rmontanana/BayesNet
rmontanana/BayesNet
1
0
Fork 0
Code Issues 2 Pull Requests Packages Projects Releases 3 Wiki Activity

Merge pull request 'Add the probabilities aggregation method to compute prediction with ensembles' (#16) from baode_proba into main

Browse Source 
Reviewed-on: #16

As only the voting method was implemented, this approach computes the classifiers prediction using a weighted average of the probabilities computed by each model.
Added the predict_proba methods to BaseClassifier - Classifier and Ensemble classes.
Add a hyperparameter to decide the type of computation for ensembles voting - probability aggregation
This commit is contained in:
Ricardo Montañana Gómez 2024-02-25 11:26:26 +00:00
commit b8589bcd0a
56 changed files with 595 additions and 358 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.gitmodules vendored
View File

@ -5,14 +5,16 @@
update = merge
[submodule "lib/catch2"]
path = lib/catch2
main = v2.x
main = v2.x
update = merge
url = https://github.com/catchorg/Catch2.git
[submodule "lib/json"]
path = lib/json
url = https://github.com/nlohmann/json.git
master = master
master = master
update = merge
[submodule "lib/folding"]
path = lib/folding
url = https://github.com/rmontanana/folding
main = main
update = merge

9
CHANGELOG.md
View File

@ -7,6 +7,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
### Added
- Voting / probability aggregation in Ensemble classes
- predict_proba method in Classifier
- predict_proba method in BoostAODE
- predict_voting parameter in BoostAODE constructor to use voting or probability to predict (default is voting)
- hyperparameter predict_voting to AODE, AODELd and BoostAODE (Ensemble child classes)
- tests to check predict & predict_proba coherence
## [1.0.2] - 2024-02-20
### Fixed

8
CMakeLists.txt
View File

@ -1,7 +1,7 @@
cmake_minimum_required(VERSION 3.20)
project(BayesNet
VERSION 1.0.2
VERSION 1.0.3
DESCRIPTION "Bayesian Network and basic classifiers Library."
HOMEPAGE_URL "https://github.com/rmontanana/bayesnet"
LANGUAGES CXX
@ -58,14 +58,12 @@ add_git_submodule("lib/json")
# --------------
add_subdirectory(config)
add_subdirectory(lib/Files)
add_subdirectory(src/BayesNet)
add_subdirectory(src)
file(GLOB BayesNet_HEADERS CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/BayesNet/*.h ${BayesNet_SOURCE_DIR}/BayesNet/*.h)
file(GLOB BayesNet_SOURCES CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/BayesNet/*.cc ${BayesNet_SOURCE_DIR}/src/BayesNet/*.cpp)
file(GLOB BayesNet_SOURCES CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/*.cc)
# Testing
# -------
if (ENABLE_TESTING)
MESSAGE("Testing enabled")
add_git_submodule("lib/catch2")

1
lib/argparse

@ -1 +0,0 @@
Subproject commit 69dabd88a8e6680b1a1a18397eb3e165e4019ce6

2
lib/catch2

@ -1 +1 @@
Subproject commit 863c662c0eff026300f4d729a7054e90d6d12cdd
Subproject commit ed6ac8a629f9a4206575be784c1e340da2a94855

2
lib/json

@ -1 +1 @@
Subproject commit a259ecc51e1951e12f757ce17db958e9881e9c6c
Subproject commit 0457de21cffb298c22b629e538036bfeb96130b7

1
lib/libxlsxwriter

@ -1 +0,0 @@
Subproject commit 29355a0887475488c7cc470ad43cc867fcfa92e2

34
src/AODE.cc Normal file
View File

@ -0,0 +1,34 @@
#include "AODE.h"
namespace bayesnet {
AODE::AODE(bool predict_voting) : Ensemble(predict_voting)
{
validHyperparameters = { "predict_voting" };
}
void AODE::setHyperparameters(const nlohmann::json& hyperparameters_)
{
auto hyperparameters = hyperparameters_;
if (hyperparameters.contains("predict_voting")) {
predict_voting = hyperparameters["predict_voting"];
hyperparameters.erase("predict_voting");
}
if (!hyperparameters.empty()) {
throw std::invalid_argument("Invalid hyperparameters" + hyperparameters.dump());
}
}
void AODE::buildModel(const torch::Tensor& weights)
{
models.clear();
significanceModels.clear();
for (int i = 0; i < features.size(); ++i) {
models.push_back(std::make_unique<SPODE>(i));
}
n_models = models.size();
significanceModels = std::vector<double>(n_models, 1.0);
}
std::vector<std::string> AODE::graph(const std::string& title) const
{
return Ensemble::graph(title);
}
}

9
src/BayesNet/AODE.h → src/AODE.h
View File

@ -4,12 +4,13 @@
#include "SPODE.h"
namespace bayesnet {
class AODE : public Ensemble {
public:
AODE(bool predict_voting = true);
virtual ~AODE() {};
void setHyperparameters(const nlohmann::json& hyperparameters) override;
std::vector<std::string> graph(const std::string& title = "AODE") const override;
protected:
void buildModel(const torch::Tensor& weights) override;
public:
AODE();
virtual ~AODE() {};
std::vector<std::string> graph(const std::string& title = "AODE") const override;
};
}
#endif

17
src/BayesNet/AODELd.cc → src/AODELd.cc
View File

@ -1,7 +1,22 @@
#include "AODELd.h"
namespace bayesnet {
AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
AODELd::AODELd(bool predict_voting) : Ensemble(predict_voting), Proposal(dataset, features, className)
{
validHyperparameters = { "predict_voting" };
}
void AODELd::setHyperparameters(const nlohmann::json& hyperparameters_)
{
auto hyperparameters = hyperparameters_;
if (hyperparameters.contains("predict_voting")) {
predict_voting = hyperparameters["predict_voting"];
hyperparameters.erase("predict_voting");
}
if (!hyperparameters.empty()) {
throw std::invalid_argument("Invalid hyperparameters" + hyperparameters.dump());
}
}
AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
{
checkInput(X_, y_);

12
src/BayesNet/AODELd.h → src/AODELd.h
View File

@ -6,15 +6,15 @@
namespace bayesnet {
class AODELd : public Ensemble, public Proposal {
public:
AODELd(bool predict_voting = true);
virtual ~AODELd() = default;
AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_) override;
void setHyperparameters(const nlohmann::json& hyperparameters) override;
std::vector<std::string> graph(const std::string& name = "AODELd") const override;
protected:
void trainModel(const torch::Tensor& weights) override;
void buildModel(const torch::Tensor& weights) override;
public:
AODELd();
AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_) override;
virtual ~AODELd() = default;
std::vector<std::string> graph(const std::string& name = "AODELd") const override;
static inline std::string version() { return "0.0.1"; };
};
}
#endif // !AODELD_H

