Skip to content
GitLab
Select Git revision
  • master default
Find file BlameHistoryPermalink
  • Bonte Bruno's avatar
    Add features for using R to couple models · f050aa02
    Bonte Bruno authored 
    	* Cormas: A dedicated identifier function in Entity Class (in Add-ons)
	* Cormas: A change in setAttributeofClassvalue function (in Add-ons) to set or to get values of attribute of all instances of a class
	* Cormas: A spectial class to do this (DataTansfR in Add-ons)
	* R: functions to call theses cormas functions in cormas-func.R
    f050aa02
otbVectorDimensionalityReduction.cxx 13.96 KiB
1 
/*
2 
* Copyright (C) 2005-2017 Centre National d'Etudes Spatiales (CNES)
3 
*
4 
* This file is part of Orfeo Toolbox
5 
*
6 
* https://www.orfeo-toolbox.org/
7 
*
8 
* Licensed under the Apache License, Version 2.0 (the "License");
9 
* you may not use this file except in compliance with the License.
10 
* You may obtain a copy of the License at
11 
*
12 
* http://www.apache.org/licenses/LICENSE-2.0
13 
*
14 
* Unless required by applicable law or agreed to in writing, software
15 
* distributed under the License is distributed on an "AS IS" BASIS,
16 
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17 
* See the License for the specific language governing permissions and
18 
* limitations under the License.
19 
*/
20
21 
#include "otbWrapperApplication.h"
22 
#include "otbWrapperApplicationFactory.h"
23 
#include "otbOGRDataSourceWrapper.h"
24 
#include "otbOGRFeatureWrapper.h"
25 
#include "itkVariableLengthVector.h"
26 
#include "otbStatisticsXMLFileReader.h"
27 
#include "itkListSample.h"
28 
#include "otbShiftScaleSampleListFilter.h"
29 
#include "otbDimensionalityReductionModelFactory.h"
30 
#include <time.h>
31
32 
namespace otb
33 
{
34 
namespace Wrapper
35 
{
36
37 
/** Utility function to negate std::isalnum */
38 
bool IsNotAlphaNum(char c)
39 
{
40 
return !std::isalnum(c);
41 
}
42
43 
class VectorDimensionalityReduction : public Application
44 
{
45 
	public:
46
47 
		/** Standard class typedefs. */
48 
  typedef VectorDimensionalityReduction Self;
49 
  typedef Application Superclass;
50 
		typedef itk::SmartPointer<Self> Pointer;
51 
		typedef itk::SmartPointer<const Self> ConstPointer;
52
53 
		/** Standard macro */
54 
		itkNewMacro(Self);
55 
		itkTypeMacro(Self, Application)
56
57 
		/** Filters typedef */
58
59 
		typedef float 															ValueType;
60 
		typedef itk::VariableLengthVector<ValueType> 							InputSampleType;
61 
		typedef itk::Statistics::ListSample<InputSampleType> 					ListSampleType;
62 
		typedef MachineLearningModel<itk::VariableLengthVector<ValueType>, itk::VariableLengthVector<ValueType>>	DimensionalityReductionModelType;
63 
		typedef DimensionalityReductionModelFactory<ValueType,ValueType> 		DimensionalityReductionModelFactoryType;
64 
		typedef DimensionalityReductionModelType::Pointer 						ModelPointerType;
65
66 
		/** Statistics Filters typedef */
67 
		typedef itk::VariableLengthVector<ValueType> 										MeasurementType;
68 
		typedef otb::StatisticsXMLFileReader<MeasurementType> 								StatisticsReader;
69 
		typedef otb::Statistics::ShiftScaleSampleListFilter<ListSampleType, ListSampleType> ShiftScaleFilterType;
70 
  ~VectorDimensionalityReduction() ITK_OVERRIDE
7172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140
