commit inicial

bayesnet/utils/BayesMetrics.cc

@@ -0,0 +1,260 @@
+// ***************************************************************
+// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
+// SPDX-FileType: SOURCE
+// SPDX-License-Identifier: MIT
+// ***************************************************************
+
+#include <map>
+#include <unordered_map>
+#include <tuple>
+#include "Mst.h"
+#include "BayesMetrics.h"
+namespace bayesnet {
+    //samples is n+1xm tensor used to fit the model
+    Metrics::Metrics(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int classNumStates)
+        : samples(samples)
+        , className(className)
+        , features(features)
+        , classNumStates(classNumStates)
+    {
+    }
+    //samples is n+1xm std::vector used to fit the model
+    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)
+        : samples(torch::zeros({ static_cast<int>(vsamples.size() + 1), static_cast<int>(vsamples[0].size()) }, torch::kInt32))
+        , className(className)
+        , features(features)
+        , classNumStates(classNumStates)
+    {
+        for (int i = 0; i < vsamples.size(); ++i) {
+            samples.index_put_({ i,  "..." }, torch::tensor(vsamples[i], torch::kInt32));
+        }
+        samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
+    }
+    std::vector<std::pair<int, int>> Metrics::SelectKPairs(const torch::Tensor& weights, std::vector<int>& featuresExcluded, bool ascending, unsigned k)
+    {
+        // Return the K Best features 
+        auto n = features.size();
+        // compute scores
+        scoresKPairs.clear();
+        pairsKBest.clear();
+        auto labels = samples.index({ -1, "..." });
+        for (int i = 0; i < n - 1; ++i) {
+            if (std::find(featuresExcluded.begin(), featuresExcluded.end(), i) != featuresExcluded.end()) {
+                continue;
+            }
+            for (int j = i + 1; j < n; ++j) {
+                if (std::find(featuresExcluded.begin(), featuresExcluded.end(), j) != featuresExcluded.end()) {
+                    continue;
+                }
+                auto key = std::make_pair(i, j);
+                auto value = conditionalMutualInformation(samples.index({ i, "..." }), samples.index({ j, "..." }), labels, weights);
+                scoresKPairs.push_back({ key, value });
+            }
+        }
+        // sort scores
+        if (ascending) {
+            sort(scoresKPairs.begin(), scoresKPairs.end(), [](auto& a, auto& b)
+                { return a.second < b.second; });
+
+        } else {
+            sort(scoresKPairs.begin(), scoresKPairs.end(), [](auto& a, auto& b)
+                { return a.second > b.second; });
+        }
+        for (auto& [pairs, score] : scoresKPairs) {
+            pairsKBest.push_back(pairs);
+        }
+        if (k != 0 && k < pairsKBest.size()) {
+            if (ascending) {
+                int limit = pairsKBest.size() - k;
+                for (int i = 0; i < limit; i++) {
+                    pairsKBest.erase(pairsKBest.begin());
+                    scoresKPairs.erase(scoresKPairs.begin());
+                }
+            } else {
+                pairsKBest.resize(k);
+                scoresKPairs.resize(k);
+            }
+        }
+        return pairsKBest;
+    }
+    std::vector<int> Metrics::SelectKBestWeighted(const torch::Tensor& weights, bool ascending, unsigned k)
+    {
+        // Return the K Best features 
+        auto n = features.size();
+        if (k == 0) {
+            k = n;
+        }
+        // compute scores
+        scoresKBest.clear();
+        featuresKBest.clear();
+        auto label = samples.index({ -1, "..." });
+        for (int i = 0; i < n; ++i) {
+            scoresKBest.push_back(mutualInformation(label, samples.index({ i, "..." }), weights));
+            featuresKBest.push_back(i);
+        }
+        // sort & reduce scores and features
+        if (ascending) {
+            sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
+                { return scoresKBest[i] < scoresKBest[j]; });
+            sort(scoresKBest.begin(), scoresKBest.end(), std::less<double>());
+            if (k < n) {
+                for (int i = 0; i < n - k; ++i) {
+                    featuresKBest.erase(featuresKBest.begin());
+                    scoresKBest.erase(scoresKBest.begin());
+                }
+            }
+        } else {
+            sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
+                { return scoresKBest[i] > scoresKBest[j]; });
+            sort(scoresKBest.begin(), scoresKBest.end(), std::greater<double>());
+            featuresKBest.resize(k);
+            scoresKBest.resize(k);
+        }
+        return featuresKBest;
+    }
+    std::vector<double> Metrics::getScoresKBest() const
+    {
+        return scoresKBest;
+    }