3
src/BayesNet/BaseClassifier.h → src/BaseClassifier.h
View File

@ -16,12 +16,15 @@ namespace bayesnet {
virtual ~BaseClassifier() = default;
torch::Tensor virtual predict(torch::Tensor& X) = 0;
std::vector<int> virtual predict(std::vector<std::vector<int >>& X) = 0;
torch::Tensor virtual predict_proba(torch::Tensor& X) = 0;
std::vector<std::vector<double>> virtual predict_proba(std::vector<std::vector<int >>& X) = 0;
status_t virtual getStatus() const = 0;
float virtual score(std::vector<std::vector<int>>& X, std::vector<int>& y) = 0;
float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
int virtual getNumberOfNodes()const = 0;
int virtual getNumberOfEdges()const = 0;
int virtual getNumberOfStates() const = 0;
int virtual getClassNumStates() const = 0;
std::vector<std::string> virtual show() const = 0;
std::vector<std::string> virtual graph(const std::string& title = "") const = 0;
virtual std::string getVersion() = 0;

0
src/BayesNet/BayesMetrics.cc → src/BayesMetrics.cc
View File

0
src/BayesNet/BayesMetrics.h → src/BayesMetrics.h
View File

18
src/BayesNet/AODE.cc
View File

@ -1,18 +0,0 @@
#include "AODE.h"
namespace bayesnet {
AODE::AODE() : Ensemble() {}
void AODE::buildModel(const torch::Tensor& weights)
{
models.clear();
for (int i = 0; i < features.size(); ++i) {
models.push_back(std::make_unique<SPODE>(i));
}
n_models = models.size();
significanceModels = std::vector<double>(n_models, 1.0);
}
std::vector<std::string> AODE::graph(const std::string& title) const
{
return Ensemble::graph(title);
}
}

141
src/BayesNet/Ensemble.cc
View File

@ -1,141 +0,0 @@
#include "Ensemble.h"
namespace bayesnet {
Ensemble::Ensemble() : Classifier(Network()), n_models(0) {}
void Ensemble::trainModel(const torch::Tensor& weights)
{
n_models = models.size();
for (auto i = 0; i < n_models; ++i) {
// fit with std::vectors
models[i]->fit(dataset, features, className, states);
}
}
std::vector<int> Ensemble::voting(torch::Tensor& y_pred)
{
auto y_pred_ = y_pred.accessor<int, 2>();
std::vector<int> y_pred_final;
int numClasses = states.at(className).size();
// y_pred is m x n_models with the prediction of every model for each sample
for (int i = 0; i < y_pred.size(0); ++i) {
// votes store in each index (value of class) the significance added by each model
// i.e. votes[0] contains how much value has the value 0 of class. That value is generated by the models predictions
std::vector<double> votes(numClasses, 0.0);
for (int j = 0; j < n_models; ++j) {
votes[y_pred_[i][j]] += significanceModels.at(j);
}
// argsort in descending order
auto indices = argsort(votes);
y_pred_final.push_back(indices[0]);
}
return y_pred_final;
}
torch::Tensor Ensemble::predict(torch::Tensor& X)
{
if (!fitted) {
throw std::logic_error("Ensemble has not been fitted");
}
torch::Tensor y_pred = torch::zeros({ X.size(1), n_models }, torch::kInt32);
auto threads{ std::vector<std::thread>() };
std::mutex mtx;
for (auto i = 0; i < n_models; ++i) {
threads.push_back(std::thread([&, i]() {
auto ypredict = models[i]->predict(X);
std::lock_guard<std::mutex> lock(mtx);
y_pred.index_put_({ "...", i }, ypredict);
}));
}
for (auto& thread : threads) {
thread.join();
}
return torch::tensor(voting(y_pred));
}
std::vector<int> Ensemble::predict(std::vector<std::vector<int>>& X)
{
if (!fitted) {
throw std::logic_error("Ensemble has not been fitted");
}
long m_ = X[0].size();
long n_ = X.size();
std::vector<std::vector<int>> Xd(n_, std::vector<int>(m_, 0));
for (auto i = 0; i < n_; i++) {
Xd[i] = std::vector<int>(X[i].begin(), X[i].end());
}
torch::Tensor y_pred = torch::zeros({ m_, n_models }, torch::kInt32);
for (auto i = 0; i < n_models; ++i) {
y_pred.index_put_({ "...", i }, torch::tensor(models[i]->predict(Xd), torch::kInt32));
}
return voting(y_pred);
}
float Ensemble::score(torch::Tensor& X, torch::Tensor& y)
{
if (!fitted) {
throw std::logic_error("Ensemble has not been fitted");
}
auto y_pred = predict(X);
int correct = 0;
for (int i = 0; i < y_pred.size(0); ++i) {
if (y_pred[i].item<int>() == y[i].item<int>()) {
correct++;
}
}
return (double)correct / y_pred.size(0);
}
float Ensemble::score(std::vector<std::vector<int>>& X, std::vector<int>& y)
{
if (!fitted) {
throw std::logic_error("Ensemble has not been fitted");
}
auto y_pred = predict(X);
int correct = 0;
for (int i = 0; i < y_pred.size(); ++i) {
if (y_pred[i] == y[i]) {
correct++;
}
}
return (double)correct / y_pred.size();
}
std::vector<std::string> Ensemble::show() const
{
auto result = std::vector<std::string>();
for (auto i = 0; i < n_models; ++i) {
auto res = models[i]->show();
result.insert(result.end(), res.begin(), res.end());
}
return result;
}
std::vector<std::string> Ensemble::graph(const std::string& title) const
{
auto result = std::vector<std::string>();
for (auto i = 0; i < n_models; ++i) {
auto res = models[i]->graph(title + "_" + std::to_string(i));
result.insert(result.end(), res.begin(), res.end());
}
return result;
}
int Ensemble::getNumberOfNodes() const
{
int nodes = 0;
for (auto i = 0; i < n_models; ++i) {
nodes += models[i]->getNumberOfNodes();
}
return nodes;
}
int Ensemble::getNumberOfEdges() const
{
int edges = 0;
for (auto i = 0; i < n_models; ++i) {
edges += models[i]->getNumberOfEdges();
}
return edges;
}
int Ensemble::getNumberOfStates() const
{
int nstates = 0;
for (auto i = 0; i < n_models; ++i) {
nstates += models[i]->getNumberOfStates();
}
return nstates;
}
}

