35#ifndef VIGRA_RF_ALGORITHM_HXX
36#define VIGRA_RF_ALGORITHM_HXX
67 int columnCount = std::distance(b, e);
68 int rowCount =
in.shape(0);
71 for(Iter iter = b; iter != e; ++iter, ++
ii)
73 columnVector(
out,
ii) = columnVector(
in, *iter);
101 template<
class Feature_t,
class Response_t>
110 return oob.oob_breiman;
126 typedef std::vector<int> FeatureList_t;
127 typedef std::vector<double> ErrorList_t;
128 typedef FeatureList_t::iterator Pivot_t;
167 vigra_precondition(std::distance(b, e) ==
static_cast<std::ptrdiff_t
>(
selected.size()),
168 "Number of features in ranking != number of features matrix");
224 std::map<typename ResponseT::value_type, int>
res_map;
225 std::vector<int>
cts;
227 for(
int ii = 0;
ii < response.shape(0); ++
ii)
239 /
double(response.shape(0));
294template<
class FeatureT,
class ResponseT,
class ErrorRateCallBack>
300 VariableSelectionResult::FeatureList_t & selected = result.
selected;
301 VariableSelectionResult::ErrorList_t & errors = result.
errors;
302 VariableSelectionResult::Pivot_t & pivot = result.pivot;
303 int featureCount = features.shape(1);
309 vigra_precondition(
static_cast<int>(selected.size()) == featureCount,
310 "forward_selection(): Number of features in Feature "
311 "matrix and number of features in previously used "
312 "result struct mismatch!");
320 VariableSelectionResult::Pivot_t next = pivot;
323 std::swap(*pivot, *next);
325 detail::choose( features,
331 std::swap(*pivot, *next);
337 std::advance(next, pos);
338 std::swap(*pivot, *next);
339 errors[std::distance(selected.begin(), pivot)] =
current_errors[pos];
342 std::cerr <<
"Choosing " << *pivot <<
" at error of " <<
current_errors[pos] << std::endl;
348template<
class FeatureT,
class ResponseT>
351 VariableSelectionResult & result)
396template<
class FeatureT,
class ResponseT,
class ErrorRateCallBack>
402 int featureCount = features.shape(1);
403 VariableSelectionResult::FeatureList_t & selected = result.
selected;
404 VariableSelectionResult::ErrorList_t & errors = result.
errors;
405 VariableSelectionResult::Pivot_t & pivot = result.pivot;
412 vigra_precondition(
static_cast<int>(selected.size()) == featureCount,
413 "backward_elimination(): Number of features in Feature "
414 "matrix and number of features in previously used "
415 "result struct mismatch!");
417 pivot = selected.end() - 1;
422 VariableSelectionResult::Pivot_t next = selected.begin();
426 std::swap(*pivot, *next);
428 detail::choose( features,
434 std::swap(*pivot, *next);
439 next = selected.begin();
440 std::advance(next, pos);
441 std::swap(*pivot, *next);
443 errors[std::distance(selected.begin(), pivot)-1] =
current_errors[pos];
447 std::cerr <<
"Eliminating " << *pivot <<
" at error of " <<
current_errors[pos] << std::endl;
453template<
class FeatureT,
class ResponseT>
456 VariableSelectionResult & result)
493template<
class FeatureT,
class ResponseT,
class ErrorRateCallBack>
499 VariableSelectionResult::FeatureList_t & selected = result.
selected;
500 VariableSelectionResult::ErrorList_t & errors = result.
errors;
501 VariableSelectionResult::Pivot_t & iter = result.pivot;
502 int featureCount = features.shape(1);
508 vigra_precondition(
static_cast<int>(selected.size()) == featureCount,
509 "forward_selection(): Number of features in Feature "
510 "matrix and number of features in previously used "
511 "result struct mismatch!");
514 for(; iter != selected.end(); ++iter)
517 detail::choose( features,
522 errors[std::distance(selected.begin(), iter)] =
error;
524 std::copy(selected.begin(), iter+1, std::ostream_iterator<int>(std::cerr,
", "));
525 std::cerr <<
"Choosing " << *(iter+1) <<
" at error of " <<
error << std::endl;
531template<
class FeatureT,
class ResponseT>
534 VariableSelectionResult & result)
541enum ClusterLeafTypes{c_Leaf = 95, c_Node = 99};
557 ClusterNode(
int nCol,
558 BT::T_Container_type & topology,
559 BT::P_Container_type & split_param)
560 : BT(nCol + 5, 5,topology, split_param)
570 ClusterNode( BT::T_Container_type
const & topology,
571 BT::P_Container_type
const & split_param,
573 :
NodeBase(5 , 5,topology, split_param, n)
579 ClusterNode( BT & node_)
584 BT::parameter_size_ += 0;
590 void set_index(
int in)
617 : parent(p), level(
l), addr(a), infm(
in)
646 double dist_func(
double a,
double b)
648 return std::min(a, b);
654 template<
class Functor>
658 std::vector<int>
stack;
659 stack.push_back(begin_addr);
660 while(!
stack.empty())
662 ClusterNode node(topology_, parameters_,
stack.back());
666 if(node.columns_size() != 1)
668 stack.push_back(node.child(0));
669 stack.push_back(node.child(1));
677 template<
class Functor>
681 std::queue<HC_Entry>
queue;
687 while(!