+    std::vector<std::pair<std::pair<int, int>, double>> Metrics::getScoresKPairs() const
+    {
+        return scoresKPairs;
+    }
+    torch::Tensor Metrics::conditionalEdge(const torch::Tensor& weights)
+    {
+        auto result = std::vector<double>();
+        auto source = std::vector<std::string>(features);
+        source.push_back(className);
+        auto combinations = doCombinations(source);
+        // Compute class prior
+        auto margin = torch::zeros({ classNumStates }, torch::kFloat);
+        for (int value = 0; value < classNumStates; ++value) {
+            auto mask = samples.index({ -1,  "..." }) == value;
+            margin[value] = mask.sum().item<double>() / samples.size(1);
+        }
+        for (auto [first, second] : combinations) {
+            int index_first = find(features.begin(), features.end(), first) - features.begin();
+            int index_second = find(features.begin(), features.end(), second) - features.begin();
+            double accumulated = 0;
+            for (int value = 0; value < classNumStates; ++value) {
+                auto mask = samples.index({ -1, "..." }) == value;
+                auto first_dataset = samples.index({ index_first, mask });
+                auto second_dataset = samples.index({ index_second, mask });
+                auto weights_dataset = weights.index({ mask });
+                auto mi = mutualInformation(first_dataset, second_dataset, weights_dataset);
+                auto pb = margin[value].item<double>();
+                accumulated += pb * mi;
+            }
+            result.push_back(accumulated);
+        }
+        long n_vars = source.size();
+        auto matrix = torch::zeros({ n_vars, n_vars });
+        auto indices = torch::triu_indices(n_vars, n_vars, 1);
+        for (auto i = 0; i < result.size(); ++i) {
+            auto x = indices[0][i];
+            auto y = indices[1][i];
+            matrix[x][y] = result[i];
+            matrix[y][x] = result[i];
+        }
+        return matrix;
+    }
+    // Measured in nats (natural logarithm (log) base e)
+    // Elements of Information Theory, 2nd Edition, Thomas M. Cover, Joy A. Thomas p. 14
+    double Metrics::entropy(const torch::Tensor& feature, const torch::Tensor& weights)
+    {
+        torch::Tensor counts = feature.bincount(weights);
+        double totalWeight = counts.sum().item<double>();
+        torch::Tensor probs = counts.to(torch::kFloat) / totalWeight;
+        torch::Tensor logProbs = torch::log(probs);
+        torch::Tensor entropy = -probs * logProbs;
+        return entropy.nansum().item<double>();
+    }
+    // H(Y|X) = sum_{x in X} p(x) H(Y|X=x)
+    double Metrics::conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights)
+    {
+        int numSamples = firstFeature.sizes()[0];
+        torch::Tensor featureCounts = secondFeature.bincount(weights);
+        std::unordered_map<int, std::unordered_map<int, double>> jointCounts;
+        double totalWeight = 0;
+        for (auto i = 0; i < numSamples; i++) {
+            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += weights[i].item<double>();
+            totalWeight += weights[i].item<float>();
+        }
+        if (totalWeight == 0)
+            return 0;
+        double entropyValue = 0;
+        for (int value = 0; value < featureCounts.sizes()[0]; ++value) {
+            double p_f = featureCounts[value].item<double>() / totalWeight;
+            double entropy_f = 0;
+            for (auto& [label, jointCount] : jointCounts[value]) {
+                double p_l_f = jointCount / featureCounts[value].item<double>();
+                if (p_l_f > 0) {
+                    entropy_f -= p_l_f * log(p_l_f);
+                } else {
+                    entropy_f = 0;
+                }
+            }
+            entropyValue += p_f * entropy_f;
+        }
+        return entropyValue;
+    }
+    // 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]);
+            auto keyMarginal = std::make_tuple(firstFeatureData[i], labelsData[i]);
+
+            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) >= 0
+    double Metrics::mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights)
+    {
+        return std::max(entropy(firstFeature, weights) - conditionalEntropy(firstFeature, secondFeature, weights), 0.0);
+    }
+    // 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);
+    }
+    /*
+    Compute the maximum spanning tree considering the weights as distances
+    and the indices of the weights as nodes of this square matrix using
+    Kruskal algorithm
+    */
+    std::vector<std::pair<int, int>> Metrics::maximumSpanningTree(const std::vector<std::string>& features, const torch::Tensor& weights, const int root)
+    {
+        auto mst = MST(features, weights, root);
+        return mst.maximumSpanningTree();
+    }
+}