{ DimensionalityReductionModelFactoryType::CleanFactories(); } private: void DoInit() ITK_OVERRIDE { SetName("VectorDimensionalityReduction"); SetDescription("Performs dimensionality reduction of the input vector data according to a model file."); SetDocName("Vector Dimensionality Reduction"); SetDocAuthors("OTB-Team"); SetDocLongDescription("This application performs a vector data dimensionality reduction based on a model file produced by the TrainDimensionalityReduction application."); SetDocSeeAlso("TrainDimensionalityReduction"); AddDocTag(Tags::Learning); AddParameter(ParameterType_InputVectorData, "in", "Name of the input vector data"); SetParameterDescription("in","The input vector data to reduce."); AddParameter(ParameterType_InputFilename, "instat", "Statistics file"); SetParameterDescription("instat", "A XML file containing mean and standard deviation to center" "and reduce samples before dimensionality reduction (produced by ComputeImagesStatistics application)."); MandatoryOff("instat"); AddParameter(ParameterType_InputFilename, "model", "Model file"); SetParameterDescription("model", "A model file (produced by the TrainDimensionalityReduction application,"); AddParameter(ParameterType_ListView, "feat", "Field names to be calculated."); // SetParameterDescription("feat","List of field names in the input vector data used as features for reduction."); // AddParameter(ParameterType_StringList, "featout", "Field names to be calculated."); // SetParameterDescription("featout","List of field names in the input vector data used as features for reduction."); // AddParameter(ParameterType_OutputFilename, "out", "Output vector data file containing the reduced vector"); SetParameterDescription("out","Output vector data file storing sample values (OGR format)." "If not given, the input vector data file is updated."); MandatoryOff("out"); AddParameter(ParameterType_Int, "indim", "Dimension of the input vector"); SetParameterDescription("indim","Dimension of the whole input vector, this value is required if only a part of the bands contained in the vector are used." "If not given, the dimension is deduced from the length of the 'feat' parameter"); MandatoryOff("indim"); AddParameter(ParameterType_Int, "pcadim", "Principal component"); // SetParameterDescription("pcadim","This optional parameter can be set to reduce the number of eignevectors used in the PCA model file."); // MandatoryOff("pcadim"); AddParameter(ParameterType_String, "mode", "Writting mode"); // SetParameterString("mode","overwrite", false); SetParameterDescription("mode","This parameter determines if the output file is overwritten or updated [overwrite/update]"); // // Doc example parameter settings SetDocExampleParameterValue("in", "vectorData.shp"); SetDocExampleParameterValue("instat", "meanVar.xml"); SetDocExampleParameterValue("model", "model.txt"); SetDocExampleParameterValue("out", "vectorDataOut.shp"); SetDocExampleParameterValue("feat", "perimeter area width"); SetDocExampleParameterValue("featout", "perimeter area width"); //SetOfficialDocLink(); } // void DoUpdateParameters() ITK_OVERRIDE { if ( HasValue("in") ) { std::string shapefile = GetParameterString("in"); otb::ogr::DataSource::Pointer ogrDS;
141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210