25
src/BayesNet/bayesnetUtils.cc
View File

@ -1,25 +0,0 @@
#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<int>> tensorToVector(torch::Tensor& tensor)
{
// convert mxn tensor to nxm std::vector
std::vector<std::vector<int>> result;
// Iterate over cols
for (int i = 0; i < tensor.size(1); ++i) {
auto col_tensor = tensor.index({ "...", i });
auto col = std::vector<int>(col_tensor.data_ptr<int>(), col_tensor.data_ptr<int>() + tensor.size(0));
result.push_back(col);
}
return result;
}
}

17
src/BayesNet/BoostAODE.cc → src/BoostAODE.cc
View File

@ -8,15 +8,16 @@
#include "folding.hpp"
namespace bayesnet {
BoostAODE::BoostAODE() : Ensemble()
BoostAODE::BoostAODE(bool predict_voting) : Ensemble(predict_voting)
{
validHyperparameters = { "repeatSparent", "maxModels", "ascending", "convergence", "threshold", "select_features", "tolerance" };
validHyperparameters = { "repeatSparent", "maxModels", "ascending", "convergence", "threshold", "select_features", "tolerance", "predict_voting" };
}
void BoostAODE::buildModel(const torch::Tensor& weights)
{
// Models shall be built in trainModel
models.clear();
significanceModels.clear();
n_models = 0;
// Prepare the validation dataset
auto y_ = dataset.index({ -1, "..." });
@ -72,6 +73,10 @@ namespace bayesnet {
tolerance = hyperparameters["tolerance"];
hyperparameters.erase("tolerance");
}
if (hyperparameters.contains("predict_voting")) {
predict_voting = hyperparameters["predict_voting"];
hyperparameters.erase("predict_voting");
}
if (hyperparameters.contains("select_features")) {
auto selectedAlgorithm = hyperparameters["select_features"];
std::vector<std::string> algos = { "IWSS", "FCBF", "CFS" };
@ -128,8 +133,11 @@ namespace bayesnet {
if (selectFeatures) {
featuresUsed = initializeModels();
}
if (maxModels == 0)
bool resetMaxModels = false;
if (maxModels == 0) {
maxModels = .1 * n > 10 ? .1 * n : n;
resetMaxModels = true; // Flag to unset maxModels
}
torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
bool exitCondition = false;
// Variables to control the accuracy finish condition
@ -211,6 +219,9 @@ namespace bayesnet {
status = WARNING;
}
notes.push_back("Number of models: " + std::to_string(n_models));
if (resetMaxModels) {
maxModels = 0;
}
}
std::vector<std::string> BoostAODE::graph(const std::string& title) const
{

2
src/BayesNet/BoostAODE.h → src/BoostAODE.h
View File

@ -7,7 +7,7 @@
namespace bayesnet {
class BoostAODE : public Ensemble {
public:
BoostAODE();
BoostAODE(bool predict_voting = true);
virtual ~BoostAODE() = default;
std::vector<std::string> graph(const std::string& title = "BoostAODE") const override;
void setHyperparameters(const nlohmann::json& hyperparameters) override;

0
src/BayesNet/CFS.cc → src/CFS.cc
View File

0
src/BayesNet/CFS.h → src/CFS.h
View File

2
src/BayesNet/CMakeLists.txt → src/CMakeLists.txt
View File

@ -3,7 +3,7 @@ include_directories(
${BayesNet_SOURCE_DIR}/lib/Files
${BayesNet_SOURCE_DIR}/lib/folding
${BayesNet_SOURCE_DIR}/lib/json/include
${BayesNet_SOURCE_DIR}/src/BayesNet
${BayesNet_SOURCE_DIR}/src
${CMAKE_BINARY_DIR}/configured_files/include
)

34
src/BayesNet/Classifier.cc → src/Classifier.cc
View File

@ -3,6 +3,7 @@
namespace bayesnet {
Classifier::Classifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
const std::string CLASSIFIER_NOT_FITTED = "Classifier has not been fitted";
Classifier& Classifier::build(const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights)
{
this->features = features;
@ -87,14 +88,14 @@ namespace bayesnet {
torch::Tensor Classifier::predict(torch::Tensor& X)
{
if (!fitted) {
throw std::logic_error("Classifier has not been fitted");
throw std::logic_error(CLASSIFIER_NOT_FITTED);
}
return model.predict(X);
}
std::vector<int> Classifier::predict(std::vector<std::vector<int>>& X)
{
if (!fitted) {
throw std::logic_error("Classifier has not been fitted");
throw std::logic_error(CLASSIFIER_NOT_FITTED);
}
auto m_ = X[0].size();
auto n_ = X.size();
@ -105,18 +106,37 @@ namespace bayesnet {
auto yp = model.predict(Xd);
return yp;
}
float Classifier::score(torch::Tensor& X, torch::Tensor& y)
torch::Tensor Classifier::predict_proba(torch::Tensor& X)
{
if (!fitted) {
throw std::logic_error("Classifier has not been fitted");
throw std::logic_error(CLASSIFIER_NOT_FITTED);
}
return model.predict_proba(X);
}
std::vector<std::vector<double>> Classifier::predict_proba(std::vector<std::vector<int>>& X)
{
if (!fitted) {
throw std::logic_error(CLASSIFIER_NOT_FITTED);
}
auto m_ = X[0].size();
auto n_ = X.size();
std::vector<std::vector<int>> Xd(n_, std::vector<int>(m_, 0));
// Convert to nxm vector
for (auto i = 0; i < n_; i++) {
Xd[i] = std::vector<int>(X[i].begin(), X[i].end());
}
auto yp = model.predict_proba(Xd);
return yp;
}
float Classifier::score(torch::Tensor& X, torch::Tensor& y)
{
torch::Tensor y_pred = predict(X);
return (y_pred == y).sum().item<float>() / y.size(0);
}
float Classifier::score(std::vector<std::vector<int>>& X, std::vector<int>& y)
{
if (!fitted) {
throw std::logic_error("Classifier has not been fitted");
throw std::logic_error(CLASSIFIER_NOT_FITTED);
}
return model.score(X, y);
}
@ -145,6 +165,10 @@ namespace bayesnet {
{
return fitted ? model.getStates() : 0;
}
int Classifier::getClassNumStates() const
{
return fitted ? model.getClassNumStates() : 0;
}
std::vector<std::string> Classifier::topological_order()
{
return model.topological_sort();

