Finance

Description¶

The first step is to choose dependent and independent variables. This choice is essentially a mapping from multidimensional data into an unstructured point dataset. This example chooses MONTHLY_PAYMENT, INTEREST_RATE, and LOAN_AMOUNT as (x, y, z) point coordinates, and TIME_LATE as a scalar value. This maps four of six variables. For now we will ignore the other two variables.

The example uses vtkGaussianSplatter to perform the splatting operation (i.e., conversion from unstructured points to volume dataset). This is followed by an isosurface extraction. We splat the data two times. The first time we splat the entire population. This is to show context and appears as gray/ wireframe in the figure. The second time we splat the data and scale it by the value of TIME_LATE . As a result, only payments that are late contribute to the second isosurface. The results of this visualization are interesting. First, we see that there is a strong correlation between the two independent variables MONTHLY_PAYMENT and LOAN_AMOUNT . (This is more evident when viewing the data interactively.) We see that the data falls roughly on a plane at a 45 degree angle between these two axes. With a little reflection this is evident: the monthly payment is strongly a function of loan amount (as well as interest rate and payment period). Second, we see that there is a clustering of delinquent accounts within the total population. The cluster tends to grow with larger interest rates and shrink with smaller monthly payments and loan amounts. Although the relationship with interest rate is expected, the clustering towards smaller monthly payments is not. Thus our visualization has provided a clue into the data. Further exploration may reveal the reason(s), or we may perform additional data analysis and acquisition to understand the phenomena.

One important note about multidimensional visualization. Because we tend to combine variables in odd ways (e.g., the use of MONTHLY_PAYMENT , INTEREST_RATE , and LOAN_AMOUNT as (x, y, z) coordinates), normalization of the data is usually required. To normalize data we simply adjust data values to lie between (0,1). Otherwise our data can be badly skewed and result in poor visualizations.

Info

See Figure 9-50 in Chapter 9 The VTK Textbook.

Other Languages

See (Python)

Code¶

Finance.cxx

#include <vtkActor.h>
#include <vtkAxes.h>
#include <vtkCamera.h>
#include <vtkContourFilter.h>
#include <vtkDataSet.h>
#include <vtkFloatArray.h>
#include <vtkGaussianSplatter.h>
#include <vtkImageData.h>
#include <vtkNamedColors.h>
#include <vtkPointData.h>
#include <vtkPoints.h>
#include <vtkPolyDataMapper.h>
#include <vtkProperty.h>
#include <vtkRenderer.h>
#include <vtkRenderWindow.h> 
#include <vtkRenderWindowInteractor.h>
#include <vtkSmartPointer.h>
#include <vtkTubeFilter.h>
#include <vtkUnstructuredGrid.h>

#include <algorithm>
#include <array>
#include <string>

namespace
{
vtkSmartPointer<vtkDataSet> ReadFinancialData(const char *fname, const char *x, const char *y, const char *z, const char *s);
int ParseFile(FILE *file, const char *tag, float *data);
}

int main( int argc, char *argv[] )
{
  double bounds[6];

  if (argc < 2)
  {
    std::cout << "Usage: " << argv[0] << " financial_file" << endl;
    return EXIT_FAILURE;
  }
  char* fname = argv[1];

  vtkSmartPointer<vtkNamedColors> colors =
    vtkSmartPointer<vtkNamedColors>::New();

  // Set the color for the population.
  std::array<unsigned char , 4> popColor{{230, 230, 230, 255}};
    colors->SetColor("PopColor", popColor.data());

  // read data
  vtkSmartPointer<vtkDataSet> dataSet =
    ReadFinancialData(fname, "MONTHLY_PAYMENT","INTEREST_RATE",
                      "LOAN_AMOUNT","TIME_LATE");
  // construct pipeline for original population
  vtkSmartPointer<vtkGaussianSplatter> popSplatter =
    vtkSmartPointer<vtkGaussianSplatter>::New();
  popSplatter->SetInputData(dataSet);
  popSplatter->SetSampleDimensions(100, 100, 100);
  popSplatter->SetRadius(0.05);
  popSplatter->ScalarWarpingOff();

  vtkSmartPointer<vtkContourFilter> popSurface =
    vtkSmartPointer<vtkContourFilter>::New();
  popSurface->SetInputConnection(popSplatter->GetOutputPort());
  popSurface->SetValue(0,0.01);

  vtkSmartPointer<vtkPolyDataMapper> popMapper =
    vtkSmartPointer<vtkPolyDataMapper>::New();
  popMapper->SetInputConnection(popSurface->GetOutputPort());
  popMapper->ScalarVisibilityOff();

  vtkSmartPointer<vtkActor> popActor = vtkSmartPointer<vtkActor>::New();
  popActor->SetMapper(popMapper);
  popActor->GetProperty()->SetOpacity(0.3);
  popActor->GetProperty()->SetColor(colors->GetColor3d("popColor").GetData());

