rmontanana/BayesNet
1
0
Fork 0
Code Issues 2 Pull Requests 1 Actions Packages Projects Releases 6 Wiki Activity

Set smoothing as fit parameter

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2024-06-11 11:40:45 +02:00
parent 27a3e5a5e0
commit b34869cc61
30 changed files with 168 additions and 178 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
bayesnet/classifiers/Classifier.cc
View File

@@ -11,7 +11,7 @@
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)
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, const Smoothing_t smoothing)
{
this->features = features;
this->className = className;
@@ -22,9 +22,8 @@ namespace bayesnet {
auto n_classes = states.at(className).size();
metrics = Metrics(dataset, features, className, n_classes);
model.initialize();
model.setSmoothing(smoothing);
buildModel(weights);
trainModel(weights);
trainModel(weights, smoothing);
fitted = true;
return *this;
}
@@ -42,20 +41,20 @@ namespace bayesnet {
throw std::runtime_error(oss.str());
}
}
void Classifier::trainModel(const torch::Tensor& weights)
void Classifier::trainModel(const torch::Tensor& weights, Smoothing_t smoothing)
{
model.fit(dataset, weights, features, className, states);
model.fit(dataset, weights, features, className, states, smoothing);
}
// 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, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states)
Classifier& 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, const Smoothing_t smoothing)
{
dataset = X;
buildDataset(y);
const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
return build(features, className, states, weights);
return build(features, className, states, weights, smoothing);
}
// X is nxm where n is the number of features and m the number of samples
Classifier& 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)
Classifier& 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, const Smoothing_t smoothing)
{
dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, torch::kInt32);
for (int i = 0; i < X.size(); ++i) {
@@ -64,18 +63,18 @@ namespace bayesnet {
auto ytmp = torch::tensor(y, torch::kInt32);
buildDataset(ytmp);
const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
return build(features, className, states, weights);
return build(features, className, states, weights, smoothing);
}
Classifier& Classifier::fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states)
Classifier& Classifier::fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const Smoothing_t smoothing)
{
this->dataset = dataset;
const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
return build(features, className, states, weights);
return build(features, className, states, weights, smoothing);
}
Classifier& 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)
Classifier& 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, const Smoothing_t smoothing)
{
this->dataset = dataset;
return build(features, className, states, weights);
return build(features, className, states, weights, smoothing);
}
void Classifier::checkFitParameters()
{

12
bayesnet/classifiers/Classifier.h
View File

@@ -15,10 +15,10 @@ namespace bayesnet {
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;
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, const Smoothing_t smoothing) 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, const Smoothing_t smoothing) 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 Smoothing_t smoothing) 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, const Smoothing_t smoothing) override;
void addNodes();
int getNumberOfNodes() const override;
int getNumberOfEdges() const override;
@@ -50,10 +50,10 @@ namespace bayesnet {
std::vector<std::string> notes; // Used to store messages occurred during the fit process
void checkFitParameters();
virtual void buildModel(const torch::Tensor& weights) = 0;
void trainModel(const torch::Tensor& weights) override;
void trainModel(const torch::Tensor& weights, const Smoothing_t smoothing) override;
void buildDataset(torch::Tensor& y);
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);
Classifier& build(const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights, const Smoothing_t smoothing);
};
}
#endif

4
bayesnet/classifiers/KDBLd.cc
View File

@@ -8,7 +8,7 @@
namespace bayesnet {
KDBLd::KDBLd(int k) : KDB(k), Proposal(dataset, features, className) {}
KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_, const Smoothing_t smoothing)
{
checkInput(X_, y_);
features = features_;
@@ -19,7 +19,7 @@ namespace bayesnet {
states = fit_local_discretization(y);
// 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
KDB::fit(dataset, features, className, states);
KDB::fit(dataset, features, className, states, smoothing);
states = localDiscretizationProposal(states, model);
return *this;
}