53
src/BayesNet/Classifier.h → src/Classifier.h
View File

@ -7,11 +7,34 @@
namespace bayesnet {
class Classifier : public BaseClassifier {
private:
Classifier& build(const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
public:
Classifier(Network model);
virtual ~Classifier() = default;
Classifier& fit(std::vector<std::vector<int>>& X, std::vector<int>& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
Classifier& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
Classifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
Classifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights) override;
void addNodes();
int getNumberOfNodes() const override;
int getNumberOfEdges() const override;
int getNumberOfStates() const override;
int getClassNumStates() const override;
torch::Tensor predict(torch::Tensor& X) override;
std::vector<int> predict(std::vector<std::vector<int>>& X) override;
torch::Tensor predict_proba(torch::Tensor& X) override;
std::vector<std::vector<double>> predict_proba(std::vector<std::vector<int>>& X) override;
status_t getStatus() const override { return status; }
std::string getVersion() override { return { project_version.begin(), project_version.end() }; };
float score(torch::Tensor& X, torch::Tensor& y) override;
float score(std::vector<std::vector<int>>& X, std::vector<int>& y) override;
std::vector<std::string> show() const override;
std::vector<std::string> topological_order() override;
std::vector<std::string> getNotes() const override { return notes; }
void dump_cpt() const override;
void setHyperparameters(const nlohmann::json& hyperparameters) override; //For classifiers that don't have hyperparameters
protected:
bool fitted;
int m, n; // m: number of samples, n: number of features
unsigned int m, n; // m: number of samples, n: number of features
Network model;
Metrics metrics;
std::vector<std::string> features;
@ -24,28 +47,8 @@ namespace bayesnet {
virtual void buildModel(const torch::Tensor& weights) = 0;
void trainModel(const torch::Tensor& weights) override;
void buildDataset(torch::Tensor& y);
public:
Classifier(Network model);
virtual ~Classifier() = default;
Classifier& fit(std::vector<std::vector<int>>& X, std::vector<int>& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
Classifier& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
Classifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
Classifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights) override;
void addNodes();
int getNumberOfNodes() const override;
int getNumberOfEdges() const override;
int getNumberOfStates() const override;
torch::Tensor predict(torch::Tensor& X) override;
status_t getStatus() const override { return status; }
std::string getVersion() override { return { project_version.begin(), project_version.end() }; };
std::vector<int> predict(std::vector<std::vector<int>>& X) override;
float score(torch::Tensor& X, torch::Tensor& y) override;
float score(std::vector<std::vector<int>>& X, std::vector<int>& y) override;
std::vector<std::string> show() const override;
std::vector<std::string> topological_order() override;
std::vector<std::string> getNotes() const override { return notes; }
void dump_cpt() const override;
void setHyperparameters(const nlohmann::json& hyperparameters) override; //For classifiers that don't have hyperparameters
private:
Classifier& build(const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
};
}
#endif

