Compare commits
5 Commits
ef1bffcac3
...
optimize_m
Author | SHA1 | Date | |
---|---|---|---|
182b52a887
|
|||
405887f833
|
|||
3a85481a5a
|
|||
0ad5505c16
|
|||
323444b74a
|
3
.vscode/launch.json
vendored
3
.vscode/launch.json
vendored
@@ -25,8 +25,7 @@
|
|||||||
"program": "${workspaceFolder}/build/src/Platform/main",
|
"program": "${workspaceFolder}/build/src/Platform/main",
|
||||||
"args": [
|
"args": [
|
||||||
"-m",
|
"-m",
|
||||||
"AODE",
|
"SPODELd",
|
||||||
"--discretize",
|
|
||||||
"-p",
|
"-p",
|
||||||
"/Users/rmontanana/Code/discretizbench/datasets",
|
"/Users/rmontanana/Code/discretizbench/datasets",
|
||||||
"--stratified",
|
"--stratified",
|
||||||
|
@@ -9,7 +9,7 @@ namespace bayesnet {
|
|||||||
models.push_back(std::make_unique<SPODE>(i));
|
models.push_back(std::make_unique<SPODE>(i));
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
vector<string> AODE::graph(const string& title)
|
vector<string> AODE::graph(const string& title) const
|
||||||
{
|
{
|
||||||
return Ensemble::graph(title);
|
return Ensemble::graph(title);
|
||||||
}
|
}
|
||||||
|
@@ -9,7 +9,7 @@ namespace bayesnet {
|
|||||||
public:
|
public:
|
||||||
AODE();
|
AODE();
|
||||||
virtual ~AODE() {};
|
virtual ~AODE() {};
|
||||||
vector<string> graph(const string& title = "AODE") override;
|
vector<string> graph(const string& title = "AODE") const override;
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
@@ -1,18 +1,23 @@
|
|||||||
#include "AODELd.h"
|
#include "AODELd.h"
|
||||||
|
#include "Models.h"
|
||||||
|
|
||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
|
AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
|
||||||
AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
|
AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
|
||||||
{
|
{
|
||||||
|
// This first part should go in a Classifier method called fit_local_discretization o fit_float...
|
||||||
features = features_;
|
features = features_;
|
||||||
className = className_;
|
className = className_;
|
||||||
states = states_;
|
Xf = X_;
|
||||||
buildModel();
|
y = y_;
|
||||||
trainModel();
|
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
|
||||||
n_models = models.size();
|
states = fit_local_discretization(y);
|
||||||
fitted = true;
|
// We have discretized the input data
|
||||||
|
// 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
|
||||||
|
Ensemble::fit(dataset, features, className, states);
|
||||||
return *this;
|
return *this;
|
||||||
|
|
||||||
}
|
}
|
||||||
void AODELd::buildModel()
|
void AODELd::buildModel()
|
||||||
{
|
{
|
||||||
@@ -20,18 +25,15 @@ namespace bayesnet {
|
|||||||
for (int i = 0; i < features.size(); ++i) {
|
for (int i = 0; i < features.size(); ++i) {
|
||||||
models.push_back(std::make_unique<SPODELd>(i));
|
models.push_back(std::make_unique<SPODELd>(i));
|
||||||
}
|
}
|
||||||
|
n_models = models.size();
|
||||||
}
|
}
|
||||||
void AODELd::trainModel()
|
void AODELd::trainModel()
|
||||||
{
|
{
|
||||||
for (const auto& model : models) {
|
for (const auto& model : models) {
|
||||||
model->fit(dataset, features, className, states);
|
model->fit(Xf, y, features, className, states);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
Tensor AODELd::predict(Tensor& X)
|
vector<string> AODELd::graph(const string& name) const
|
||||||
{
|
|
||||||
return Ensemble::predict(X);
|
|
||||||
}
|
|
||||||
vector<string> AODELd::graph(const string& name)
|
|
||||||
{
|
{
|
||||||
return Ensemble::graph(name);
|
return Ensemble::graph(name);
|
||||||
}
|
}
|
||||||
|
@@ -7,15 +7,14 @@
|
|||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
class AODELd : public Ensemble, public Proposal {
|
class AODELd : public Ensemble, public Proposal {
|
||||||
private:
|
protected:
|
||||||
void trainModel() override;
|
void trainModel() override;
|
||||||
void buildModel() override;
|
void buildModel() override;
|
||||||
public:
|
public:
|
||||||
AODELd();
|
AODELd();
|
||||||
|
AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_) override;
|
||||||
virtual ~AODELd() = default;
|
virtual ~AODELd() = default;
|
||||||
AODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
vector<string> graph(const string& name = "AODE") const override;
|
||||||
vector<string> graph(const string& name = "AODE") override;
|
|
||||||
Tensor predict(Tensor& X) override;
|
|
||||||
static inline string version() { return "0.0.1"; };
|
static inline string version() { return "0.0.1"; };
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
@@ -5,6 +5,8 @@
|
|||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
class BaseClassifier {
|
class BaseClassifier {
|
||||||
|
protected:
|
||||||
|
virtual void trainModel() = 0;
|
||||||
public:
|
public:
|
||||||
// X is nxm vector, y is nx1 vector
|
// X is nxm vector, y is nx1 vector
|
||||||
virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
|
virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
|
||||||
@@ -16,14 +18,14 @@ namespace bayesnet {
|
|||||||
vector<int> virtual predict(vector<vector<int>>& X) = 0;
|
vector<int> virtual predict(vector<vector<int>>& X) = 0;
|
||||||
float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
|
float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
|
||||||
float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
|
float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
|
||||||
int virtual getNumberOfNodes() = 0;
|
int virtual getNumberOfNodes()const = 0;
