tensor Metrics::conditionalEdge(const torch::Tensor& weights) 71 : { 72 152 : auto result = std::vector<double>(); 73 152 : auto source = std::vector<std::string>(features); 74 152 : source.push_back(className); 75 152 : auto combinations = doCombinations(source); 76 : // Compute class prior 77 152 : auto margin = torch::zeros({ classNumStates }, torch::kFloat); 78 828 : for (int value = 0; value < classNumStates; ++value) { 79 2704 : auto mask = samples.index({ -1, "..." }) == value; 80 676 : margin[value] = mask.sum().item<double>() / samples.size(1); 81 676 : } 82 4164 : for (auto [first, second] : combinations) { 83 4012 : int index_first = find(features.begin(), features.end(), first) - features.begin(); 84 4012 : int index_second = find(features.begin(), features.end(), second) - features.begin(); 85 4012 : double accumulated = 0; 86 23820 : for (int value = 0; value < classNumStates; ++value) { 87 79232 : auto mask = samples.index({ -1, "..." }) == value; 88 59424 : auto first_dataset = samples.index({ index_first, mask }); 89 59424 : auto second_dataset = samples.index({ index_second, mask }); 90 39616 : auto weights_dataset = weights.index({ mask }); 91 39616 : auto mi = mutualInformation(first_dataset, second_dataset, weights_dataset); 92 19808 : auto pb = margin[value].item<double>(); 93 19808 : accumulated += pb * mi; 94 19808 : } 95 4012 : result.push_back(accumulated); 96 4012 : } 97 152 : long n_vars = source.size(); 98 152 : auto matrix = torch::zeros({ n_vars, n_vars }); 99 152 : auto indices = torch::triu_indices(n_vars, n_vars, 1); 100 4164 : for (auto i = 0; i < result.size(); ++i) { 101 4012 : auto x = indices[0][i]; 102 4012 : auto y = indices[1][i]; 103 4012 : matrix[x][y] = result[i]; 104 4012 : matrix[y][x] = result[i]; 105 4012 : } 106 304 : return matrix; 107 99868 : } 108 41732 : double Metrics::entropy(const torch::Tensor& feature, const torch::Tensor& weights) 109 : { 110 41732 : torch::Tensor counts = feature.bincount(weights); 111 41732 : double totalWeight = counts.sum().item<double>(); 112 41732 : torch::Tensor probs = counts.to(torch::kFloat) / totalWeight; 113 41732 : torch::Tensor logProbs = torch::log(probs); 114 41732 : torch::Tensor entropy = -probs * logProbs; 115 83464 : return entropy.nansum().item<double>(); 116 41732 : } 117 : // H(Y|X) = sum_{x in X} p(x) H(Y|X=x) 118 34276 : double Metrics::conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights) 119 : { 120 34276 : int numSamples = firstFeature.sizes()[0]; 121 34276 : torch::Tensor featureCounts = secondFeature.bincount(weights); 122 34276 : std::unordered_map<int, std::unordered_map<int, double>> jointCounts; 123 34276 : double totalWeight = 0; 124 6993324 : for (auto i = 0; i < numSamples; i++) { 125 6959048 : jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += weights[i].item<double>(); 126 6959048 : totalWeight += weights[i].item<float>(); 127 : } 128 34276 : if (totalWeight == 0) 129 0 : return 0; 130 34276 : double entropyValue = 0; 131 168251 : for (int value = 0; value < featureCounts.sizes()[0]; ++value) { 132 133975 : double p_f = featureCounts[value].item<double>() / totalWeight; 133 133975 : double entropy_f = 0; 134 454356 : for (auto& [label, jointCount] : jointCounts[value]) { 135 320381 : double p_l_f = jointCount / featureCounts[value].item<double>(); 136 320381 : if (p_l_f > 0) { 137 320381 : entropy_f -= p_l_f * log(p_l_f); 138 : } else { 139 0 : entropy_f = 0; 140 : } 141 : } 142 133975 : entropyValue += p_f * entropy_f; 143 : } 144 34276 : return entropyValue; 145 34276 : } 146 : // I(X;Y) = H(Y) - H(Y|X) 147 34276 : double Metrics::mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights) 148 : { 149 34276 : return entropy(firstFeature, weights) - conditionalEntropy(firstFeature, secondFeature, weights); 150 : } 151 : /* 152 : Compute the maximum spanning tree considering the weights as distances 153 : and the indices of the weights as nodes of this square matrix using 154 : Kruskal algorithm 155 : */ 156 148 : std::vector<std::pair<int, int>> Metrics::maximumSpanningTree(const std::vector<std::string>& features, const torch::Tensor& weights, const int root) 157 : { 158 148 : auto mst = MST(features, weights, root); 159 296 : return mst.maximumSpanningTree(); 160 148 : } 161 : } |
|
| Generated by: LCOV version 2.0-1 |
</html>