216
src/Ensemble.cc Normal file
View File

@ -0,0 +1,216 @@
#include "Ensemble.h"
namespace bayesnet {
Ensemble::Ensemble(bool predict_voting) : Classifier(Network()), n_models(0), predict_voting(predict_voting)
{
};
const std::string ENSEMBLE_NOT_FITTED = "Ensemble has not been fitted";
void Ensemble::trainModel(const torch::Tensor& weights)
{
n_models = models.size();
for (auto i = 0; i < n_models; ++i) {
// fit with std::vectors
models[i]->fit(dataset, features, className, states);
}
}
std::vector<int> Ensemble::compute_arg_max(std::vector<std::vector<double>>& X)
{
std::vector<int> y_pred;
for (auto i = 0; i < X.size(); ++i) {
auto max = std::max_element(X[i].begin(), X[i].end());
y_pred.push_back(std::distance(X[i].begin(), max));
}
return y_pred;
}
torch::Tensor Ensemble::compute_arg_max(torch::Tensor& X)
{
auto y_pred = torch::argmax(X, 1);
return y_pred;
}
torch::Tensor Ensemble::voting(torch::Tensor& votes)
{
// Convert m x n_models tensor to a m x n_class_states with voting probabilities
auto y_pred_ = votes.accessor<int, 2>();
std::vector<int> y_pred_final;
int numClasses = states.at(className).size();
// votes is m x n_models with the prediction of every model for each sample
auto result = torch::zeros({ votes.size(0), numClasses }, torch::kFloat32);
auto sum = std::reduce(significanceModels.begin(), significanceModels.end());
for (int i = 0; i < votes.size(0); ++i) {
// n_votes store in each index (value of class) the significance added by each model
// i.e. n_votes[0] contains how much value has the value 0 of class. That value is generated by the models predictions
std::vector<double> n_votes(numClasses, 0.0);
for (int j = 0; j < n_models; ++j) {
n_votes[y_pred_[i][j]] += significanceModels.at(j);
}
result[i] = torch::tensor(n_votes);
}
// To only do one division and gain precision
result /= sum;
return result;
}
std::vector<std::vector<double>> Ensemble::predict_proba(std::vector<std::vector<int>>& X)
{
if (!fitted) {
throw std::logic_error(ENSEMBLE_NOT_FITTED);
}
return predict_voting ? predict_average_voting(X) : predict_average_proba(X);
}
torch::Tensor Ensemble::predict_proba(torch::Tensor& X)
{
if (!fitted) {
throw std::logic_error(ENSEMBLE_NOT_FITTED);
}
return predict_voting ? predict_average_voting(X) : predict_average_proba(X);
}
std::vector<int> Ensemble::predict(std::vector<std::vector<int>>& X)
{
auto res = predict_proba(X);
return compute_arg_max(res);
}
torch::Tensor Ensemble::predict(torch::Tensor& X)
{
auto res = predict_proba(X);
return compute_arg_max(res);
}
torch::Tensor Ensemble::predict_average_proba(torch::Tensor& X)
{
auto n_states = models[0]->getClassNumStates();
torch::Tensor y_pred = torch::zeros({ X.size(1), n_states }, torch::kFloat32);
auto threads{ std::vector<std::thread>() };
std::mutex mtx;
for (auto i = 0; i < n_models; ++i) {
threads.push_back(std::thread([&, i]() {
auto ypredict = models[i]->predict_proba(X);
std::lock_guard<std::mutex> lock(mtx);
y_pred += ypredict * significanceModels[i];
}));
}
for (auto& thread : threads) {
thread.join();
}
auto sum = std::reduce(significanceModels.begin(), significanceModels.end());
y_pred /= sum;
return y_pred;
}
std::vector<std::vector<double>> Ensemble::predict_average_proba(std::vector<std::vector<int>>& X)
{
auto n_states = models[0]->getClassNumStates();
std::vector<std::vector<double>> y_pred(X[0].size(), std::vector<double>(n_states, 0.0));
auto threads{ std::vector<std::thread>() };
std::mutex mtx;
for (auto i = 0; i < n_models; ++i) {
threads.push_back(std::thread([&, i]() {
auto ypredict = models[i]->predict_proba(X);
assert(ypredict.size() == y_pred.size());
assert(ypredict[0].size() == y_pred[0].size());
std::lock_guard<std::mutex> lock(mtx);
// Multiply each prediction by the significance of the model and then add it to the final prediction
for (auto j = 0; j < ypredict.size(); ++j) {
std::transform(y_pred[j].begin(), y_pred[j].end(), ypredict[j].begin(), y_pred[j].begin(),
[significanceModels = significanceModels[i]](double x, double y) { return x + y * significanceModels; });
}
}));
}
for (auto& thread : threads) {
thread.join();
}
auto sum = std::reduce(significanceModels.begin(), significanceModels.end());
//Divide each element of the prediction by the sum of the significances
for (auto j = 0; j < y_pred.size(); ++j) {
std::transform(y_pred[j].begin(), y_pred[j].end(), y_pred[j].begin(), [sum](double x) { return x / sum; });
}
return y_pred;
}
std::vector<std::vector<double>> Ensemble::predict_average_voting(std::vector<std::vector<int>>& X)
{
torch::Tensor Xt = bayesnet::vectorToTensor(X, false);
auto y_pred = predict_average_voting(Xt);
std::vector<std::vector<double>> result = tensorToVectorDouble(y_pred);
return result;
}
torch::Tensor Ensemble::predict_average_voting(torch::Tensor& X)
{
// Build a m x n_models tensor with the predictions of each model
torch::Tensor y_pred = torch::zeros({ X.size(1), n_models }, torch::kInt32);
auto threads{ std::vector<std::thread>() };
std::mutex mtx;
for (auto i = 0; i < n_models; ++i) {
threads.push_back(std::thread([&, i]() {
auto ypredict = models[i]->predict(X);
std::lock_guard<std::mutex> lock(mtx);
y_pred.index_put_({ "...", i }, ypredict);
}));
}
for (auto& thread : threads) {
thread.join();
}
return voting(y_pred);
}
float Ensemble::score(torch::Tensor& X, torch::Tensor& y)
{
auto y_pred = predict(X);
int correct = 0;
for (int i = 0; i < y_pred.size(0); ++i) {
if (y_pred[i].item<int>() == y[i].item<int>()) {
correct++;
}
}
return (double)correct / y_pred.size(0);
}
float Ensemble::score(std::vector<std::vector<int>>& X, std::vector<int>& y)
{
auto y_pred = predict(X);
int correct = 0;
for (int i = 0; i < y_pred.size(); ++i) {
if (y_pred[i] == y[i]) {
correct++;
}
}
return (double)correct / y_pred.size();
}
std::vector<std::string> Ensemble::show() const
{
auto result = std::vector<std::string>();
for (auto i = 0; i < n_models; ++i) {
auto res = models[i]->show();
result.insert(result.end(), res.begin(), res.end());
}
return result;
}
std::vector<std::string> Ensemble::graph(const std::string& title) const
{
auto result = std::vector<std::string>();
for (auto i = 0; i < n_models; ++i) {
auto res = models[i]->graph(title + "_" + std::to_string(i));
result.insert(result.end(), res.begin(), res.end());
}
return result;
}
int Ensemble::getNumberOfNodes() const
{
int nodes = 0;
for (auto i = 0; i < n_models; ++i) {
nodes += models[i]->getNumberOfNodes();
}
return nodes;
}
int Ensemble::getNumberOfEdges() const
{
int edges = 0;
for (auto i = 0; i < n_models; ++i) {
edges += models[i]->getNumberOfEdges();
}
return edges;
}
int Ensemble::getNumberOfStates() const
{
int nstates = 0;
for (auto i = 0; i < n_models; ++i) {
nstates += models[i]->getNumberOfStates();
}
return nstates;
}
}

25
src/BayesNet/Ensemble.h → src/Ensemble.h
View File

@ -7,19 +7,13 @@
namespace bayesnet {
class Ensemble : public Classifier {
private:
Ensemble& build(std::vector<std::string>& features, std::string className, std::map<std::string, std::vector<int>>& states);
protected:
unsigned n_models;
std::vector<std::unique_ptr<Classifier>> models;
std::vector<double> significanceModels;
void trainModel(const torch::Tensor& weights) override;
std::vector<int> voting(torch::Tensor& y_pred);
public:
Ensemble();
Ensemble(bool predict_voting = true);
virtual ~Ensemble() = default;
torch::Tensor predict(torch::Tensor& X) override;
std::vector<int> predict(std::vector<std::vector<int>>& X) override;
torch::Tensor predict_proba(torch::Tensor& X) override;
std::vector<std::vector<double>> predict_proba(std::vector<std::vector<int>>& X) override;
float score(torch::Tensor& X, torch::Tensor& y) override;
float score(std::vector<std::vector<int>>& X, std::vector<int>& y) override;
int getNumberOfNodes() const override;
@ -34,6 +28,19 @@ namespace bayesnet {
void dump_cpt() const override
{
}
protected:
torch::Tensor predict_average_voting(torch::Tensor& X);
std::vector<std::vector<double>> predict_average_voting(std::vector<std::vector<int>>& X);
torch::Tensor predict_average_proba(torch::Tensor& X);
std::vector<std::vector<double>> predict_average_proba(std::vector<std::vector<int>>& X);
torch::Tensor compute_arg_max(torch::Tensor& X);
std::vector<int> compute_arg_max(std::vector<std::vector<double>>& X);
torch::Tensor voting(torch::Tensor& votes);
unsigned n_models;
std::vector<std::unique_ptr<Classifier>> models;
std::vector<double> significanceModels;
void trainModel(const torch::Tensor& weights) override;
bool predict_voting;
};
}
#endif