|
||||||
int virtual getNumberOfEdges() = 0;
|
int virtual getNumberOfEdges()const = 0;
|
||||||
int virtual getNumberOfStates() = 0;
|
int virtual getNumberOfStates() const = 0;
|
||||||
vector<string> virtual show() = 0;
|
vector<string> virtual show() const = 0;
|
||||||
vector<string> virtual graph(const string& title = "") = 0;
|
vector<string> virtual graph(const string& title = "") const = 0;
|
||||||
const string inline getVersion() const { return "0.1.0"; };
|
const string inline getVersion() const { return "0.1.0"; };
|
||||||
vector<string> virtual topological_order() = 0;
|
vector<string> virtual topological_order() = 0;
|
||||||
void virtual dump_cpt() = 0;
|
void virtual dump_cpt()const = 0;
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
@@ -1,5 +1,7 @@
|
|||||||
include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
|
include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
|
||||||
include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
|
include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
|
||||||
|
include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
|
||||||
|
include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
|
||||||
add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc
|
add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc
|
||||||
KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc Mst.cc Proposal.cc)
|
KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc Mst.cc Proposal.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
|
||||||
target_link_libraries(BayesNet mdlp ArffFiles "${TORCH_LIBRARIES}")
|
target_link_libraries(BayesNet mdlp ArffFiles "${TORCH_LIBRARIES}")
|
@@ -37,7 +37,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
void Classifier::trainModel()
|
void Classifier::trainModel()
|
||||||
{
|
{
|
||||||
model.fit(dataset, features, className);
|
model.fit(dataset, features, className, states);
|
||||||
}
|
}
|
||||||
// X is nxm where n is the number of features and m the number of samples
|
// X is nxm where n is the number of features and m the number of samples
|
||||||
Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
|
Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
|
||||||
@@ -112,7 +112,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return model.score(X, y);
|
return model.score(X, y);
|
||||||
}
|
}
|
||||||
vector<string> Classifier::show()
|
vector<string> Classifier::show() const
|
||||||
{
|
{
|
||||||
return model.show();
|
return model.show();
|
||||||
}
|
}
|
||||||
@@ -124,16 +124,16 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
model.addNode(className);
|
model.addNode(className);
|
||||||
}
|
}
|
||||||
int Classifier::getNumberOfNodes()
|
int Classifier::getNumberOfNodes() const
|
||||||
{
|
{
|
||||||
// Features does not include class
|
// Features does not include class
|
||||||
return fitted ? model.getFeatures().size() + 1 : 0;
|
return fitted ? model.getFeatures().size() + 1 : 0;
|
||||||
}
|
}
|
||||||
int Classifier::getNumberOfEdges()
|
int Classifier::getNumberOfEdges() const
|
||||||
{
|
{
|
||||||
return fitted ? model.getEdges().size() : 0;
|
return fitted ? model.getNumEdges() : 0;
|
||||||
}
|
}
|
||||||
int Classifier::getNumberOfStates()
|
int Classifier::getNumberOfStates() const
|
||||||
{
|
{
|
||||||
return fitted ? model.getStates() : 0;
|
return fitted ? model.getStates() : 0;
|
||||||
}
|
}
|
||||||
@@ -141,7 +141,7 @@ namespace bayesnet {
|
|||||||
{
|
{
|
||||||
return model.topological_sort();
|
return model.topological_sort();
|
||||||
}
|
}
|
||||||
void Classifier::dump_cpt()
|
void Classifier::dump_cpt() const
|
||||||
{
|
{
|
||||||
model.dump_cpt();
|
model.dump_cpt();
|
||||||
}
|
}
|
||||||
|
@@ -23,7 +23,7 @@ namespace bayesnet {
|
|||||||
map<string, vector<int>> states;
|
map<string, vector<int>> states;
|
||||||
void checkFitParameters();
|
void checkFitParameters();
|
||||||
virtual void buildModel() = 0;
|
virtual void buildModel() = 0;
|
||||||
virtual void trainModel();
|
void trainModel() override;
|
||||||
public:
|
public:
|
||||||
Classifier(Network model);
|
Classifier(Network model);
|
||||||
virtual ~Classifier() = default;
|
virtual ~Classifier() = default;
|
||||||
@@ -31,16 +31,16 @@ namespace bayesnet {
|
|||||||
Classifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
Classifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
||||||
Classifier& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
Classifier& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
||||||
void addNodes();
|
void addNodes();
|
||||||
int getNumberOfNodes() override;
|
int getNumberOfNodes() const override;
|
||||||
int getNumberOfEdges() override;
|
int getNumberOfEdges() const override;
|
||||||
int getNumberOfStates() override;
|
int getNumberOfStates() const override;
|
||||||
Tensor predict(Tensor& X) override;
|
Tensor predict(Tensor& X) override;
|
||||||
vector<int> predict(vector<vector<int>>& X) override;
|
vector<int> predict(vector<vector<int>>& X) override;
|
||||||
float score(Tensor& X, Tensor& y) override;
|
float score(Tensor& X, Tensor& y) override;
|
||||||
float score(vector<vector<int>>& X, vector<int>& y) override;
|
float score(vector<vector<int>>& X, vector<int>& y) override;
|
||||||
vector<string> show() override;
|
vector<string> show() const override;
|
||||||
vector<string> topological_order() override;
|
vector<string> topological_order() override;
