createDataFrame.cpp

This code shows how to create a DataFrame object and add data to it.

This code shows how to create a DataFrame object and add data to it.

Index	Diameter(μm)	Elongation factor	Type
1	6.52	0.93	Nucleus
2	2.47	0.37	Mitochondrion
3	5.78	0.86	Nucleus

Then another Formula column is added to give the result of the multiplication of Diameter and Elongation factor columns.

#include <iostream>
#include <numeric>
#include <vector>
 
#include <iolink/view/DataFrameViewFactory.h>
 
using namespace iolink;
 
// Create a DataFrame object with 4 columns, using given values:
// - Indexer (int)
// - Diameter (double)
// - Elongation Factor (double)
// - Type (string)
std::shared_ptr<DataFrameView>
createDataFrame(const std::vector<double>& diameterValues,
                const std::vector<double>& elongFactValues,
                const std::vector<std::string>& typeValues)
{
  // each list should have the same size
  if (diameterValues.size() != elongFactValues.size() || diameterValues.size() != typeValues.size())
  {
    throw std::invalid_argument("All lists should have the same size");
  }
 
  // create a DataFrame object with 4 columns and the number of rows equal to the size of the given data
  std::vector<std::string> columnNames = {"Index", "Diameter", "Elongation Factor", "Type"};
  std::vector<DataType> columnTypes = {
    DataTypeId::UINT64, DataTypeId::DOUBLE, DataTypeId::DOUBLE, DataTypeId::UTF8_STRING};
  std::shared_ptr<DataFrameView> dataFrame =
    DataFrameViewFactory::allocate(Vector2u64{4, diameterValues.size()}, columnNames.data(), columnTypes.data());
 
  // set the unit of the Diameter column
  dataFrame->setUnit(dataFrame->columnIndex("Diameter"), "μm");
 
  std::vector<uint64_t> indexValues(diameterValues.size());
  std::iota(indexValues.begin(), indexValues.end(), 1);
 
  // fill each column with the given data, one shot
  dataFrame->write(dataFrame->columnIndex("Index"), 0, indexValues.size(), indexValues.data());
  dataFrame->write(dataFrame->columnIndex("Diameter"), 0, diameterValues.size(), diameterValues.data());
  dataFrame->write(dataFrame->columnIndex("Elongation Factor"), 0, elongFactValues.size(), elongFactValues.data());
  dataFrame->write(dataFrame->columnIndex("Type"), 0, typeValues.size(), typeValues.data());
 
  return dataFrame;
}
 
// Add a new column "formula" to the DataFrame object which is the result of the multiplication of the Diameter and
// Elongation Factor columns
void
addFormulaToDataFrame(std::shared_ptr<DataFrameView> df)
{
  // add a new column "formula" to the DataFrame object
  df->addColumn("Formula", DataTypeId::DOUBLE);
 
  // get the column index of the Diameter and Elongation Factor columns
  size_t diameterColumnIndex = df->columnIndex("Diameter");
  size_t elongationFactorColumnIndex = df->columnIndex("Elongation Factor");
 
  // get the column index of the new column "formula"
  size_t formulaColumnIndex = df->columnIndex("Formula");
 
  // get the number of rows in the DataFrame object
  size_t numRows = df->shape()[1];
 
  // create a vector to store the result of the multiplication of the Diameter and Elongation Factor columns
  std::vector<double> formulaValues(numRows);
 
  // calculate the result of the multiplication of the Diameter and Elongation Factor columns
  for (size_t i = 0; i < numRows; ++i)
  {
    formulaValues[i] = df->at<double>(diameterColumnIndex, i) * df->at<double>(elongationFactorColumnIndex, i);
    // write the result of the multiplication of the Diameter and Elongation Factor columns to the new column "formula"
    df->setAt<double>(formulaColumnIndex, i, formulaValues[i]);
  }
}
 
int
main(int argc, char** argv)
{
  // create a DataFrame object with 4 columns and 3 rows
  // and fill it with the following data:
  // | Index | Diameter(μm) | Elongation factor | Type          |
  // |------ |--------------|-------------------|---------------|
  // |  1    |     6.52     |       0.93        | Nucleus       |
  // |  2    |     2.47     |       0.37        | Mitochondrion |
  // |  3    |     5.78     |       0.86        | Nucleus       |
 
  std::shared_ptr<DataFrameView> df =
    createDataFrame({6.52, 2.47, 5.78}, {0.93, 0.37, 0.86}, {"Nucleus", "Mitochondrion", "Nucleus"});
 
  // print the DataFrame object
  std::cout << df->toString() << std::endl;
 
  // add one column "formula" to the DataFrame object which contains the result of the multiplication of the Diameter
  // and Elongation Factor columns
  addFormulaToDataFrame(df);
 
  // print the DataFrame object after adding the new column "formula"
  std::cout << df->toString() << std::endl;
 
  return EXIT_SUCCESS;
}