0
src/BayesNet/FCBF.cc → src/FCBF.cc
View File

0
src/BayesNet/FCBF.h → src/FCBF.h
View File

0
src/BayesNet/FeatureSelect.cc → src/FeatureSelect.cc
View File

0
src/BayesNet/FeatureSelect.h → src/FeatureSelect.h
View File

0
src/BayesNet/IWSS.cc → src/IWSS.cc
View File

0
src/BayesNet/IWSS.h → src/IWSS.h
View File

0
src/BayesNet/KDB.cc → src/KDB.cc
View File

0
src/BayesNet/KDB.h → src/KDB.h
View File

0
src/BayesNet/KDBLd.cc → src/KDBLd.cc
View File

0
src/BayesNet/KDBLd.h → src/KDBLd.h
View File

0
src/BayesNet/Mst.cc → src/Mst.cc
View File

0
src/BayesNet/Mst.h → src/Mst.h
View File

1
src/BayesNet/Network.cc → src/Network.cc
View File

@ -238,6 +238,7 @@ namespace bayesnet {
return predictions;
}
// Return mxn std::vector of probabilities
// tsamples is nxm std::vector of samples
std::vector<std::vector<double>> Network::predict_proba(const std::vector<std::vector<int>>& tsamples)
{
if (!fitted) {

34
src/BayesNet/Network.h → src/Network.h
View File

@ -7,23 +7,6 @@
namespace bayesnet {
class Network {
private:
std::map<std::string, std::unique_ptr<Node>> nodes;
bool fitted;
float maxThreads = 0.95;
int classNumStates;
std::vector<std::string> features; // Including classname
std::string className;
double laplaceSmoothing;
torch::Tensor samples; // nxm tensor used to fit the model
bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
std::vector<double> predict_sample(const std::vector<int>&);
std::vector<double> predict_sample(const torch::Tensor&);
std::vector<double> exactInference(std::map<std::string, int>&);
double computeFactor(std::map<std::string, int>&);
void completeFit(const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
void checkFitData(int n_features, int n_samples, int n_samples_y, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
void setStates(const std::map<std::string, std::vector<int>>&);
public:
Network();
explicit Network(float);
@ -58,6 +41,23 @@ namespace bayesnet {
void initialize();
void dump_cpt() const;
inline std::string version() { return { project_version.begin(), project_version.end() }; }
private:
std::map<std::string, std::unique_ptr<Node>> nodes;
bool fitted;
float maxThreads = 0.95;
int classNumStates;
std::vector<std::string> features; // Including classname
std::string className;
double laplaceSmoothing;
torch::Tensor samples; // nxm tensor used to fit the model
bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
std::vector<double> predict_sample(const std::vector<int>&);
std::vector<double> predict_sample(const torch::Tensor&);
std::vector<double> exactInference(std::map<std::string, int>&);
double computeFactor(std::map<std::string, int>&);
void completeFit(const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
void checkFitData(int n_features, int n_samples, int n_samples_y, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
void setStates(const std::map<std::string, std::vector<int>>&);
};
}
#endif

0
src/BayesNet/Node.cc → src/Node.cc
View File

0
src/BayesNet/Node.h → src/Node.h
View File

0
src/BayesNet/Proposal.cc → src/Proposal.cc
View File

0
src/BayesNet/Proposal.h → src/Proposal.h
View File

0
src/BayesNet/SPODE.cc → src/SPODE.cc
View File

0
src/BayesNet/SPODE.h → src/SPODE.h
View File

0
src/BayesNet/SPODELd.cc → src/SPODELd.cc
View File

0
src/BayesNet/SPODELd.h → src/SPODELd.h
View File

0
src/BayesNet/TAN.cc → src/TAN.cc
View File

0
src/BayesNet/TAN.h → src/TAN.h
View File

0
src/BayesNet/TANLd.cc → src/TANLd.cc
View File

0
src/BayesNet/TANLd.h → src/TANLd.h
View File

50
src/bayesnetUtils.cc Normal file
View File

@ -0,0 +1,50 @@
#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<int>> tensorToVector(torch::Tensor& dtensor)
{
// convert mxn tensor to nxm std::vector
std::vector<std::vector<int>> result;
// Iterate over cols
for (int i = 0; i < dtensor.size(1); ++i) {
auto col_tensor = dtensor.index({ "...", i });
auto col = std::vector<int>(col_tensor.data_ptr<int>(), col_tensor.data_ptr<int>() + dtensor.size(0));
result.push_back(col);
}
return result;
}
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;
}
}

4
src/BayesNet/bayesnetUtils.h → src/bayesnetUtils.h
View File

@ -4,6 +4,8 @@
#include <vector>
namespace bayesnet {
std::vector<int> argsort(std::vector<double>& nums);
std::vector<std::vector<int>> tensorToVector(torch::Tensor& tensor);
std::vector<std::vector<int>> tensorToVector(torch::Tensor& dtensor);
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

4
tests/CMakeLists.txt
View File

@ -1,7 +1,7 @@
if(ENABLE_TESTING)
set(TEST_BAYESNET "unit_tests_bayesnet")
include_directories(
${BayesNet_SOURCE_DIR}/src/BayesNet
${BayesNet_SOURCE_DIR}/src
${BayesNet_SOURCE_DIR}/src/Platform
${BayesNet_SOURCE_DIR}/lib/Files
${BayesNet_SOURCE_DIR}/lib/mdlp
@ -11,6 +11,6 @@ if(ENABLE_TESTING)
)
set(TEST_SOURCES_BAYESNET TestBayesModels.cc TestBayesNetwork.cc TestBayesMetrics.cc TestUtils.cc ${BayesNet_SOURCES})
add_executable(${TEST_BAYESNET} ${TEST_SOURCES_BAYESNET})
target_link_libraries(${TEST_BAYESNET} PUBLIC "${TORCH_LIBRARIES}" ArffFiles mdlp Catch2::Catch2WithMain)
target_link_libraries(${TEST_BAYESNET} PUBLIC "${TORCH_LIBRARIES}" ArffFiles mdlp Catch2::Catch2WithMain )
add_test(NAME ${TEST_BAYESNET} COMMAND ${TEST_BAYESNET})
endif(ENABLE_TESTING)