2
bayesnet/classifiers/KDBLd.h
View File

@@ -15,7 +15,7 @@ namespace bayesnet {
public:
explicit KDBLd(int k);
virtual ~KDBLd() = default;
KDBLd& 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;
KDBLd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states, const Smoothing_t smoothing) override;
std::vector<std::string> graph(const std::string& name = "KDB") const override;
torch::Tensor predict(torch::Tensor& X) override;
static inline std::string version() { return "0.0.1"; };

2
bayesnet/classifiers/Proposal.cc
View File

@@ -70,7 +70,7 @@ namespace bayesnet {
states[pFeatures[index]] = xStates;
}
const torch::Tensor weights = torch::full({ pDataset.size(1) }, 1.0 / pDataset.size(1), torch::kDouble);
model.fit(pDataset, weights, pFeatures, pClassName, states);
model.fit(pDataset, weights, pFeatures, pClassName, states, Smoothing_t::OLD_LAPLACE);
}
return states;
}

12
bayesnet/classifiers/SPODELd.cc
View File

@@ -8,25 +8,25 @@
namespace bayesnet {
SPODELd::SPODELd(int root) : SPODE(root), Proposal(dataset, features, className) {}
SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_, const Smoothing_t smoothing)
{
checkInput(X_, y_);
Xf = X_;
y = y_;
return commonFit(features_, className_, states_);
return commonFit(features_, className_, states_, smoothing);
}
SPODELd& SPODELd::fit(torch::Tensor& dataset, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
SPODELd& SPODELd::fit(torch::Tensor& dataset, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_, const Smoothing_t smoothing)
{
if (!torch::is_floating_point(dataset)) {
throw std::runtime_error("Dataset must be a floating point tensor");
}
Xf = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." }).clone();
y = dataset.index({ -1, "..." }).clone().to(torch::kInt32);
return commonFit(features_, className_, states_);
return commonFit(features_, className_, states_, smoothing);
}
SPODELd& SPODELd::commonFit(const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
SPODELd& SPODELd::commonFit(const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_, const Smoothing_t smoothing)
{
features = features_;
className = className_;
@@ -34,7 +34,7 @@ namespace bayesnet {
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);
SPODE::fit(dataset, features, className, states, smoothing);
states = localDiscretizationProposal(states, model);
return *this;
}

8
bayesnet/classifiers/SPODELd.h
View File

@@ -14,10 +14,10 @@ namespace bayesnet {
public:
explicit SPODELd(int root);
virtual ~SPODELd() = default;
SPODELd& 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;
SPODELd& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
SPODELd& commonFit(const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states);
std::vector<std::string> graph(const std::string& name = "SPODE") const override;
SPODELd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states, const Smoothing_t smoothing) override;
SPODELd& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states, const Smoothing_t smoothing) override;
SPODELd& commonFit(const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states, const Smoothing_t smoothing);
std::vector<std::string> graph(const std::string& name = "SPODELd") const override;
torch::Tensor predict(torch::Tensor& X) override;
static inline std::string version() { return "0.0.1"; };
};

4
bayesnet/classifiers/TANLd.cc
View File

@@ -8,7 +8,7 @@
namespace bayesnet {
TANLd::TANLd() : TAN(), Proposal(dataset, features, className) {}
TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_, const Smoothing_t smoothing)
{
checkInput(X_, y_);
features = features_;
@@ -19,7 +19,7 @@ namespace bayesnet {
states = fit_local_discretization(y);
// 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
TAN::fit(dataset, features, className, states);
TAN::fit(dataset, features, className, states, smoothing);
states = localDiscretizationProposal(states, model);
return *this;

5
bayesnet/classifiers/TANLd.h
View File

@@ -15,10 +15,9 @@ namespace bayesnet {
public:
TANLd();
virtual ~TANLd() = default;
TANLd& 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;
std::vector<std::string> graph(const std::string& name = "TAN") const override;
TANLd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states, const Smoothing_t smoothing) override;
std::vector<std::string> graph(const std::string& name = "TANLd") const override;
torch::Tensor predict(torch::Tensor& X) override;
static inline std::string version() { return "0.0.1"; };
};
}
#endif // !TANLD_H