|
||||||
void dump_cpt() override;
|
void dump_cpt() const override;
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
||||||
|
@@ -94,7 +94,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return (double)correct / y_pred.size();
|
return (double)correct / y_pred.size();
|
||||||
}
|
}
|
||||||
vector<string> Ensemble::show()
|
vector<string> Ensemble::show() const
|
||||||
{
|
{
|
||||||
auto result = vector<string>();
|
auto result = vector<string>();
|
||||||
for (auto i = 0; i < n_models; ++i) {
|
for (auto i = 0; i < n_models; ++i) {
|
||||||
@@ -103,7 +103,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
vector<string> Ensemble::graph(const string& title)
|
vector<string> Ensemble::graph(const string& title) const
|
||||||
{
|
{
|
||||||
auto result = vector<string>();
|
auto result = vector<string>();
|
||||||
for (auto i = 0; i < n_models; ++i) {
|
for (auto i = 0; i < n_models; ++i) {
|
||||||
@@ -112,7 +112,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
int Ensemble::getNumberOfNodes()
|
int Ensemble::getNumberOfNodes() const
|
||||||
{
|
{
|
||||||
int nodes = 0;
|
int nodes = 0;
|
||||||
for (auto i = 0; i < n_models; ++i) {
|
for (auto i = 0; i < n_models; ++i) {
|
||||||
@@ -120,7 +120,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return nodes;
|
return nodes;
|
||||||
}
|
}
|
||||||
int Ensemble::getNumberOfEdges()
|
int Ensemble::getNumberOfEdges() const
|
||||||
{
|
{
|
||||||
int edges = 0;
|
int edges = 0;
|
||||||
for (auto i = 0; i < n_models; ++i) {
|
for (auto i = 0; i < n_models; ++i) {
|
||||||
@@ -128,7 +128,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return edges;
|
return edges;
|
||||||
}
|
}
|
||||||
int Ensemble::getNumberOfStates()
|
int Ensemble::getNumberOfStates() const
|
||||||
{
|
{
|
||||||
int nstates = 0;
|
int nstates = 0;
|
||||||
for (auto i = 0; i < n_models; ++i) {
|
for (auto i = 0; i < n_models; ++i) {
|
||||||
|
@@ -23,16 +23,16 @@ namespace bayesnet {
|
|||||||
vector<int> predict(vector<vector<int>>& X) override;
|
vector<int> predict(vector<vector<int>>& X) override;
|
||||||
float score(Tensor& X, Tensor& y) override;
|
float score(Tensor& X, Tensor& y) override;
|
||||||
float score(vector<vector<int>>& X, vector<int>& y) override;
|
float score(vector<vector<int>>& X, vector<int>& y) override;
|
||||||
int getNumberOfNodes() override;
|
int getNumberOfNodes() const override;
|
||||||
int getNumberOfEdges() override;
|
int getNumberOfEdges() const override;
|
||||||
int getNumberOfStates() override;
|
int getNumberOfStates() const override;
|
||||||
vector<string> show() override;
|
vector<string> show() const override;
|
||||||
vector<string> graph(const string& title) override;
|
vector<string> graph(const string& title) const override;
|
||||||
vector<string> topological_order() override
|
vector<string> topological_order() override
|
||||||
{
|
{
|
||||||
return vector<string>();
|
return vector<string>();
|
||||||
}
|
}
|
||||||
void dump_cpt() override
|
void dump_cpt() const override
|
||||||
{
|
{
|
||||||
}
|
}
|
||||||
};
|
};
|
||||||
|
@@ -79,7 +79,7 @@ namespace bayesnet {
|
|||||||
exit_cond = num == n_edges || candidates.size(0) == 0;
|
exit_cond = num == n_edges || candidates.size(0) == 0;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
vector<string> KDB::graph(const string& title)
|
vector<string> KDB::graph(const string& title) const
|
||||||
{
|
{
|
||||||
string header{ title };
|
string header{ title };
|
||||||
if (title == "KDB") {
|
if (title == "KDB") {
|
||||||
|
@@ -15,7 +15,7 @@ namespace bayesnet {
|
|||||||
public:
|
public:
|
||||||
explicit KDB(int k, float theta = 0.03);
|
explicit KDB(int k, float theta = 0.03);
|
||||||
virtual ~KDB() {};
|
virtual ~KDB() {};
|
||||||
vector<string> graph(const string& name = "KDB") override;
|
vector<string> graph(const string& name = "KDB") const override;
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
@@ -11,11 +11,11 @@ namespace bayesnet {
|
|||||||
Xf = X_;
|
Xf = X_;
|
||||||
y = y_;
|
y = y_;
|
||||||
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
|
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
|
||||||
fit_local_discretization(states, y);
|
states = fit_local_discretization(y);
|
||||||
// We have discretized the input data
|
// We have discretized the input data
|
||||||
// 1st we need to fit the model to build the normal KDB structure, KDB::fit initializes the base Bayesian network
|
// 1st we need to fit the model to build the normal KDB structure, KDB::fit initializes the base Bayesian network
|
||||||
KDB::fit(dataset, features, className, states);
|
KDB::fit(dataset, features, className, states);
|
||||||
localDiscretizationProposal(states, model);
|
states = localDiscretizationProposal(states, model);
|
||||||
return *this;
|
return *this;
|
||||||
}
|
}
|
||||||
Tensor KDBLd::predict(Tensor& X)
|
Tensor KDBLd::predict(Tensor& X)
|
||||||
@@ -23,7 +23,7 @@ namespace bayesnet {
|
|||||||
auto Xt = prepareX(X);
|
auto Xt = prepareX(X);
|
||||||
return KDB::predict(Xt);
|
return KDB::predict(Xt);
|
||||||
}
|
}
|
||||||
vector<string> KDBLd::graph(const string& name)
|
vector<string> KDBLd::graph(const string& name) const
|
||||||
{
|
{
|
||||||
return KDB::graph(name);
|
return KDB::graph(name);
|
||||||
}
|
}
|
||||||
|
@@ -11,7 +11,7 @@ namespace bayesnet {
|
|||||||
explicit KDBLd(int k);
|
explicit KDBLd(int k);
|
||||||
virtual ~KDBLd() = default;
