Begin b_list excel

This commit is contained in:
2024-02-29 12:53:11 +01:00
parent 9a26baec47
commit c69dc08134
58 changed files with 148 additions and 39 deletions

51
src/list/DatasetsExcel.cc Normal file
View File

@@ -0,0 +1,51 @@
#include <sstream>
#include "DatasetsExcel.h"
#include "Paths.h"
namespace platform {
DatasetsExcel::DatasetsExcel()
{
file_name = "datasets.xlsx";
workbook = workbook_new(getFileName().c_str());
setProperties("Datasets");
}
DatasetsExcel::~DatasetsExcel()
{
workbook_close(workbook);
}
void DatasetsExcel::report()
{
worksheet = workbook_add_worksheet(workbook, "Datasets");
formatColumns();
worksheet_merge_range(worksheet, 0, 0, 0, 4, "Datasets", styles["headerFirst"]);
// Body header
row = 3;
int col = 1;
int i = 0;
// Get Datasets
// auto data = platform::Datasets(false, platform::Paths::datasets());
// auto datasets = data.getNames();
auto datasets = std::vector<std::string>{ "iris", "wine", "digits", "breast_cancer" };
int maxDatasetName = (*std::max_element(datasets.begin(), datasets.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
datasetNameSize = std::max(datasetNameSize, maxDatasetName);
writeString(row, 0, "", "bodyHeader");
writeString(row, 1, "Dataset", "bodyHeader");
for (auto const& name : datasets) {
row++;
writeInt(row, 0, i++, "ints");
writeString(row, 1, name.c_str(), "text");
}
row++;
formatColumns();
}
void DatasetsExcel::formatColumns()
{
worksheet_freeze_panes(worksheet, 4, 2);
std::vector<int> columns_sizes = { 5, datasetNameSize };
for (int i = 0; i < columns_sizes.size(); ++i) {
worksheet_set_column(worksheet, i, i, columns_sizes.at(i), NULL);
}
}
}

22
src/list/DatasetsExcel.h Normal file
View File

@@ -0,0 +1,22 @@
#ifndef DATASETS_EXCEL_H
#define DATASETS_EXCEL_H
#include "ExcelFile.h"
#include <vector>
#include <map>
#include <nlohmann/json.hpp>
using json = nlohmann::json;
namespace platform {
class DatasetsExcel : public ExcelFile {
public:
DatasetsExcel();
~DatasetsExcel();
void report();
private:
void formatColumns();
int datasetNameSize = 25; // Min size of the column
};
}
#endif //DATASETS_EXCEL_H

71
src/list/b_list.cc Normal file
View File

@@ -0,0 +1,71 @@
#include <iostream>
#include <locale>
#include <argparse/argparse.hpp>
#include "Paths.h"
#include "Colors.h"
#include "Datasets.h"
#include "DatasetsExcel.h"
#include "config.h"
const int BALANCE_LENGTH = 75;
struct separated : numpunct<char> {
char do_decimal_point() const { return ','; }
char do_thousands_sep() const { return '.'; }
std::string do_grouping() const { return "\03"; }
};
void outputBalance(const std::string& balance)
{
auto temp = std::string(balance);
while (temp.size() > BALANCE_LENGTH - 1) {
auto part = temp.substr(0, BALANCE_LENGTH);
std::cout << part << std::endl;
std::cout << setw(52) << " ";
temp = temp.substr(BALANCE_LENGTH);
}
std::cout << temp << std::endl;
}
int main(int argc, char** argv)
{
auto data = platform::Datasets(false, platform::Paths::datasets());
argparse::ArgumentParser program("b_list", { project_version.begin(), project_version.end() });
program.add_argument("--excel")
.help("Output in Excel format")
.default_value(false)
.implicit_value(true);
program.parse_args(argc, argv);
auto excel = program.get<bool>("--excel");
locale mylocale(std::cout.getloc(), new separated);
locale::global(mylocale);
std::cout.imbue(mylocale);
std::cout << Colors::GREEN() << " # Dataset Sampl. Feat. Cls Balance" << std::endl;
std::string balanceBars = std::string(BALANCE_LENGTH, '=');
std::cout << "=== ============================== ====== ===== === " << balanceBars << std::endl;
int num = 0;
for (const auto& dataset : data.getNames()) {
auto color = num % 2 ? Colors::CYAN() : Colors::BLUE();
std::cout << color << setw(3) << right << num++ << " ";
std::cout << setw(30) << left << dataset << " ";
data.loadDataset(dataset);
auto nSamples = data.getNSamples(dataset);
std::cout << setw(6) << right << nSamples << " ";
std::cout << setw(5) << right << data.getFeatures(dataset).size() << " ";
std::cout << setw(3) << right << data.getNClasses(dataset) << " ";
std::stringstream oss;
std::string sep = "";
for (auto number : data.getClassesCounts(dataset)) {
oss << sep << std::setprecision(2) << fixed << (float)number / nSamples * 100.0 << "% (" << number << ")";
sep = " / ";
}
outputBalance(oss.str());
}
std::cout << Colors::RESET() << std::endl;
if (excel) {
auto report = platform::DatasetsExcel();
report.report();
std::cout << "Output saved in " << report.getFileName() << std::endl;
}
return 0;
}