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

Add numeric features management to Dataset

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2024-06-06 13:03:57 +02:00
parent 6858b3d89a
commit a7ec930fa0
15 changed files with 210 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/main/Experiment.cpp
View File

@@ -115,7 +115,7 @@ namespace platform {
}
void Experiment::cross_validation(const std::string& fileName, bool quiet, bool no_train_score, bool generate_fold_files)
{
auto datasets = Datasets(discretized, Paths::datasets());
auto datasets = Datasets(false, Paths::datasets()); // Never discretize here
// Get dataset
auto [X, y] = datasets.getTensors(fileName);
auto states = datasets.getStates(fileName);
@@ -176,6 +176,12 @@ namespace platform {
auto y_train = y.index({ train_t });
auto X_test = X.index({ "...", test_t });
auto y_test = y.index({ test_t });
if (discretized) {
// compute states too
// discretizer->fit(X_train, y_train);
// X_train = discretizer->transform(X_train);
// X_test = discretizer->transform(X_test);
}
if (generate_fold_files)
generate_files(fileName, discretized, stratified, seed, nfold, X_train, y_train, X_test, y_test, train, test);
if (!quiet)