|
virtual ~KDBLd() = default;
|
||||||
KDBLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
KDBLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
||||||
vector<string> graph(const string& name = "KDB") override;
|
vector<string> graph(const string& name = "KDB") const override;
|
||||||
Tensor predict(Tensor& X) override;
|
Tensor predict(Tensor& X) override;
|
||||||
static inline string version() { return "0.0.1"; };
|
static inline string version() { return "0.0.1"; };
|
||||||
};
|
};
|
||||||
|
@@ -43,15 +43,15 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
nodes[name] = std::make_unique<Node>(name);
|
nodes[name] = std::make_unique<Node>(name);
|
||||||
}
|
}
|
||||||
vector<string> Network::getFeatures()
|
vector<string> Network::getFeatures() const
|
||||||
{
|
{
|
||||||
return features;
|
return features;
|
||||||
}
|
}
|
||||||
int Network::getClassNumStates()
|
int Network::getClassNumStates() const
|
||||||
{
|
{
|
||||||
return classNumStates;
|
return classNumStates;
|
||||||
}
|
}
|
||||||
int Network::getStates()
|
int Network::getStates() const
|
||||||
{
|
{
|
||||||
int result = 0;
|
int result = 0;
|
||||||
for (auto& node : nodes) {
|
for (auto& node : nodes) {
|
||||||
@@ -59,7 +59,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
string Network::getClassName()
|
string Network::getClassName() const
|
||||||
{
|
{
|
||||||
return className;
|
return className;
|
||||||
}
|
}
|
||||||
@@ -104,7 +104,7 @@ namespace bayesnet {
|
|||||||
{
|
{
|
||||||
return nodes;
|
return nodes;
|
||||||
}
|
}
|
||||||
void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className)
|
void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
if (n_samples != n_samples_y) {
|
if (n_samples != n_samples_y) {
|
||||||
throw invalid_argument("X and y must have the same number of samples in Network::fit (" + to_string(n_samples) + " != " + to_string(n_samples_y) + ")");
|
throw invalid_argument("X and y must have the same number of samples in Network::fit (" + to_string(n_samples) + " != " + to_string(n_samples_y) + ")");
|
||||||
@@ -122,39 +122,42 @@ namespace bayesnet {
|
|||||||
if (find(features.begin(), features.end(), feature) == features.end()) {
|
if (find(features.begin(), features.end(), feature) == features.end()) {
|
||||||
throw invalid_argument("Feature " + feature + " not found in Network::features");
|
throw invalid_argument("Feature " + feature + " not found in Network::features");
|
||||||
}
|
}
|
||||||
|
if (states.find(feature) == states.end()) {
|
||||||
|
throw invalid_argument("Feature " + feature + " not found in states");
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
void Network::setStates()
|
void Network::setStates(const map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
// Set states to every Node in the network
|
// Set states to every Node in the network
|
||||||
for (int i = 0; i < features.size(); ++i) {
|
for (int i = 0; i < features.size(); ++i) {
|
||||||
nodes[features[i]]->setNumStates(static_cast<int>(torch::max(samples.index({ i, "..." })).item<int>()) + 1);
|
nodes[features[i]]->setNumStates(states.at(features[i]).size());
|
||||||
}
|
}
|
||||||
classNumStates = nodes[className]->getNumStates();
|
classNumStates = nodes[className]->getNumStates();
|
||||||
}
|
}
|
||||||
// X comes in nxm, where n is the number of features and m the number of samples
|
// X comes in nxm, where n is the number of features and m the number of samples
|
||||||
void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const vector<string>& featureNames, const string& className)
|
void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className);
|
checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className, states);
|
||||||
this->className = className;
|
this->className = className;
|
||||||
Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
|
Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
|
||||||
samples = torch::cat({ X , ytmp }, 0);
|
samples = torch::cat({ X , ytmp }, 0);
|
||||||
for (int i = 0; i < featureNames.size(); ++i) {
|
for (int i = 0; i < featureNames.size(); ++i) {
|
||||||
auto row_feature = X.index({ i, "..." });
|
auto row_feature = X.index({ i, "..." });
|
||||||
}
|
}
|
||||||
completeFit();
|
completeFit(states);
|
||||||
}
|
}
|
||||||
void Network::fit(const torch::Tensor& samples, const vector<string>& featureNames, const string& className)
|
void Network::fit(const torch::Tensor& samples, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
checkFitData(samples.size(1), samples.size(0) - 1, samples.size(1), featureNames, className);
|
checkFitData(samples.size(1), samples.size(0) - 1, samples.size(1), featureNames, className, states);
|
||||||
this->className = className;
|
this->className = className;
|
||||||
this->samples = samples;
|
this->samples = samples;
|
||||||
completeFit();
|
completeFit(states);
|
||||||
}
|
}
|
||||||
// input_data comes in nxm, where n is the number of features and m the number of samples
|
// input_data comes in nxm, where n is the number of features and m the number of samples
|
||||||
void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<string>& featureNames, const string& className)
|
void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className);
|
checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className, states);
|
||||||
this->className = className;
|
this->className = className;
|