bayesnet/utils/BayesMetrics.h

@@ -0,0 +1,62 @@
+// ***************************************************************
+// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
+// SPDX-FileType: SOURCE
+// SPDX-License-Identifier: MIT
+// ***************************************************************
+
+#ifndef BAYESNET_METRICS_H
+#define BAYESNET_METRICS_H
+#include <vector>
+#include <string>
+#include <torch/torch.h>
+namespace bayesnet {
+    class Metrics {
+    public:
+        Metrics() = default;
+        Metrics(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int classNumStates);
+        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);
+        std::vector<int> SelectKBestWeighted(const torch::Tensor& weights, bool ascending = false, unsigned k = 0);
+        std::vector<std::pair<int, int>> SelectKPairs(const torch::Tensor& weights, std::vector<int>& featuresExcluded, bool ascending = false, unsigned k = 0);
+        std::vector<double> getScoresKBest() const;
+        std::vector<std::pair<std::pair<int, int>, double>> getScoresKPairs() const;
+        double mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights);
+        double conditionalMutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& labels, const torch::Tensor& weights);
+        torch::Tensor conditionalEdge(const torch::Tensor& weights);
+        std::vector<std::pair<int, int>> maximumSpanningTree(const std::vector<std::string>& features, const torch::Tensor& weights, const int root);
+        // Measured in nats (natural logarithm (log) base e)
+        // Elements of Information Theory, 2nd Edition, Thomas M. Cover, Joy A. Thomas p. 14
+        double entropy(const torch::Tensor& feature, const torch::Tensor& weights);
+        double conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& labels, const torch::Tensor& weights);
+    protected:
+        torch::Tensor samples; // n+1xm torch::Tensor used to fit the model where samples[-1] is the y std::vector
+        std::string className;
+        std::vector<std::string> features;
+        template <class T>
+        std::vector<std::pair<T, T>> doCombinations(const std::vector<T>& source)
+        {
+            std::vector<std::pair<T, T>> result;
+            for (int i = 0; i < source.size() - 1; ++i) {
+                T temp = source[i];
+                for (int j = i + 1; j < source.size(); ++j) {
+                    result.push_back({ temp, source[j] });
+                }
+            }
+            return result;
+        }
+        template <class T>
+        T pop_first(std::vector<T>& v)
+        {
+            T temp = v[0];
+            v.erase(v.begin());
+            return temp;
+        }
+    private:
+        int classNumStates = 0;
+        std::vector<double> scoresKBest;
+        std::vector<int> featuresKBest; // sorted indices of the features
+        std::vector<std::pair<int, int>> pairsKBest; // sorted indices of the pairs
+        std::vector<std::pair<std::pair<int, int>, double>> scoresKPairs;
+        double conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights);
+    };
+}
+#endif