  // construct pipeline for delinquent population
  vtkSmartPointer<vtkGaussianSplatter> lateSplatter =
    vtkSmartPointer<vtkGaussianSplatter>::New();
  lateSplatter->SetInputData(dataSet);
  lateSplatter->SetSampleDimensions(50,50,50);
  lateSplatter->SetRadius(0.05);
  lateSplatter->SetScaleFactor(0.005);

  vtkSmartPointer<vtkContourFilter> lateSurface =
    vtkSmartPointer<vtkContourFilter>::New();
  lateSurface->SetInputConnection(lateSplatter->GetOutputPort());
  lateSurface->SetValue(0,0.01);

  vtkSmartPointer<vtkPolyDataMapper> lateMapper =
    vtkSmartPointer<vtkPolyDataMapper>::New();
  lateMapper->SetInputConnection(lateSurface->GetOutputPort());
  lateMapper->ScalarVisibilityOff();

  vtkSmartPointer<vtkActor> lateActor =
    vtkSmartPointer<vtkActor>::New();
  lateActor->SetMapper(lateMapper);
  lateActor->GetProperty()->SetColor(colors->GetColor3d("Red").GetData());

  // create axes
  popSplatter->Update();
  popSplatter->GetOutput()->GetBounds(bounds);

  vtkSmartPointer<vtkAxes> axes =
    vtkSmartPointer<vtkAxes>::New();
  axes->SetOrigin(bounds[0], bounds[2], bounds[4]);
  axes->SetScaleFactor(popSplatter->GetOutput()->GetLength()/5);

  vtkSmartPointer<vtkTubeFilter> axesTubes =
    vtkSmartPointer<vtkTubeFilter>::New();
  axesTubes->SetInputConnection(axes->GetOutputPort());
  axesTubes->SetRadius(axes->GetScaleFactor()/25.0);
  axesTubes->SetNumberOfSides(6);

  vtkSmartPointer<vtkPolyDataMapper> axesMapper =
    vtkSmartPointer<vtkPolyDataMapper>::New();
  axesMapper->SetInputConnection(axesTubes->GetOutputPort());

  vtkSmartPointer<vtkActor> axesActor =
    vtkSmartPointer<vtkActor>::New();
  axesActor->SetMapper(axesMapper);

  // graphics stuff
  vtkSmartPointer<vtkRenderer> renderer =
    vtkSmartPointer<vtkRenderer>::New();

  vtkSmartPointer<vtkRenderWindow> renWin =
    vtkSmartPointer<vtkRenderWindow>::New();
  renWin->AddRenderer(renderer);

  vtkSmartPointer<vtkRenderWindowInteractor> interactor =
    vtkSmartPointer<vtkRenderWindowInteractor>::New();
  interactor->SetRenderWindow(renWin);

  //set up renderer
  renderer->AddActor(lateActor);
  renderer->AddActor(axesActor);
  renderer->AddActor(popActor);
  renderer->SetBackground(colors->GetColor3d("Wheat").GetData());
  renWin->SetSize(640, 480);

  renderer->ResetCamera();
  renderer->GetActiveCamera()->Dolly(1.3);
  renderer->ResetCameraClippingRange();

  // interact with data
  renWin->Render();
  interactor->Start();

  return EXIT_SUCCESS;
}

namespace
{
vtkSmartPointer<vtkDataSet> ReadFinancialData(const char* filename, const char *x, const char *y, const char *z, const char *s)
{
  float xyz[3];
  FILE *file;
  int i, npts;
  char tag[80];

  if ( (file = fopen(filename,"r")) == 0 )
  {
    std::cerr << "ERROR: Can't open file: " << filename << std::endl;
    return NULL;
  }

  int n = fscanf (file, "%s %d", tag, &npts); // read number of points
  if (n != 2)
  {
    std::cerr << "ERROR: Can't read file: " << filename << std::endl;
    fclose(file);
    return NULL;
  }
  // Check for a reasonable npts
  if (npts <= 0)
  {
    std::cerr << "ERROR: Number of points must be greater that 0" << std::endl;
    fclose(file);
    return NULL;
  }
  // We arbitrarily pick a large upper limit on npts
  if (npts > VTK_INT_MAX / 10)
  {
    std::cerr << "ERROR: npts (" << npts << ") is unreasonably large" << std::endl;
    fclose(file);
    return NULL;
  }
  vtkSmartPointer<vtkUnstructuredGrid> dataSet =
    vtkSmartPointer<vtkUnstructuredGrid>::New();
  float *xV = new float[npts];
  float *yV = new float[npts];
  float *zV = new float[npts];
  float *sV = new float[npts];