||||||
// Build tensor of samples (nxm) (n+1 because of the class)
|
// Build tensor of samples (nxm) (n+1 because of the class)
|
||||||
samples = torch::zeros({ static_cast<int>(input_data.size() + 1), static_cast<int>(input_data[0].size()) }, torch::kInt32);
|
samples = torch::zeros({ static_cast<int>(input_data.size() + 1), static_cast<int>(input_data[0].size()) }, torch::kInt32);
|
||||||
@@ -162,11 +165,11 @@ namespace bayesnet {
|
|||||||
samples.index_put_({ i, "..." }, torch::tensor(input_data[i], torch::kInt32));
|
samples.index_put_({ i, "..." }, torch::tensor(input_data[i], torch::kInt32));
|
||||||
}
|
}
|
||||||
samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
|
samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
|
||||||
completeFit();
|
completeFit(states);
|
||||||
}
|
}
|
||||||
void Network::completeFit()
|
void Network::completeFit(const map<string, vector<int>>& states)
|
||||||
{
|
{
|
||||||
setStates();
|
setStates(states);
|
||||||
int maxThreadsRunning = static_cast<int>(std::thread::hardware_concurrency() * maxThreads);
|
int maxThreadsRunning = static_cast<int>(std::thread::hardware_concurrency() * maxThreads);
|
||||||
if (maxThreadsRunning < 1) {
|
if (maxThreadsRunning < 1) {
|
||||||
maxThreadsRunning = 1;
|
maxThreadsRunning = 1;
|
||||||
@@ -212,7 +215,7 @@ namespace bayesnet {
|
|||||||
torch::Tensor result;
|
torch::Tensor result;
|
||||||
result = torch::zeros({ samples.size(1), classNumStates }, torch::kFloat64);
|
result = torch::zeros({ samples.size(1), classNumStates }, torch::kFloat64);
|
||||||
for (int i = 0; i < samples.size(1); ++i) {
|
for (int i = 0; i < samples.size(1); ++i) {
|
||||||
auto sample = samples.index({ "...", i });
|
const Tensor sample = samples.index({ "...", i });
|
||||||
auto psample = predict_sample(sample);
|
auto psample = predict_sample(sample);
|
||||||
auto temp = torch::tensor(psample, torch::kFloat64);
|
auto temp = torch::tensor(psample, torch::kFloat64);
|
||||||
// result.index_put_({ i, "..." }, torch::tensor(predict_sample(sample), torch::kFloat64));
|
// result.index_put_({ i, "..." }, torch::tensor(predict_sample(sample), torch::kFloat64));
|
||||||
@@ -343,7 +346,7 @@ namespace bayesnet {
|
|||||||
transform(result.begin(), result.end(), result.begin(), [sum](double& value) { return value / sum; });
|
transform(result.begin(), result.end(), result.begin(), [sum](double& value) { return value / sum; });
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
vector<string> Network::show()
|
vector<string> Network::show() const
|
||||||
{
|
{
|
||||||
vector<string> result;
|
vector<string> result;
|
||||||
// Draw the network
|
// Draw the network
|
||||||
@@ -356,7 +359,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
vector<string> Network::graph(const string& title)
|
vector<string> Network::graph(const string& title) const
|
||||||
{
|
{
|
||||||
auto output = vector<string>();
|
auto output = vector<string>();
|
||||||
auto prefix = "digraph BayesNet {\nlabel=<BayesNet ";
|
auto prefix = "digraph BayesNet {\nlabel=<BayesNet ";
|
||||||
@@ -370,7 +373,7 @@ namespace bayesnet {
|
|||||||
output.push_back("}\n");
|
output.push_back("}\n");
|
||||||
return output;
|
return output;
|
||||||
}
|
}
|
||||||
vector<pair<string, string>> Network::getEdges()
|
vector<pair<string, string>> Network::getEdges() const
|
||||||
{
|
{
|
||||||
auto edges = vector<pair<string, string>>();
|
auto edges = vector<pair<string, string>>();
|
||||||
for (const auto& node : nodes) {
|
for (const auto& node : nodes) {
|
||||||
@@ -382,6 +385,10 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return edges;
|
return edges;
|
||||||
}
|
}
|
||||||
|
int Network::getNumEdges() const
|
||||||
|
{
|
||||||
|
return getEdges().size();
|
||||||
|
}
|
||||||
vector<string> Network::topological_sort()
|
vector<string> Network::topological_sort()
|
||||||
{
|
{
|
||||||
/* Check if al the fathers of every node are before the node */
|
/* Check if al the fathers of every node are before the node */
|
||||||
@@ -420,7 +427,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
void Network::dump_cpt()
|
void Network::dump_cpt() const
|
||||||
{
|
{
|
||||||
for (auto& node : nodes) {
|
for (auto& node : nodes) {
|
||||||
cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
|
cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
|
||||||
|
@@ -20,13 +20,9 @@ namespace bayesnet {
|
|||||||
vector<double> predict_sample(const torch::Tensor&);
|
vector<double> predict_sample(const torch::Tensor&);
|
||||||
vector<double> exactInference(map<string, int>&);
|
vector<double> exactInference(map<string, int>&);
|
||||||
double computeFactor(map<string, int>&);
|
double computeFactor(map<string, int>&);
|
||||||
double mutual_info(torch::Tensor&, torch::Tensor&);
|
void completeFit(const map<string, vector<int>>&);
|
||||||
double entropy(torch::Tensor&);
|
void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>&);
|
||||||
double conditionalEntropy(torch::Tensor&, torch::Tensor&);
|
void setStates(const map<string, vector<int>>&);
|
||||||
double mutualInformation(torch::Tensor&, torch::Tensor&);
|
|
||||||
void completeFit();
|
|
||||||
void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className);
|
|
||||||
void setStates();
|
|
||||||
public:
|
public:
|
||||||
Network();
|
Network();
|
||||||
explicit Network(float, int);
|
explicit Network(float, int);
|
||||||