bayesnet/utils/CountingSemaphore.h

@@ -0,0 +1,54 @@
+#ifndef COUNTING_SEMAPHORE_H
+#define COUNTING_SEMAPHORE_H
+#include <mutex>
+#include <condition_variable>
+#include <algorithm>
+#include <thread>
+#include <mutex>
+#include <condition_variable>
+#include <thread>
+
+class CountingSemaphore {
+public:
+    static CountingSemaphore& getInstance()
+    {
+        static CountingSemaphore instance;
+        return instance;
+    }
+    // Delete copy constructor and assignment operator
+    CountingSemaphore(const CountingSemaphore&) = delete;
+    CountingSemaphore& operator=(const CountingSemaphore&) = delete;
+    void acquire()
+    {
+        std::unique_lock<std::mutex> lock(mtx_);
+        cv_.wait(lock, [this]() { return count_ > 0; });
+        --count_;
+    }
+    void release()
+    {
+        std::lock_guard<std::mutex> lock(mtx_);
+        ++count_;
+        if (count_ <= max_count_) {
+            cv_.notify_one();
+        }
+    }
+    uint getCount() const
+    {
+        return count_;
+    }
+    uint getMaxCount() const
+    {
+        return max_count_;
+    }
+private:
+    CountingSemaphore()
+        : max_count_(std::max(1u, static_cast<uint>(0.95 * std::thread::hardware_concurrency()))),
+        count_(max_count_)
+    {
+    }
+    std::mutex mtx_;
+    std::condition_variable cv_;
+    const uint max_count_;
+    uint count_;
+};
+#endif

bayesnet/utils/Mst.cc

@@ -0,0 +1,120 @@
+// ***************************************************************
+// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
+// SPDX-FileType: SOURCE
+// SPDX-License-Identifier: MIT
+// ***************************************************************
+
+#include <sstream>
+#include <vector>
+#include <list>
+#include "Mst.h"
+/*
+    Based on the code from https://www.softwaretestinghelp.com/minimum-spanning-tree-tutorial/
+
+*/
+
+namespace bayesnet {
+    Graph::Graph(int V) : V(V), parent(std::vector<int>(V))
+    {
+        for (int i = 0; i < V; i++)
+            parent[i] = i;
+        G.clear();
+        T.clear();
+    }
+    void Graph::addEdge(int u, int v, float wt)
+    {
+        G.push_back({ wt, { u, v } });
+    }
+    int Graph::find_set(int i)
+    {
+        // If i is the parent of itself
+        if (i == parent[i])
+            return i;
+        else
+            //else recursively find the parent of i
+            return find_set(parent[i]);
+    }
+    void Graph::union_set(int u, int v)
+    {
+        parent[u] = parent[v];
+    }
+    void Graph::kruskal_algorithm()
+    {
+        // sort the edges ordered on decreasing weight
+        stable_sort(G.begin(), G.end(), [](const auto& left, const auto& right) {return left.first > right.first;});
+        for (int i = 0; i < G.size(); i++) {
+            int uSt, vEd;
+            uSt = find_set(G[i].second.first);
+            vEd = find_set(G[i].second.second);
+            if (uSt != vEd) {
+                T.push_back(G[i]); // add to mst std::vector
+                union_set(uSt, vEd);
+            }
+        }
+    }
+
+    void MST::insertElement(std::list<int>& variables, int variable)
+    {
+        if (std::find(variables.begin(), variables.end(), variable) == variables.end()) {
+            variables.push_front(variable);
+        }
+    }
+
+    std::vector<std::pair<int, int>> MST::reorder(std::vector<std::pair<float, std::pair<int, int>>> T, int root_original)
+    {
+        // Create the edges of a DAG from the MST
+        // replacing unordered_set with list because unordered_set cannot guarantee the order of the elements inserted
+        auto result = std::vector<std::pair<int, int>>();
+        auto visited = std::vector<int>();
+        auto nextVariables = std::list<int>();
+        nextVariables.push_front(root_original);
+        while (nextVariables.size() > 0) {
+            int root = nextVariables.front();
+            nextVariables.pop_front();
+            for (int i = 0; i < T.size(); ++i) {
+                auto [weight, edge] = T[i];
+                auto [from, to] = edge;
+                if (from == root || to == root) {
+                    visited.insert(visited.begin(), i);
+                    if (from == root) {
+                        result.push_back({ from, to });
+                        insertElement(nextVariables, to);
+                    } else {
+                        result.push_back({ to, from });
+                        insertElement(nextVariables, from);
+                    }
+                }
+            }
+            // Remove visited
+            for (int i = 0; i < visited.size(); ++i) {
+                T.erase(T.begin() + visited[i]);
+            }
+            visited.clear();
+        }
+        if (T.size() > 0) {
+            for (int i = 0; i < T.size(); ++i) {
+                auto [weight, edge] = T[i];
+                auto [from, to] = edge;
+                result.push_back({ from, to });
+            }
+        }
+        return result;
+    }
+
+    MST::MST(const std::vector<std::string>& features, const torch::Tensor& weights, const int root) : features(features), weights(weights), root(root) {}
+    std::vector<std::pair<int, int>> MST::maximumSpanningTree()
+    {
+        auto num_features = features.size();
+        Graph g(num_features);
+        // Make a complete graph
+        for (int i = 0; i < num_features - 1; ++i) {
+            for (int j = i + 1; j < num_features; ++j) {
+                g.addEdge(i, j, weights[i][j].item<float>());
+            }
+        }
+        g.kruskal_algorithm();
+        auto mst = g.get_mst();
+        return reorder(mst, root);
+    }
+
+}