223
tests/TestBayesModels.cc
View File

@ -2,9 +2,6 @@
#include <catch2/catch_test_macros.hpp>
#include <catch2/catch_approx.hpp>
#include <catch2/generators/catch_generators.hpp>
#include <vector>
#include <map>
#include <string>
#include "KDB.h"
#include "TAN.h"
#include "SPODE.h"
@ -16,12 +13,9 @@
#include "AODELd.h"
#include "TestUtils.h"
TEST_CASE("Library check version", "[BayesNet]")
{
auto clf = bayesnet::KDB(2);
REQUIRE(clf.getVersion() == "1.0.2");
}
TEST_CASE("Test Bayesian Classifiers score", "[BayesNet]")
const std::string ACTUAL_VERSION = "1.0.3";
TEST_CASE("Test Bayesian Classifiers score & version", "[BayesNet]")
{
map <pair<std::string, std::string>, float> scores = {
// Diabetes
@ -37,87 +31,34 @@ TEST_CASE("Test Bayesian Classifiers score", "[BayesNet]")
{{"iris", "AODE"}, 0.973333}, {{"iris", "KDB"}, 0.973333}, {{"iris", "SPODE"}, 0.973333}, {{"iris", "TAN"}, 0.973333},
{{"iris", "AODELd"}, 0.973333}, {{"iris", "KDBLd"}, 0.973333}, {{"iris", "SPODELd"}, 0.96f}, {{"iris", "TANLd"}, 0.97333f}, {{"iris", "BoostAODE"}, 0.98f}
};
std::map<std::string, bayesnet::BaseClassifier*> models = {
{"AODE", new bayesnet::AODE()}, {"AODELd", new bayesnet::AODELd()},
{"BoostAODE", new bayesnet::BoostAODE()},
{"KDB", new bayesnet::KDB(2)}, {"KDBLd", new bayesnet::KDBLd(2)},
{"SPODE", new bayesnet::SPODE(1)}, {"SPODELd", new bayesnet::SPODELd(1)},
{"TAN", new bayesnet::TAN()}, {"TANLd", new bayesnet::TANLd()}
};
std::string name = GENERATE("AODE", "AODELd", "KDB", "KDBLd", "SPODE", "SPODELd", "TAN", "TANLd");
auto clf = models[name];
std::string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
auto raw = RawDatasets(file_name, false);
SECTION("Test TAN classifier (" + file_name + ")")
SECTION("Test " + name + " classifier")
{
auto clf = bayesnet::TAN();
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
auto score = clf.score(raw.Xv, raw.yv);
//scores[{file_name, "TAN"}] = score;
REQUIRE(score == Catch::Approx(scores[{file_name, "TAN"}]).epsilon(raw.epsilon));
for (const std::string& file_name : { "glass", "iris", "ecoli", "diabetes" }) {
auto clf = models[name];
auto discretize = name.substr(name.length() - 2) != "Ld";
auto raw = RawDatasets(file_name, discretize);
clf->fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
auto score = clf->score(raw.Xt, raw.yt);
INFO("File: " + file_name);
REQUIRE(score == Catch::Approx(scores[{file_name, name}]).epsilon(raw.epsilon));
}
}
SECTION("Test TANLd classifier (" + file_name + ")")
SECTION("Library check version")
{
auto clf = bayesnet::TANLd();
clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
auto score = clf.score(raw.Xt, raw.yt);
//scores[{file_name, "TANLd"}] = score;
REQUIRE(score == Catch::Approx(scores[{file_name, "TANLd"}]).epsilon(raw.epsilon));
INFO("Checking version of " + name + " classifier");
REQUIRE(clf->getVersion() == ACTUAL_VERSION);
}
SECTION("Test KDB classifier (" + file_name + ")")
{
auto clf = bayesnet::KDB(2);
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
auto score = clf.score(raw.Xv, raw.yv);
//scores[{file_name, "KDB"}] = score;
REQUIRE(score == Catch::Approx(scores[{file_name, "KDB"
}]).epsilon(raw.epsilon));
}
SECTION("Test KDBLd classifier (" + file_name + ")")
{
auto clf = bayesnet::KDBLd(2);
clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
auto score = clf.score(raw.Xt, raw.yt);
//scores[{file_name, "KDBLd"}] = score;
REQUIRE(score == Catch::Approx(scores[{file_name, "KDBLd"
}]).epsilon(raw.epsilon));
}
SECTION("Test SPODE classifier (" + file_name + ")")
{
auto clf = bayesnet::SPODE(1);
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
auto score = clf.score(raw.Xv, raw.yv);
// scores[{file_name, "SPODE"}] = score;
REQUIRE(score == Catch::Approx(scores[{file_name, "SPODE"}]).epsilon(raw.epsilon));
}
SECTION("Test SPODELd classifier (" + file_name + ")")
{
auto clf = bayesnet::SPODELd(1);
clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
auto score = clf.score(raw.Xt, raw.yt);
// scores[{file_name, "SPODELd"}] = score;
REQUIRE(score == Catch::Approx(scores[{file_name, "SPODELd"}]).epsilon(raw.epsilon));
}
SECTION("Test AODE classifier (" + file_name + ")")
{
auto clf = bayesnet::AODE();
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
auto score = clf.score(raw.Xv, raw.yv);
// scores[{file_name, "AODE"}] = score;
REQUIRE(score == Catch::Approx(scores[{file_name, "AODE"}]).epsilon(raw.epsilon));
}
SECTION("Test AODELd classifier (" + file_name + ")")
{
auto clf = bayesnet::AODELd();
clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
auto score = clf.score(raw.Xt, raw.yt);
// scores[{file_name, "AODELd"}] = score;
REQUIRE(score == Catch::Approx(scores[{file_name, "AODELd"}]).epsilon(raw.epsilon));
}
SECTION("Test BoostAODE classifier (" + file_name + ")")
{
auto clf = bayesnet::BoostAODE();
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
auto score = clf.score(raw.Xv, raw.yv);
// scores[{file_name, "BoostAODE"}] = score;
REQUIRE(score == Catch::Approx(scores[{file_name, "BoostAODE"}]).epsilon(raw.epsilon));
}
// for (auto scores : scores) {
// std::cout << "{{\"" << scores.first.first << "\", \"" << scores.first.second << "\"}, " << scores.second << "}, ";
// }
delete clf;
}
TEST_CASE("Models features", "[BayesNet]")
{
@ -133,6 +74,8 @@ TEST_CASE("Models features", "[BayesNet]")
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
REQUIRE(clf.getNumberOfNodes() == 5);
REQUIRE(clf.getNumberOfEdges() == 7);
REQUIRE(clf.getNumberOfStates() == 19);