@@ -37,27 +33,26 @@ namespace bayesnet {
|
|||||||
void addNode(const string&);
|
void addNode(const string&);
|
||||||
void addEdge(const string&, const string&);
|
void addEdge(const string&, const string&);
|
||||||
map<string, std::unique_ptr<Node>>& getNodes();
|
map<string, std::unique_ptr<Node>>& getNodes();
|
||||||
vector<string> getFeatures();
|
vector<string> getFeatures() const;
|
||||||
int getStates();
|
int getStates() const;
|
||||||
vector<pair<string, string>> getEdges();
|
vector<pair<string, string>> getEdges() const;
|
||||||
int getClassNumStates();
|
int getNumEdges() const;
|
||||||
string getClassName();
|
int getClassNumStates() const;
|
||||||
void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&);
|
string getClassName() const;
|
||||||
void fit(const torch::Tensor&, const torch::Tensor&, const vector<string>&, const string&);
|
void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&, const map<string, vector<int>>&);
|
||||||
void fit(const torch::Tensor&, const vector<string>&, const string&);
|
void fit(const torch::Tensor&, const torch::Tensor&, const vector<string>&, const string&, const map<string, vector<int>>&);
|
||||||
|
void fit(const torch::Tensor&, const vector<string>&, const string&, const map<string, vector<int>>&);
|
||||||
vector<int> predict(const vector<vector<int>>&); // Return mx1 vector of predictions
|
vector<int> predict(const vector<vector<int>>&); // Return mx1 vector of predictions
|
||||||
torch::Tensor predict(const torch::Tensor&); // Return mx1 tensor of predictions
|
torch::Tensor predict(const torch::Tensor&); // Return mx1 tensor of predictions
|
||||||
//Computes the conditional edge weight of variable index u and v conditioned on class_node
|
|
||||||
torch::Tensor conditionalEdgeWeight();
|
|
||||||
torch::Tensor predict_tensor(const torch::Tensor& samples, const bool proba);
|
torch::Tensor predict_tensor(const torch::Tensor& samples, const bool proba);
|
||||||
vector<vector<double>> predict_proba(const vector<vector<int>>&); // Return mxn vector of probabilities
|
vector<vector<double>> predict_proba(const vector<vector<int>>&); // Return mxn vector of probabilities
|
||||||
torch::Tensor predict_proba(const torch::Tensor&); // Return mxn tensor of probabilities
|
torch::Tensor predict_proba(const torch::Tensor&); // Return mxn tensor of probabilities
|
||||||
double score(const vector<vector<int>>&, const vector<int>&);
|
double score(const vector<vector<int>>&, const vector<int>&);
|
||||||
vector<string> topological_sort();
|
vector<string> topological_sort();
|
||||||
vector<string> show();
|
vector<string> show() const;
|
||||||
vector<string> graph(const string& title); // Returns a vector of strings representing the graph in graphviz format
|
vector<string> graph(const string& title) const; // Returns a vector of strings representing the graph in graphviz format
|
||||||
void initialize();
|
void initialize();
|
||||||
void dump_cpt();
|
void dump_cpt() const;
|
||||||
inline string version() { return "0.1.0"; }
|
inline string version() { return "0.1.0"; }
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
@@ -2,19 +2,20 @@
|
|||||||
#include "ArffFiles.h"
|
#include "ArffFiles.h"
|
||||||
|
|
||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
Proposal::Proposal(torch::Tensor& dataset_, vector<string>& features_, string& className_) : pDataset(dataset_), pFeatures(features_), pClassName(className_), m(dataset_.size(1)), n(dataset_.size(0) - 1) {}
|
Proposal::Proposal(torch::Tensor& dataset_, vector<string>& features_, string& className_) : pDataset(dataset_), pFeatures(features_), pClassName(className_) {}
|
||||||
Proposal::~Proposal()
|
Proposal::~Proposal()
|
||||||
{
|
{
|
||||||
for (auto& [key, value] : discretizers) {
|
for (auto& [key, value] : discretizers) {
|
||||||
delete value;
|
delete value;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
void Proposal::localDiscretizationProposal(map<string, vector<int>>& states, Network& model)
|
map<string, vector<int>> Proposal::localDiscretizationProposal(const map<string, vector<int>>& oldStates, Network& model)
|
||||||
{
|
{
|
||||||
// order of local discretization is important. no good 0, 1, 2...
|
// order of local discretization is important. no good 0, 1, 2...
|
||||||
// although we rediscretize features after the local discretization of every feature
|
// although we rediscretize features after the local discretization of every feature
|
||||||
auto order = model.topological_sort();
|
auto order = model.topological_sort();
|
||||||
auto& nodes = model.getNodes();
|
auto& nodes = model.getNodes();
|
||||||
|
map<string, vector<int>> states = oldStates;
|
||||||
vector<int> indicesToReDiscretize;
|
vector<int> indicesToReDiscretize;
|
||||||
bool upgrade = false; // Flag to check if we need to upgrade the model
|
bool upgrade = false; // Flag to check if we need to upgrade the model
|
||||||
for (auto feature : order) {
|
for (auto feature : order) {
|
||||||
@@ -32,9 +33,9 @@ namespace bayesnet {
|
|||||||
indices.push_back(-1); // Add class index
|
indices.push_back(-1); // Add class index
|
||||||
transform(parents.begin(), parents.end(), back_inserter(indices), [&](const auto& p) {return find(pFeatures.begin(), pFeatures.end(), p) - pFeatures.begin(); });
|
transform(parents.begin(), parents.end(), back_inserter(indices), [&](const auto& p) {return find(pFeatures.begin(), pFeatures.end(), p) - pFeatures.begin(); });
