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

Fix some mistakes in tensors treatment

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2023-07-26 01:39:01 +02:00
parent be06e475f0
commit 099b4bea09
18 changed files with 255 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/Platform/CMakeLists.txt
View File

@@ -5,4 +5,5 @@ include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
add_executable(main Experiment.cc Folding.cc platformUtils.cc)
add_executable(testx testx.cpp Folding.cc)
target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
target_link_libraries(testx ArffFiles mdlp "${TORCH_LIBRARIES}")

23
src/Platform/Experiment.cc
View File

@@ -18,8 +18,13 @@
using namespace std;
Result cross_validation(Fold* fold, bayesnet::BaseClassifier* model, Tensor& X, Tensor& y, vector<string> features, string className, map<string, vector<int>> states)
Result cross_validation(Fold* fold, string model_name, Tensor& X, Tensor& y, vector<string> features, string className, map<string, vector<int>> states)
{
auto classifiers = map<string, bayesnet::BaseClassifier*>({
{ "AODE", new bayesnet::AODE() }, { "KDB", new bayesnet::KDB(2) },
{ "SPODE", new bayesnet::SPODE(2) }, { "TAN", new bayesnet::TAN() }
}
);
auto result = Result();
auto k = fold->getNumberOfFolds();
auto accuracy = torch::zeros({ k }, kFloat64);
@@ -27,6 +32,7 @@ Result cross_validation(Fold* fold, bayesnet::BaseClassifier* model, Tensor& X,
auto test_time = torch::zeros({ k }, kFloat64);
Timer train_timer, test_timer;
for (int i = 0; i < k; i++) {
bayesnet::BaseClassifier* model = classifiers[model_name];
train_timer.start();
auto [train, test] = fold->getFold(i);
auto train_t = torch::tensor(train);
@@ -43,8 +49,7 @@ Result cross_validation(Fold* fold, bayesnet::BaseClassifier* model, Tensor& X,
cout << "y_test: " << y_test.sizes() << endl;
train_time[i] = train_timer.getDuration();
test_timer.start();
//auto acc = model->score(X_test, y_test);
auto acc = 7;
auto acc = model->score(X_test, y_test);
test_time[i] = test_timer.getDuration();
accuracy[i] = acc;
}
@@ -140,18 +145,16 @@ int main(int argc, char** argv)
fold = new StratifiedKFold(n_folds, y, -1);
else
fold = new KFold(n_folds, y.numel(), -1);
auto classifiers = map<string, bayesnet::BaseClassifier*>({
{ "AODE", new bayesnet::AODE() }, { "KDB", new bayesnet::KDB(2) },
{ "SPODE", new bayesnet::SPODE(2) }, { "TAN", new bayesnet::TAN() }
}
);
auto experiment = Experiment();
experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform("cpp");
experiment.setStratified(stratified).setNFolds(5).addRandomSeed(271).setScoreName("accuracy");
bayesnet::BaseClassifier* model = classifiers[model_name];
auto result = cross_validation(fold, model, X, y, features, className, states);
auto result = cross_validation(fold, model_name, X, y, features, className, states);
result.setDataset(file_name);
experiment.addResult(result);
experiment.save(path);
for (auto& item : states) {
cout << item.first << ": " << item.second.size() << endl;
}
return 0;
}

13
src/Platform/Folding.cc
View File

@@ -1,13 +1,16 @@
#include "Folding.h"
#include <algorithm>
#include <map>
#include <random>
Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
{
random_device rd;
random_seed = default_random_engine(seed == -1 ? rd() : seed);
srand(seed == -1 ? time(0) : seed);
}
KFold::KFold(int k, int n, int seed) : Fold(k, n, seed)
{
indices = vector<int>(n);
iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
random_device rd;
default_random_engine random_seed(seed == -1 ? rd() : seed);
shuffle(indices.begin(), indices.end(), random_seed);
}
pair<vector<int>, vector<int>> KFold::getFold(int nFold)
@@ -54,8 +57,6 @@ void StratifiedKFold::build()
class_indices[y[i]].push_back(i);
}
// Shuffle class indices
random_device rd;
default_random_engine random_seed(seed == -1 ? rd() : seed);
for (auto& [cls, indices] : class_indices) {
shuffle(indices.begin(), indices.end(), random_seed);
}
@@ -71,7 +72,7 @@ void StratifiedKFold::build()
class_indices[label].erase(class_indices[label].begin(), it);
}
while (remainder_samples_to_take > 0) {
int fold = (arc4random() % static_cast<int>(k));
int fold = (rand() % static_cast<int>(k));
if (stratified_indices[fold].size() == fold_size) {
continue;
}