OGRSpatialReference oSRS(""); std::vector<std::string> options; ogrDS = otb::ogr::DataSource::New(shapefile, otb::ogr::DataSource::Modes::Read); otb::ogr::Layer layer = ogrDS->GetLayer(0); OGRFeatureDefn &layerDefn = layer.GetLayerDefn(); ClearChoices("feat"); //ClearChoices("featout"); for(int iField=0; iField< layerDefn.GetFieldCount(); iField++) { std::string item = layerDefn.GetFieldDefn(iField)->GetNameRef(); std::string key(item); std::string::iterator end = std::remove_if( key.begin(), key.end(), IsNotAlphaNum ); std::transform( key.begin(), end, key.begin(), tolower ); /* key.erase( std::remove_if(key.begin(),key.end(),IsNotAlphaNum), key.end()); std::transform(key.begin(), key.end(), key.begin(), tolower);*/ OGRFieldType fieldType = layerDefn.GetFieldDefn(iField)->GetType(); /* if(fieldType == OFTInteger || ogr::version_proxy::IsOFTInteger64(fieldType) || fieldType == OFTReal) {*/ //std::string tmpKey="feat."+key; std::string tmpKey = "feat." + key.substr( 0, static_cast<unsigned long>( end - key.begin() ) ); AddChoice(tmpKey,item); //} // this is the same as in otbVectorClassifier, but it doesnt work } } } void DoExecute() ITK_OVERRIDE { clock_t tic = clock(); std::string shapefile = GetParameterString("in"); otb::ogr::DataSource::Pointer source = otb::ogr::DataSource::New(shapefile, otb::ogr::DataSource::Modes::Read); otb::ogr::Layer layer = source->GetLayer(0); ListSampleType::Pointer input = ListSampleType::New(); int nbFeatures = GetSelectedItems("feat").size(); input->SetMeasurementVectorSize(nbFeatures); otb::ogr::Layer::const_iterator it = layer.cbegin(); otb::ogr::Layer::const_iterator itEnd = layer.cend(); for( ; it!=itEnd ; ++it) { MeasurementType mv; mv.SetSize(nbFeatures); for(int idx=0; idx < nbFeatures; ++idx) { mv[idx] = static_cast<float>( (*it)[GetSelectedItems("feat")[idx]].GetValue<double>() ); } input->PushBack(mv); } /** Statistics for shift/scale */ MeasurementType meanMeasurementVector; MeasurementType stddevMeasurementVector; if (HasValue("instat") && IsParameterEnabled("instat")) { StatisticsReader::Pointer statisticsReader = StatisticsReader::New(); std::string XMLfile = GetParameterString("instat"); statisticsReader->SetFileName(XMLfile);
211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280
meanMeasurementVector = statisticsReader->GetStatisticVectorByName("mean"); stddevMeasurementVector = statisticsReader->GetStatisticVectorByName("stddev"); } else { meanMeasurementVector.SetSize(nbFeatures); meanMeasurementVector.Fill(0.); stddevMeasurementVector.SetSize(nbFeatures); stddevMeasurementVector.Fill(1.); } ShiftScaleFilterType::Pointer trainingShiftScaleFilter = ShiftScaleFilterType::New(); trainingShiftScaleFilter->SetInput(input); trainingShiftScaleFilter->SetShifts(meanMeasurementVector); trainingShiftScaleFilter->SetScales(stddevMeasurementVector); trainingShiftScaleFilter->Update(); otbAppLogINFO("mean used: " << meanMeasurementVector); otbAppLogINFO("standard deviation used: " << stddevMeasurementVector); otbAppLogINFO("Loading model"); /** Read the model */ m_Model = DimensionalityReductionModelFactoryType::CreateDimensionalityReductionModel(GetParameterString("model"), DimensionalityReductionModelFactoryType::ReadMode); if (m_Model.IsNull()) { otbAppLogFATAL(<< "Error when loading model " << GetParameterString("model") << " : unsupported model type"); } if (HasValue("pcadim") && IsParameterEnabled("pcadim")) { int dimension = GetParameterInt("pcadim"); m_Model->SetDimension(dimension ); } m_Model->Load(GetParameterString("model")); otbAppLogINFO("Model loaded"); /** Perform Dimensionality Reduction */ ListSampleType::Pointer listSample = trainingShiftScaleFilter->GetOutput(); ListSampleType::Pointer target = m_Model->PredictBatch(listSample); /** Create/Update Output Shape file */ std::cout << GetParameterStringList("featout").size() << std::endl; ogr::DataSource::Pointer output; ogr::DataSource::Pointer buffer = ogr::DataSource::New(); bool updateMode = false; int nbBands = nbFeatures; if (HasValue("indim") && IsParameterEnabled("indim")) {nbBands = GetParameterInt("indim");} if (IsParameterEnabled("out") && HasValue("out")) { // Create new OGRDataSource if (GetParameterString("mode")=="overwrite") { output = ogr::DataSource::New(GetParameterString("out"), ogr::DataSource::Modes::Overwrite); otb::ogr::Layer newLayer = output->CreateLayer(GetParameterString("out"), const_cast<OGRSpatialReference*>(layer.GetSpatialRef()), layer.GetGeomType()); // Copy existing fields OGRFeatureDefn &inLayerDefn = layer.GetLayerDefn(); for (int k=0 ; k<inLayerDefn.GetFieldCount()-nbBands ; k++) // we don't copy the original bands {
281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350
OGRFieldDefn fieldDefn(inLayerDefn.GetFieldDefn(k)); newLayer.CreateField(fieldDefn); } } else if (GetParameterString("mode")=="update") { //output = ogr::DataSource::New(GetParameterString("out"), ogr::DataSource::Modes::Update_LayerCreateOnly); // Update mode otb::ogr::DataSource::Pointer source_output = otb::ogr::DataSource::New(GetParameterString("out"), otb::ogr::DataSource::Modes::Read); layer = source_output->GetLayer(0); updateMode = true; otbAppLogINFO("Update input vector data."); // fill temporary buffer for the transfer otb::ogr::Layer inputLayer = layer; layer = buffer->CopyLayer(inputLayer, std::string("Buffer")); // close input data source source_output->Clear(); // Re-open input data source in update mode output = otb::ogr::DataSource::New(GetParameterString("out"), otb::ogr::DataSource::Modes::Update_LayerUpdate); } else { otbAppLogFATAL(<< "Error when creating the output file" << GetParameterString("mode") << " : unsupported writting mode type"); } } otb::ogr::Layer outLayer = output->GetLayer(0); OGRErr errStart = outLayer.ogr().StartTransaction(); if (errStart != OGRERR_NONE) { itkExceptionMacro(<< "Unable to start transaction for OGR layer " << outLayer.ogr().GetName() << "."); } // Add the field of prediction in the output layer if field not exist for (int i=0; i<GetParameterStringList("featout").size() ;i++) { OGRFeatureDefn &layerDefn = outLayer.GetLayerDefn(); int idx = layerDefn.GetFieldIndex(GetParameterStringList("featout")[i].c_str()); if (idx >= 0) { if (layerDefn.GetFieldDefn(idx)->GetType() != OFTReal) itkExceptionMacro("Field name "<< GetParameterStringList("featout")[i] << " already exists with a different type!"); } else { OGRFieldDefn predictedField(GetParameterStringList("featout")[i].c_str(), OFTReal); ogr::FieldDefn predictedFieldDef(predictedField); outLayer.CreateField(predictedFieldDef); } } // Fill output layer unsigned int count=0; auto classfieldname = GetParameterStringList("featout"); it = layer.cbegin(); itEnd = layer.cend();
351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391
for( ; it!=itEnd ; ++it, ++count) { ogr::Feature dstFeature(outLayer.GetLayerDefn()); dstFeature.SetFrom( *it , TRUE); dstFeature.SetFID(it->GetFID()); for (std::size_t i=0; i<classfieldname.size(); ++i){ dstFeature[classfieldname[i]].SetValue<double>(target->GetMeasurementVector(count)[i]); } if (updateMode) { outLayer.SetFeature(dstFeature); } else { outLayer.CreateFeature(dstFeature); } } if(outLayer.ogr().TestCapability("Transactions")) { const OGRErr errCommitX = outLayer.ogr().CommitTransaction(); if (errCommitX != OGRERR_NONE) { itkExceptionMacro(<< "Unable to commit transaction for OGR layer " << outLayer.ogr().GetName() << "."); } } output->SyncToDisk(); clock_t toc = clock(); otbAppLogINFO( "Elapsed: "<< ((double)(toc - tic) / CLOCKS_PER_SEC)<<" seconds."); } ModelPointerType m_Model; }; } } OTB_APPLICATION_EXPORT(otb::Wrapper::VectorDimensionalityReduction)