|
||||||
// Now we fit the discretizer of the feature, conditioned on its parents and the class i.e. discretizer.fit(X[index], X[indices] + y)
|
// Now we fit the discretizer of the feature, conditioned on its parents and the class i.e. discretizer.fit(X[index], X[indices] + y)
|
||||||
vector<string> yJoinParents(indices.size());
|
vector<string> yJoinParents(Xf.size(1));
|
||||||
for (auto idx : indices) {
|
for (auto idx : indices) {
|
||||||
for (int i = 0; i < n; ++i) {
|
for (int i = 0; i < Xf.size(1); ++i) {
|
||||||
yJoinParents[i] += to_string(pDataset.index({ idx, i }).item<int>());
|
yJoinParents[i] += to_string(pDataset.index({ idx, i }).item<int>());
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -64,10 +65,16 @@ namespace bayesnet {
|
|||||||
//Update new states of the feature/node
|
//Update new states of the feature/node
|
||||||
states[pFeatures[index]] = xStates;
|
states[pFeatures[index]] = xStates;
|
||||||
}
|
}
|
||||||
|
model.fit(pDataset, pFeatures, pClassName, states);
|
||||||
}
|
}
|
||||||
|
return states;
|
||||||
}
|
}
|
||||||
void Proposal::fit_local_discretization(map<string, vector<int>>& states, torch::Tensor& y)
|
map<string, vector<int>> Proposal::fit_local_discretization(const torch::Tensor& y)
|
||||||
{
|
{
|
||||||
|
// Discretize the continuous input data and build pDataset (Classifier::dataset)
|
||||||
|
int m = Xf.size(1);
|
||||||
|
int n = Xf.size(0);
|
||||||
|
map<string, vector<int>> states;
|
||||||
pDataset = torch::zeros({ n + 1, m }, kInt32);
|
pDataset = torch::zeros({ n + 1, m }, kInt32);
|
||||||
auto yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
|
auto yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
|
||||||
// discretize input data by feature(row)
|
// discretize input data by feature(row)
|
||||||
@@ -86,6 +93,8 @@ namespace bayesnet {
|
|||||||
auto yStates = vector<int>(n_classes);
|
auto yStates = vector<int>(n_classes);
|
||||||
iota(yStates.begin(), yStates.end(), 0);
|
iota(yStates.begin(), yStates.end(), 0);
|
||||||
states[pClassName] = yStates;
|
states[pClassName] = yStates;
|
||||||
|
pDataset.index_put_({ n, "..." }, y);
|
||||||
|
return states;
|
||||||
}
|
}
|
||||||
torch::Tensor Proposal::prepareX(torch::Tensor& X)
|
torch::Tensor Proposal::prepareX(torch::Tensor& X)
|
||||||
{
|
{
|
||||||
|
@@ -14,12 +14,11 @@ namespace bayesnet {
|
|||||||
virtual ~Proposal();
|
virtual ~Proposal();
|
||||||
protected:
|
protected:
|
||||||
torch::Tensor prepareX(torch::Tensor& X);
|
torch::Tensor prepareX(torch::Tensor& X);
|
||||||
void localDiscretizationProposal(map<string, vector<int>>& states, Network& model);
|
map<string, vector<int>> localDiscretizationProposal(const map<string, vector<int>>& states, Network& model);
|
||||||
void fit_local_discretization(map<string, vector<int>>& states, torch::Tensor& y);
|
map<string, vector<int>> fit_local_discretization(const torch::Tensor& y);
|
||||||
torch::Tensor Xf; // X continuous nxm tensor
|
torch::Tensor Xf; // X continuous nxm tensor
|
||||||
torch::Tensor y; // y discrete nx1 tensor
|
torch::Tensor y; // y discrete nx1 tensor
|
||||||
map<string, mdlp::CPPFImdlp*> discretizers;
|
map<string, mdlp::CPPFImdlp*> discretizers;
|
||||||
int m, n;
|
|
||||||
private:
|
private:
|
||||||
torch::Tensor& pDataset; // (n+1)xm tensor
|
torch::Tensor& pDataset; // (n+1)xm tensor
|
||||||
vector<string>& pFeatures;
|
vector<string>& pFeatures;
|
||||||
|
@@ -17,7 +17,7 @@ namespace bayesnet {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
vector<string> SPODE::graph(const string& name)
|
vector<string> SPODE::graph(const string& name) const
|
||||||
{
|
{
|
||||||
return model.graph(name);
|
return model.graph(name);
|
||||||
}
|
}
|
||||||
|
@@ -11,7 +11,7 @@ namespace bayesnet {
|
|||||||
public:
|
public:
|
||||||
explicit SPODE(int root);
|
explicit SPODE(int root);
|
||||||
virtual ~SPODE() {};
|
virtual ~SPODE() {};
|
||||||
vector<string> graph(const string& name = "SPODE") override;
|
vector<string> graph(const string& name = "SPODE") const override;
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
@@ -11,20 +11,36 @@ namespace bayesnet {
|
|||||||
Xf = X_;
|
Xf = X_;
|
||||||
y = y_;
|
y = y_;
|
||||||
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
|
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
|
||||||
fit_local_discretization(states, y);
|
states = fit_local_discretization(y);
|
||||||
// We have discretized the input data
|
// We have discretized the input data
|
||||||
// 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
|
// 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
|
||||||
SPODE::fit(dataset, features, className, states);
|
SPODE::fit(dataset, features, className, states);
|
||||||
localDiscretizationProposal(states, model);
|
states = localDiscretizationProposal(states, model);
|
||||||
//model.fit(SPODE::Xv, SPODE::yv, features, className);
|
|
||||||
return *this;
|
return *this;
|
||||||
}
|
}
|
||||||
|
SPODELd& SPODELd::fit(torch::Tensor& dataset, vector<string>& features_, string className_, map<string, vector<int>>& states_)
|
||||||
|
{
|
||||||
|
Xf = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." }).clone();
|
||||||
|
cout << "Xf " << Xf.sizes() << " dtype: " << Xf.dtype() << endl;
|
||||||
|
y = dataset.index({ -1, "..." }).clone();
|
||||||
|
// This first part should go in a Classifier method called fit_local_discretization o fit_float...
