rmontanana/Platform
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add labels to confusion_matrices in results

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2024-05-10 17:12:11 +02:00
parent 6d4117d188
commit 69b9609154
8 changed files with 57 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/common/Dataset.cpp
View File

@@ -91,6 +91,7 @@ namespace platform {
}
yv.push_back(stoi(tokens.back()));
}
labels.clear();
file.close();
} else {
throw std::invalid_argument("Unable to open dataset file.");
@@ -117,6 +118,7 @@ namespace platform {
className = arff.getClassName();
auto attributes = arff.getAttributes();
transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& attribute) { return attribute.first; });
labels = arff.getLabels();
}
std::vector<std::string> tokenize(std::string line)
{
@@ -160,6 +162,7 @@ namespace platform {
}
yv.push_back(stoi(tokens.back()));
}
labels.clear();
file.close();
} else {
throw std::invalid_argument("Unable to open dataset file.");

30
src/common/Dataset.h
View File

@@ -10,6 +10,21 @@
namespace platform {
class Dataset {
public:
Dataset(const std::string& path, const std::string& name, const std::string& className, bool discretize, fileType_t fileType) : path(path), name(name), className(className), discretize(discretize), loaded(false), fileType(fileType) {};
explicit Dataset(const Dataset&);
std::string getName() const;
std::string getClassName() const;
std::vector<std::string> getLabels() const { return labels; }
std::vector<string> getFeatures() const;
std::map<std::string, std::vector<int>> getStates() const;
std::pair<vector<std::vector<float>>&, std::vector<int>&> getVectors();
std::pair<vector<std::vector<int>>&, std::vector<int>&> getVectorsDiscretized();
std::pair<torch::Tensor&, torch::Tensor&> getTensors();
int getNFeatures() const;
int getNSamples() const;
void load();
const bool inline isLoaded() const { return loaded; };
private:
std::string path;
std::string name;
@@ -17,6 +32,7 @@ namespace platform {
std::string className;
int n_samples{ 0 }, n_features{ 0 };
std::vector<std::string> features;
std::vector<std::string> labels;
std::map<std::string, std::vector<int>> states;
bool loaded;
bool discretize;
@@ -30,20 +46,6 @@ namespace platform {
void load_rdata();
void computeStates();
std::vector<mdlp::labels_t> discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y);
public:
Dataset(const std::string& path, const std::string& name, const std::string& className, bool discretize, fileType_t fileType) : path(path), name(name), className(className), discretize(discretize), loaded(false), fileType(fileType) {};
explicit Dataset(const Dataset&);
std::string getName() const;
std::string getClassName() const;
std::vector<string> getFeatures() const;
std::map<std::string, std::vector<int>> getStates() const;
std::pair<vector<std::vector<float>>&, std::vector<int>&> getVectors();
std::pair<vector<std::vector<int>>&, std::vector<int>&> getVectorsDiscretized();
std::pair<torch::Tensor&, torch::Tensor&> getTensors();
int getNFeatures() const;
int getNSamples() const;
void load();
const bool inline isLoaded() const { return loaded; };
};
};

8
src/common/Datasets.cpp
View File

@@ -42,6 +42,14 @@ namespace platform {
throw std::invalid_argument("Dataset not loaded.");
}
}
std::vector<std::string> Datasets::getLabels(const std::string& name) const
{
if (datasets.at(name)->isLoaded()) {
return datasets.at(name)->getLabels();
} else {
throw std::invalid_argument("Dataset not loaded.");
}
}
map<std::string, std::vector<int>> Datasets::getStates(const std::string& name) const
{
if (datasets.at(name)->isLoaded()) {

19
src/common/Datasets.h
View File

@@ -3,18 +3,12 @@
#include "Dataset.h"
namespace platform {
class Datasets {
private:
std::string path;
fileType_t fileType;
std::string sfileType;
std::map<std::string, std::unique_ptr<Dataset>> datasets;
bool discretize;
void load(); // Loads the list of datasets
public:
explicit Datasets(bool discretize, std::string sfileType) : discretize(discretize), sfileType(sfileType) { load(); };
std::vector<string> getNames();
std::vector<string> getFeatures(const std::string& name) const;
std::vector<std::string> getNames();
std::vector<std::string> getFeatures(const std::string& name) const;
int getNSamples(const std::string& name) const;
std::vector<std::string> getLabels(const std::string& name) const;
std::string getClassName(const std::string& name) const;
int getNClasses(const std::string& name);
std::vector<int> getClassesCounts(const std::string& name) const;
@@ -25,5 +19,12 @@ namespace platform {
bool isDataset(const std::string& name) const;
void loadDataset(const std::string& name) const;
std::string toString() const;
private:
std::string path;
fileType_t fileType;
std::string sfileType;
std::map<std::string, std::unique_ptr<Dataset>> datasets;
bool discretize;
void load(); // Loads the list of datasets
};
};

5
src/main/Experiment.cpp
View File

@@ -83,6 +83,7 @@ namespace platform {
auto features = datasets.getFeatures(fileName);
auto samples = datasets.getNSamples(fileName);
auto className = datasets.getClassName(fileName);
auto labels = datasets.getLabels(fileName);
if (!quiet) {
std::cout << " " << setw(5) << samples << " " << setw(5) << features.size() << flush;
}
@@ -156,12 +157,12 @@ namespace platform {
showProgress(nfold + 1, getColor(clf->getStatus()), "c");
test_timer.start();
auto y_predict = clf->predict(X_test);
Scores scores(y_test, y_predict, states[className].size());
Scores scores(y_test, y_predict, states[className].size(), labels);
auto accuracy_test_value = scores.accuracy();
test_time[item] = test_timer.getDuration();
accuracy_train[item] = accuracy_train_value;
accuracy_test[item] = accuracy_test_value;
confusion_matrices.push_back(scores.get_confusion_matrix_json());
confusion_matrices.push_back(scores.get_confusion_matrix_json(true));
if (!quiet)
std::cout << "\b\b\b, " << flush;
// Store results and times in std::vector