bayesnet/utils/Mst.h

@@ -0,0 +1,40 @@
+// ***************************************************************
+// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
+// SPDX-FileType: SOURCE
+// SPDX-License-Identifier: MIT
+// ***************************************************************
+
+#ifndef MST_H
+#define MST_H
+#include <vector>
+#include <string>
+#include <torch/torch.h>
+namespace bayesnet {
+    class MST {
+    public:
+        MST() = default;
+        MST(const std::vector<std::string>& features, const torch::Tensor& weights, const int root);
+        void insertElement(std::list<int>& variables, int variable);
+        std::vector<std::pair<int, int>> reorder(std::vector<std::pair<float, std::pair<int, int>>> T, int root_original);
+        std::vector<std::pair<int, int>> maximumSpanningTree();
+    private:
+        torch::Tensor weights;
+        std::vector<std::string> features;
+        int root = 0;
+    };
+    class Graph {
+    public:
+        explicit Graph(int V);
+        void addEdge(int u, int v, float wt);
+        int find_set(int i);
+        void union_set(int u, int v);
+        void kruskal_algorithm();
+        std::vector <std::pair<float, std::pair<int, int>>> get_mst() { return T; }
+    private:
+        int V;      // number of nodes in graph
+        std::vector <std::pair<float, std::pair<int, int>>> G; // std::vector for graph
+        std::vector <std::pair<float, std::pair<int, int>>> T; // std::vector for mst
+        std::vector<int> parent;
+    };
+}
+#endif