4
src/Platform/Folding.h
View File

@@ -2,6 +2,7 @@
#define FOLDING_H
#include <torch/torch.h>
#include <vector>
#include <random>
using namespace std;
class Fold {
@@ -9,8 +10,9 @@ protected:
int k;
int n;
int seed;
default_random_engine random_seed;
public:
Fold(int k, int n, int seed = -1) : k(k), n(n), seed(seed) {}
Fold(int k, int n, int seed = -1);
virtual pair<vector<int>, vector<int>> getFold(int nFold) = 0;
virtual ~Fold() = default;
int getNumberOfFolds() { return k; }

6
src/Platform/platformUtils.cc
View File

@@ -55,16 +55,16 @@ tuple<Tensor, Tensor, vector<string>, string, map<string, vector<int>>> loadData
auto states = map<string, vector<int>>();
if (discretize_dataset) {
auto Xr = discretizeDataset(X, y);
Xd = torch::zeros({ static_cast<int64_t>(Xr[0].size()), static_cast<int64_t>(Xr.size()) }, torch::kInt64);
Xd = torch::zeros({ static_cast<int>(Xr[0].size()), static_cast<int>(Xr.size()) }, torch::kInt32);
for (int i = 0; i < features.size(); ++i) {
states[features[i]] = vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
iota(begin(states[features[i]]), end(states[features[i]]), 0);
Xd.index_put_({ "...", i }, torch::tensor(Xr[i], torch::kInt64));
Xd.index_put_({ "...", i }, torch::tensor(Xr[i], torch::kInt32));
}
states[className] = vector<int>(*max_element(y.begin(), y.end()) + 1);
iota(begin(states[className]), end(states[className]), 0);
} else {
Xd = torch::zeros({ static_cast<int64_t>(X[0].size()), static_cast<int64_t>(X.size()) }, torch::kFloat32);
Xd = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, torch::kFloat32);
for (int i = 0; i < features.size(); ++i) {
Xd.index_put_({ "...", i }, torch::tensor(X[i]));
}

42
src/Platform/testx.cpp
View File

@@ -62,14 +62,40 @@ int main()
cout << endl;
cout << "Test Statistics: " << counts(y, test);
cout << "==============================================================================" << endl;
torch::Tensor a = torch::zeros({ 5, 3 });
torch::Tensor b = torch::zeros({ 5 }) + 1;
torch::Tensor c = torch::cat({ a, b.view({5, 1}) }, 1);
cout << "a:" << a.sizes() << endl;
cout << a << endl;
cout << "b:" << b.sizes() << endl;
cout << b << endl;
cout << "c:" << c.sizes() << endl;
cout << c << endl;
torch::Tensor d = torch::zeros({ 5, 3 });
torch::Tensor e = torch::tensor({ 1,2,3,4,5 }) + 1;
torch::Tensor f = torch::cat({ d, e.view({5, 1}) }, 1);
cout << "d:" << d.sizes() << endl;
cout << d << endl;
cout << "e:" << e.sizes() << endl;
cout << e << endl;
cout << "f:" << f.sizes() << endl;
cout << f << endl;
auto indices = torch::tensor({ 0, 2, 4 });
auto k = f.index({ indices, "..." });
cout << "k:" << k.sizes() << endl;
cout << k << endl;
auto w = torch::index_select(f, 0, indices);
cout << "w:" << w.sizes() << endl;
cout << w << endl;
// cout << "Vector poly" << endl;
// auto some = vector<A>();
// auto cx = C(5, 4);
// auto bx = B(7, 6);
// some.push_back(cx);
// some.push_back(bx);
// for (auto& obj : some) {
// cout << "Obj :" << obj.getA() << endl;
// }
// auto some = vector<A>();
// auto cx = C(5, 4);
// auto bx = B(7, 6);
// some.push_back(cx);
// some.push_back(bx);
// for (auto& obj : some) {
// cout << "Obj :" << obj.getA() << endl;
// }
}
}