REQUIRE(clf.getClassNumStates() == 3);
REQUIRE(clf.show() == std::vector<std::string>{"class -> sepallength, sepalwidth, petallength, petalwidth, ", "petallength -> sepallength, ", "petalwidth -> ", "sepallength -> sepalwidth, ", "sepalwidth -> petalwidth, "});
REQUIRE(clf.graph("Test") == graph);
}
@ -156,16 +99,15 @@ TEST_CASE("BoostAODE feature_select CFS", "[BayesNet]")
REQUIRE(clf.getNotes()[0] == "Used features in initialization: 6 of 9 with CFS");
REQUIRE(clf.getNotes()[1] == "Number of models: 9");
}
TEST_CASE("BoostAODE test used features in train note", "[BayesNet]")
TEST_CASE("BoostAODE test used features in train note and score", "[BayesNet]")
{
auto raw = RawDatasets("diabetes", true);
auto clf = bayesnet::BoostAODE();
auto clf = bayesnet::BoostAODE(true);
clf.setHyperparameters({
{"ascending",true},
{"convergence", true},
{"repeatSparent",true},
{"select_features","CFS"},
{"tolerance", 3}
});
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
REQUIRE(clf.getNumberOfNodes() == 72);
@ -174,4 +116,109 @@ TEST_CASE("BoostAODE test used features in train note", "[BayesNet]")
REQUIRE(clf.getNotes()[0] == "Used features in initialization: 6 of 8 with CFS");
REQUIRE(clf.getNotes()[1] == "Used features in train: 7 of 8");
REQUIRE(clf.getNotes()[2] == "Number of models: 8");
auto score = clf.score(raw.Xv, raw.yv);
auto scoret = clf.score(raw.Xt, raw.yt);
REQUIRE(score == Catch::Approx(0.8138).epsilon(raw.epsilon));
REQUIRE(scoret == Catch::Approx(0.8138).epsilon(raw.epsilon));
}
TEST_CASE("Model predict_proba", "[BayesNet]")
{
std::string model = GENERATE("TAN", "SPODE", "BoostAODEproba", "BoostAODEvoting");
auto res_prob_tan = std::vector<std::vector<double>>({
{ 0.00375671, 0.994457, 0.00178621 },
{ 0.00137462, 0.992734, 0.00589123 },
{ 0.00137462, 0.992734, 0.00589123 },
{ 0.00137462, 0.992734, 0.00589123 },
{ 0.00218225, 0.992877, 0.00494094 },
{ 0.00494209, 0.0978534, 0.897205 },
{ 0.0054192, 0.974275, 0.0203054 },
{ 0.00433012, 0.985054, 0.0106159 },
{ 0.000860806, 0.996922, 0.00221698 }
});
auto res_prob_spode = std::vector<std::vector<double>>({
{0.00419032, 0.994247, 0.00156265},
{0.00172808, 0.993433, 0.00483862},
{0.00172808, 0.993433, 0.00483862},
{0.00172808, 0.993433, 0.00483862},
{0.00279211, 0.993737, 0.00347077},
{0.0120674, 0.357909, 0.630024},
{0.00386239, 0.913919, 0.0822185},
{0.0244389, 0.966447, 0.00911374},
{0.003135, 0.991799, 0.0050661}
});
auto res_prob_baode = std::vector<std::vector<double>>({
{0.00803291, 0.9676, 0.0243672},
{0.00398714, 0.945126, 0.050887},
{0.00398714, 0.945126, 0.050887},
{0.00398714, 0.945126, 0.050887},
{0.00189227, 0.859575, 0.138533},
{0.0118341, 0.442149, 0.546017},
{0.0216135, 0.785781, 0.192605},
{0.0204803, 0.844276, 0.135244},
{0.00576313, 0.961665, 0.0325716},
});
auto res_prob_voting = std::vector<std::vector<double>>({
{0, 1, 0},
{0, 1, 0},
{0, 1, 0},
{0, 1, 0},
{0, 1, 0},
{0, 0.447909, 0.552091},
{0, 0.811482, 0.188517},
{0, 1, 0},
{0, 1, 0}
});
std::map<std::string, std::vector<std::vector<double>>> res_prob = { {"TAN", res_prob_tan}, {"SPODE", res_prob_spode} , {"BoostAODEproba", res_prob_baode }, {"BoostAODEvoting", res_prob_voting } };
std::map<std::string, bayesnet::BaseClassifier*> models = { {"TAN", new bayesnet::TAN()}, {"SPODE", new bayesnet::SPODE(0)}, {"BoostAODEproba", new bayesnet::BoostAODE(false)}, {"BoostAODEvoting", new bayesnet::BoostAODE(true)} };
int init_index = 78;
auto raw = RawDatasets("iris", true);
SECTION("Test " + model + " predict_proba")
{
auto clf = models[model];
clf->fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
auto y_pred_proba = clf->predict_proba(raw.Xv);
auto y_pred = clf->predict(raw.Xv);
auto yt_pred = clf->predict(raw.Xt);
auto yt_pred_proba = clf->predict_proba(raw.Xt);
REQUIRE(y_pred.size() == yt_pred.size(0));
REQUIRE(y_pred.size() == y_pred_proba.size());
REQUIRE(y_pred.size() == yt_pred_proba.size(0));
REQUIRE(y_pred.size() == raw.yv.size());
REQUIRE(y_pred_proba[0].size() == 3);
REQUIRE(yt_pred_proba.size(1) == y_pred_proba[0].size());
for (int i = 0; i < y_pred_proba.size(); ++i) {
auto maxElem = max_element(y_pred_proba[i].begin(), y_pred_proba[i].end());
int predictedClass = distance(y_pred_proba[i].begin(), maxElem);
REQUIRE(predictedClass == y_pred[i]);
// Check predict is coherent with predict_proba
REQUIRE(yt_pred_proba[i].argmax().item<int>() == y_pred[i]);
}
// Check predict_proba values for vectors and tensors
for (int i = 0; i < res_prob.size(); i++) {
REQUIRE(y_pred[i] == yt_pred[i].item<int>());
for (int j = 0; j < 3; j++) {
REQUIRE(res_prob[model][i][j] == Catch::Approx(y_pred_proba[i + init_index][j]).epsilon(raw.epsilon));
REQUIRE(res_prob[model][i][j] == Catch::Approx(yt_pred_proba[i + init_index][j].item<double>()).epsilon(raw.epsilon));
}
}
delete clf;
}
}
TEST_CASE("BoostAODE voting-proba", "[BayesNet]")
{
auto raw = RawDatasets("iris", false);
auto clf = bayesnet::BoostAODE(false);
clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
auto score_proba = clf.score(raw.Xv, raw.yv);
auto pred_proba = clf.predict_proba(raw.Xv);
clf.setHyperparameters({
{"predict_voting",true},
});
auto score_voting = clf.score(raw.Xv, raw.yv);
auto pred_voting = clf.predict_proba(raw.Xv);
REQUIRE(score_proba == Catch::Approx(0.97333).epsilon(raw.epsilon));
REQUIRE(score_voting == Catch::Approx(0.98).epsilon(raw.epsilon));
REQUIRE(pred_voting[83][2] == Catch::Approx(0.552091).epsilon(raw.epsilon));
REQUIRE(pred_proba[83][2] == Catch::Approx(0.546017).epsilon(raw.epsilon));
}