bayesnet/utils/TensorUtils.h

@@ -0,0 +1,51 @@
+#ifndef TENSORUTILS_H
+#define TENSORUTILS_H
+#include <torch/torch.h>
+#include <vector>
+namespace bayesnet {
+    class TensorUtils {
+    public:
+        static std::vector<std::vector<int>> to_matrix(const torch::Tensor& X)
+        {
+            // Ensure tensor is contiguous in memory
+            auto X_contig = X.contiguous();
+
+            // Access tensor data pointer directly
+            auto data_ptr = X_contig.data_ptr<int>();
+
+            // IF you are using int64_t as the data type, use the following line
+            //auto data_ptr = X_contig.data_ptr<int64_t>();
+            //std::vector<std::vector<int64_t>> data(X.size(0), std::vector<int64_t>(X.size(1)));
+
+            // Prepare output container
+            std::vector<std::vector<int>> data(X.size(0), std::vector<int>(X.size(1)));
+
+            // Fill the 2D vector in a single loop using pointer arithmetic
+            int rows = X.size(0);
+            int cols = X.size(1);
+            for (int i = 0; i < rows; ++i) {
+                std::copy(data_ptr + i * cols, data_ptr + (i + 1) * cols, data[i].begin());
+            }
+            return data;
+        }
+        template <typename T>
+        static std::vector<T> to_vector(const torch::Tensor& y)
+        {
+            // Ensure the tensor is contiguous in memory
+            auto y_contig = y.contiguous();
+
+            // Access data pointer
+            auto data_ptr = y_contig.data_ptr<T>();
+
+            // Prepare output container
+            std::vector<T> data(y.size(0));
+
+            // Copy data efficiently
+            std::copy(data_ptr, data_ptr + y.size(0), data.begin());
+
+            return data;
+        }
+    };
+}
+
+#endif // TENSORUTILS_H

bayesnet/utils/bayesnetUtils.cc

@@ -0,0 +1,44 @@
+// ***************************************************************
+// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
+// SPDX-FileType: SOURCE
+// SPDX-License-Identifier: MIT
+// ***************************************************************
+
+
+#include "bayesnetUtils.h"
+namespace bayesnet {
+    // Return the indices in descending order
+    std::vector<int> argsort(std::vector<double>& nums)
+    {
+        int n = nums.size();
+        std::vector<int> indices(n);
+        iota(indices.begin(), indices.end(), 0);
+        sort(indices.begin(), indices.end(), [&nums](int i, int j) {return nums[i] > nums[j];});
+        return indices;
+    }
+    std::vector<std::vector<double>> tensorToVectorDouble(torch::Tensor& dtensor)
+    {
+        // convert mxn tensor to mxn std::vector
+        std::vector<std::vector<double>> result;
+        // Iterate over cols
+        for (int i = 0; i < dtensor.size(0); ++i) {
+            auto col_tensor = dtensor.index({ i, "..." });
+            auto col = std::vector<double>(col_tensor.data_ptr<float>(), col_tensor.data_ptr<float>() + dtensor.size(1));
+            result.push_back(col);
+        }
+        return result;
+    }
+    torch::Tensor vectorToTensor(std::vector<std::vector<int>>& vector, bool transpose)
+    {
+        // convert nxm std::vector to mxn tensor if transpose
+        long int m = transpose ? vector[0].size() : vector.size();
+        long int n = transpose ? vector.size() : vector[0].size();
+        auto tensor = torch::zeros({ m, n }, torch::kInt32);
+        for (int i = 0; i < m; ++i) {
+            for (int j = 0; j < n; ++j) {
+                tensor[i][j] = transpose ? vector[j][i] : vector[i][j];
+            }
+        }
+        return tensor;
+    }
+}

bayesnet/utils/bayesnetUtils.h

@@ -0,0 +1,16 @@
+// ***************************************************************
+// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
+// SPDX-FileType: SOURCE
+// SPDX-License-Identifier: MIT
+// ***************************************************************
+
+#ifndef BAYESNET_UTILS_H
+#define BAYESNET_UTILS_H
+#include <vector>
+#include <torch/torch.h>
+namespace bayesnet {
+    std::vector<int> argsort(std::vector<double>& nums);
+    std::vector<std::vector<double>> tensorToVectorDouble(torch::Tensor& dtensor);
+    torch::Tensor vectorToTensor(std::vector<std::vector<int>>& vector, bool transpose = true);
+}
+#endif //BAYESNET_UTILS_H