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

Redo pass states to Network Fit needed in crossval

Browse Source 
fix mistake in headerline (report)
This commit is contained in:
Ricardo Montañana Gómez 2023-08-12 11:10:53 +02:00
parent 0ad5505c16
commit 3a85481a5a
Signed by: rmontanana
GPG Key ID: 46064262FD9A7ADE
6 changed files with 31 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.vscode/launch.json vendored
View File

@ -25,12 +25,12 @@
"program": "${workspaceFolder}/build/src/Platform/main",
"args": [
"-m",
"AODELd",
"TANLd",
"-p",
"/Users/rmontanana/Code/discretizbench/datasets",
"--stratified",
"-d",
"iris"
"vehicle"
],
"cwd": "/Users/rmontanana/Code/discretizbench",
},

2
src/BayesNet/Classifier.cc
View File

@ -37,7 +37,7 @@ namespace bayesnet {
}
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
Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)

33
src/BayesNet/Network.cc
View File

@ -104,7 +104,7 @@ namespace bayesnet {
{
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) {
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()) {
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
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();
}
// 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;
Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
samples = torch::cat({ X , ytmp }, 0);
for (int i = 0; i < featureNames.size(); ++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->samples = samples;
completeFit();
completeFit(states);
}
// 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;
// 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);
@ -162,11 +165,11 @@ namespace bayesnet {
samples.index_put_({ i, "..." }, torch::tensor(input_data[i], 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);
if (maxThreadsRunning < 1) {
maxThreadsRunning = 1;
@ -212,7 +215,7 @@ namespace bayesnet {
torch::Tensor result;
result = torch::zeros({ samples.size(1), classNumStates }, torch::kFloat64);
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 temp = torch::tensor(psample, torch::kFloat64);
// result.index_put_({ i, "..." }, torch::tensor(predict_sample(sample), torch::kFloat64));

18
src/BayesNet/Network.h
View File

@ -20,13 +20,9 @@ namespace bayesnet {
vector<double> predict_sample(const torch::Tensor&);
vector<double> exactInference(map<string, int>&);
double computeFactor(map<string, int>&);
double mutual_info(torch::Tensor&, torch::Tensor&);
double entropy(torch::Tensor&);
double conditionalEntropy(torch::Tensor&, torch::Tensor&);
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();
void completeFit(const map<string, vector<int>>&);
void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>&);
void setStates(const map<string, vector<int>>&);
public:
Network();
explicit Network(float, int);
@ -43,13 +39,11 @@ namespace bayesnet {
int getNumEdges() const;
int getClassNumStates() const;
string getClassName() const;
void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&);
void fit(const torch::Tensor&, const torch::Tensor&, const vector<string>&, const string&);
void fit(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 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
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);
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

2
src/BayesNet/Proposal.cc
View File

@ -64,7 +64,7 @@ namespace bayesnet {
//Update new states of the feature/node
states[pFeatures[index]] = xStates;
}
model.fit(pDataset, pFeatures, pClassName);
model.fit(pDataset, pFeatures, pClassName, states);
}
}
void Proposal::fit_local_discretization(map<string, vector<int>>& states, torch::Tensor& y)

5
src/Platform/Report.cc
View File

@ -4,6 +4,7 @@ namespace platform {
string headerLine(const string& text)
{
int n = MAXL - text.length() - 3;
n = n < 0 ? 0 : n;
return "* " + text + string(n, ' ') + "*\n";
}
string Report::fromVector(const string& key)
@ -13,7 +14,7 @@ namespace platform {
for (auto& item : data[key]) {
result += to_string(item) + ", ";
}
return "[" + result.substr(0, result.length() - 2) + "]";
return "[" + result.substr(0, result.size() - 2) + "]";
}
string fVector(const json& data)
{
@ -21,7 +22,7 @@ namespace platform {
for (const auto& item : data) {
result += to_string(item) + ", ";
}
return "[" + result.substr(0, result.length() - 2) + "]";
return "[" + result.substr(0, result.size() - 2) + "]";
}
void Report::show()
{