|
||||||
|
features = features_;
|
||||||
|
className = className_;
|
||||||
|
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
|
||||||
|
states = fit_local_discretization(y);
|
||||||
|
// We have discretized the input data
|
||||||
|
// 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
|
||||||
|
SPODE::fit(dataset, features, className, states);
|
||||||
|
states = localDiscretizationProposal(states, model);
|
||||||
|
return *this;
|
||||||
|
}
|
||||||
|
|
||||||
Tensor SPODELd::predict(Tensor& X)
|
Tensor SPODELd::predict(Tensor& X)
|
||||||
{
|
{
|
||||||
auto Xt = prepareX(X);
|
auto Xt = prepareX(X);
|
||||||
return SPODE::predict(Xt);
|
return SPODE::predict(Xt);
|
||||||
}
|
}
|
||||||
vector<string> SPODELd::graph(const string& name)
|
vector<string> SPODELd::graph(const string& name) const
|
||||||
{
|
{
|
||||||
return SPODE::graph(name);
|
return SPODE::graph(name);
|
||||||
}
|
}
|
||||||
|
@@ -6,12 +6,12 @@
|
|||||||
namespace bayesnet {
|
namespace bayesnet {
|
||||||
using namespace std;
|
using namespace std;
|
||||||
class SPODELd : public SPODE, public Proposal {
|
class SPODELd : public SPODE, public Proposal {
|
||||||
private:
|
|
||||||
public:
|
public:
|
||||||
explicit SPODELd(int root);
|
explicit SPODELd(int root);
|
||||||
virtual ~SPODELd() = default;
|
virtual ~SPODELd() = default;
|
||||||
SPODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
SPODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
||||||
vector<string> graph(const string& name = "SPODE") override;
|
SPODELd& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
||||||
|
vector<string> graph(const string& name = "SPODE") const override;
|
||||||
Tensor predict(Tensor& X) override;
|
Tensor predict(Tensor& X) override;
|
||||||
static inline string version() { return "0.0.1"; };
|
static inline string version() { return "0.0.1"; };
|
||||||
};
|
};
|
||||||
|
@@ -34,7 +34,7 @@ namespace bayesnet {
|
|||||||
model.addEdge(className, feature);
|
model.addEdge(className, feature);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
vector<string> TAN::graph(const string& title)
|
vector<string> TAN::graph(const string& title) const
|
||||||
{
|
{
|
||||||
return model.graph(title);
|
return model.graph(title);
|
||||||
}
|
}
|
||||||
|
@@ -11,7 +11,7 @@ namespace bayesnet {
|
|||||||
public:
|
public:
|
||||||
TAN();
|
TAN();
|
||||||
virtual ~TAN() {};
|
virtual ~TAN() {};
|
||||||
vector<string> graph(const string& name = "TAN") override;
|
vector<string> graph(const string& name = "TAN") const override;
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
#endif
|
#endif
|
@@ -11,20 +11,20 @@ namespace bayesnet {
|
|||||||
Xf = X_;
|
Xf = X_;
|
||||||
y = y_;
|
y = y_;
|
||||||
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
|
// Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
|
||||||
fit_local_discretization(states, y);
|
states = fit_local_discretization(y);
|
||||||
// We have discretized the input data
|
// We have discretized the input data
|
||||||
// 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
|
// 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
|
||||||
TAN::fit(dataset, features, className, states);
|
TAN::fit(dataset, features, className, states);
|
||||||
localDiscretizationProposal(states, model);
|
states = localDiscretizationProposal(states, model);
|
||||||
//model.fit(dataset, features, className);
|
|
||||||
return *this;
|
return *this;
|
||||||
|
|
||||||
}
|
}
|
||||||
Tensor TANLd::predict(Tensor& X)
|
Tensor TANLd::predict(Tensor& X)
|
||||||
{
|
{
|
||||||
auto Xt = prepareX(X);
|
auto Xt = prepareX(X);
|
||||||
return TAN::predict(Xt);
|
return TAN::predict(Xt);
|
||||||
}
|
}
|
||||||
vector<string> TANLd::graph(const string& name)
|
vector<string> TANLd::graph(const string& name) const
|
||||||
{
|
{
|
||||||
return TAN::graph(name);
|
return TAN::graph(name);
|
||||||
}
|
}
|
||||||
|
@@ -11,7 +11,7 @@ namespace bayesnet {
|
|||||||
TANLd();
|
TANLd();
|
||||||
virtual ~TANLd() = default;
|
virtual ~TANLd() = default;
|
||||||
TANLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
TANLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
|
||||||
vector<string> graph(const string& name = "TAN") override;
|
vector<string> graph(const string& name = "TAN") const override;
|
||||||
Tensor predict(Tensor& X) override;
|
Tensor predict(Tensor& X) override;
|
||||||
static inline string version() { return "0.0.1"; };
|
static inline string version() { return "0.0.1"; };
|
||||||
};
|
};
|
||||||
|
@@ -4,6 +4,7 @@ namespace platform {
|
|||||||
string headerLine(const string& text)
|
string headerLine(const string& text)
|
||||||
{
|
{
|
||||||
int n = MAXL - text.length() - 3;
|
int n = MAXL - text.length() - 3;
|
||||||
|
n = n < 0 ? 0 : n;
|
||||||
return "* " + text + string(n, ' ') + "*\n";
|
return "* " + text + string(n, ' ') + "*\n";
|
||||||
}
|
}
|
||||||
string Report::fromVector(const string& key)
|
string Report::fromVector(const string& key)
|
||||||
@@ -13,7 +14,7 @@ namespace platform {
|
|||||||
for (auto& item : data[key]) {
|
for (auto& item : data[key]) {
|
||||||
result += to_string(item) + ", ";
|
result += to_string(item) + ", ";
|
||||||
}
|
}
|
||||||
return "[" + result.substr(0, result.length() - 2) + "]";
|
return "[" + result.substr(0, result.size() - 2) + "]";
|
||||||
}
|
}
|
||||||
string fVector(const json& data)
|
string fVector(const json& data)
|
||||||
{
|
{
|
||||||
@@ -21,7 +22,7 @@ namespace platform {
|
|||||||
for (const auto& item : data) {
|
for (const auto& item : data) {
|
||||||
result += to_string(item) + ", ";
|
result += to_string(item) + ", ";
|
||||||
}
|
}
|
||||||
return "[" + result.substr(0, result.length() - 2) + "]";
|
return "[" + result.substr(0, result.size() - 2) + "]";
|
||||||
}
|
}
|
||||||
void Report::show()
|
void Report::show()
|
||||||
{
|
{
|
||||||
|
Reference in New Issue
Block a user