  if ( ! ParseFile(file, x, xV) || ! ParseFile(file, y, yV) ||
       ! ParseFile(file, z, zV) || ! ParseFile(file, s, sV) )
  {
    std::cerr << "ERROR: Couldn't read data!" << std::endl;
    delete [] xV;
    delete [] yV;
    delete [] zV;
    delete [] sV;
    fclose(file);
    return NULL;
  }

  vtkSmartPointer<vtkPoints> newPts =
    vtkSmartPointer<vtkPoints>::New();
  vtkSmartPointer<vtkFloatArray> newScalars =
    vtkSmartPointer<vtkFloatArray>::New();

  for (i=0; i<npts; i++)
  {
    xyz[0] = xV[i]; xyz[1] = yV[i]; xyz[2] = zV[i];
//     std::cout << xV[i] << " " << yV[i] << " " << zV[i] << std::endl;
    newPts->InsertPoint(i, xyz);
    newScalars->InsertValue(i, sV[i]);
  }

  dataSet->SetPoints(newPts);
  dataSet->GetPointData()->SetScalars(newScalars);

  // cleanup
  delete [] xV;
  delete [] yV;
  delete [] zV;
  delete [] sV;
  fclose(file);

  return dataSet;
}

int ParseFile(FILE *file, const char *label, float *data)
{
  char tag[80];
  int i, npts, readData=0;
  float min=VTK_FLOAT_MAX;
  float max=(-VTK_FLOAT_MAX);

  if ( file == NULL || label == NULL ) return 0;

  rewind(file);

  if (fscanf(file, "%s %d", tag, &npts) != 2)
  {
    std::cerr << "ERROR: IO Error " << __FILE__ << ":" << __LINE__ << std::endl;
    return 0;
  }
  while ( !readData && fscanf(file, "%s", tag) == 1 )
  {
    if ( ! strcmp(tag,label) )
    {
      readData = 1;
      for (i=0; i<npts; i++)
      {
        if (fscanf(file, "%f", data+i) != 1)
        {
          std::cerr << "ERROR: IO Error " << __FILE__ << ":" << __LINE__ << std::endl;
          return 0;
        }
        if ( data[i] < min ) min = data[i];
         if ( data[i] > min ) max = data[i]; // bug here
        // Should be:
        // if ( data[i] > max ) max = data[i]; 
      }
      // normalize data
      for (i=0; i<npts; i++) data[i] = min + data[i]/(max-min);
    }
    else
    {
      for (i=0; i<npts; i++)
      {
        if (fscanf(file, "%*f") != 0)
        {
          std::cerr << "ERROR: IO Error " << __FILE__ << ":" << __LINE__ << std::endl;
          return 0;
        }
      }
    }
  }

  if ( ! readData ) return 0;
  else return 1;
}
}

CMakeLists.txt¶

cmake_minimum_required(VERSION 3.3 FATAL_ERROR)

project(Finance)

find_package(VTK COMPONENTS 
  vtkCommonColor
  vtkCommonCore
  vtkCommonDataModel
  vtkFiltersCore
  vtkFiltersGeneral
  vtkImagingHybrid
  vtkInteractionStyle
  vtkRenderingCore
  vtkRenderingFreeType
  vtkRenderingOpenGL2 QUIET)
if (NOT VTK_FOUND)
  message("Skipping Finance: ${VTK_NOT_FOUND_MESSAGE}")
  return ()
endif()
message (STATUS "VTK_VERSION: ${VTK_VERSION}")
if (VTK_VERSION VERSION_LESS "8.90.0")
  # old system
  include(${VTK_USE_FILE})
  add_executable(Finance MACOSX_BUNDLE Finance.cxx )
  target_link_libraries(Finance PRIVATE ${VTK_LIBRARIES})
else ()
  # include all components
  add_executable(Finance MACOSX_BUNDLE Finance.cxx )
  target_link_libraries(Finance PRIVATE ${VTK_LIBRARIES})
  # vtk_module_autoinit is needed
  vtk_module_autoinit(
    TARGETS Finance
    MODULES ${VTK_LIBRARIES}
    )
endif ()

Download and Build Finance¶

Click here to download Finance and its CMakeLists.txt file. Once the tarball Finance.tar has been downloaded and extracted,

cd Finance/build

If VTK is installed:

cmake ..

If VTK is not installed but compiled on your system, you will need to specify the path to your VTK build:

cmake -DVTK_DIR:PATH=/home/me/vtk_build ..

Build the project:

make

and run it:

./Finance

WINDOWS USERS

Be sure to add the VTK bin directory to your path. This will resolve the VTK dll's at run time.