queue.empty())
689 level =
queue.front().level;
690 parent =
queue.front().parent;
691 addr =
queue.front().addr;
692 infm =
queue.front().infm;
693 ClusterNode node(topology_, parameters_,
queue.front().addr);
697 parnt = ClusterNode(topology_, parameters_, parent);
701 if(node.columns_size() != 1)
711 void save(std::string
file, std::string
prefix)
716 Shp(topology_.
size(),1),
720 Shp(parameters_.
size(), 1),
721 parameters_.data()));
731 template<
class T,
class C>
735 std::vector<std::pair<int, int> > addr;
737 for(
int ii = 0;
ii < distance.shape(0); ++
ii)
739 addr.push_back(std::make_pair(topology_.
size(),
ii));
740 ClusterNode
leaf(1, topology_, parameters_);
741 leaf.set_index(index);
743 leaf.columns_begin()[0] =
ii;
746 while(addr.size() != 1)
752 (addr.begin()+
jj_min)->second);
753 for(
unsigned int ii = 0;
ii < addr.
size(); ++
ii)
758 (addr.begin()+
jj_min)->second)
759 >
dist((addr.begin()+
ii)->second,
760 (addr.begin()+
jj)->second))
763 (addr.begin()+
jj)->second);
777 (addr.begin() +
ii_min)->first);
780 (addr.begin() +
jj_min)->first);
791 (addr.begin() +
ii_min)->first);
794 (addr.begin() +
jj_min)->first);
795 parent.parameters_begin()[0] =
min_dist;
796 parent.set_index(index);
800 parent.columns_begin());
804 if(*parent.columns_begin() == *
firstChild.columns_begin())
806 parent.child(0) = (addr.begin()+
ii_min)->first;
807 parent.child(1) = (addr.begin()+
jj_min)->first;
811 addr.erase(addr.begin()+
jj_min);
815 parent.child(1) = (addr.begin()+
ii_min)->first;
816 parent.child(0) = (addr.begin()+
jj_min)->first;
820 addr.erase(addr.begin()+
ii_min);
828 double bla = dist_func(
831 (addr.begin()+
jj)->second));
834 (addr.begin()+
jj)->second) =
bla;
835 dist((addr.begin()+
jj)->second,
857 bool operator()(Node& node)
870template<
class Iter,
class DT>
885 template<
class Feat_T,
class Label_T>
894 :tmp_mem_(_spl(a, b).size(),
feats.shape(1)),
897 feats_(_spl(a,b).size(),
feats.shape(1)),
898 labels_(_spl(a,b).size(),1),
904 copy_splice(_spl(a,b),
905 _spl(
feats.shape(1)),
908 copy_splice(_spl(a,b),
909 _spl(
labls.shape(1)),
915 bool operator()(Node& node)
919 int class_count = perm_imp.shape(1) - 1;
921 for(
int kk = 0;
kk < nPerm; ++
kk)
924 for(
int ii = 0;
ii < rowCount(feats_); ++
ii)
926 int index = random.uniformInt(rowCount(feats_) -
ii) +
ii;
927 for(
int jj = 0;
jj < node.columns_size(); ++
jj)
929 if(node.columns_begin()[
jj] != feats_.shape(1))
930 tmp_mem_(
ii, node.columns_begin()[
jj])
931 = tmp_mem_(index, node.columns_begin()[
jj]);
935 for(
int ii = 0;
ii < rowCount(tmp_mem_); ++
ii)
938 .predictLabel(rowVector(tmp_mem_,
ii))
942 ++perm_imp(index,labels_(
ii, 0));
944 ++perm_imp(index, class_count);
974 void save(std::string
file, std::string
prefix)
982 bool operator()(Node& node)
984 for(
int ii = 0;
ii < node.columns_size(); ++
ii)
999 bool operator()(
Nde &
cur,
int ,
Nde parent,
bool )
1002 cur.status() = std::min(parent.status(),
cur.status());
1029 std::ofstream graphviz;
1034 std::string
const gz)
1035 :features_(features), labels_(labels),
1036 graphviz(
gz.c_str(), std::ios::out)
1038 graphviz <<
"digraph G\n{\n node [shape=\"record\"]";
1042 graphviz <<
"\n}\n";
1047 bool operator()(
Nde &
cur,
int ,
Nde parent,
bool )
1049 graphviz <<
"node" <<
cur.index() <<
" [style=\"filled\"][label = \" #Feats: "<<
cur.columns_size() <<
"\\n";
1050 graphviz <<
" status: " <<
cur.status() <<
"\\n";
1051 for(
int kk = 0;
kk <
cur.columns_size(); ++
kk)
1053 graphviz <<
cur.columns_begin()[
kk] <<
" ";
1057 graphviz <<
"\"] [color = \"" <<
cur.status() <<
" 1.000 1.000\"];\n";
1059 graphviz <<
"\"node" << parent.index() <<
"\" -> \"node" <<
cur.index() <<
"\";\n";
1079 int repetition_count_;
1085 void save(std::string filename, std::string
prefix)
1105 template<
class RF,
class PR>
1108 Int32 const class_count = rf.ext_param_.class_count_;
1109 Int32 const column_count = rf.ext_param_.column_count_+1;
1130 template<
class RF,
class PR,
class SM,
class ST>
1134 Int32 column_count = rf.ext_param_.column_count_ +1;
1135 Int32 class_count = rf.ext_param_.class_count_;
1139 typename PR::Feature_t & features
1140 =
const_cast<typename PR::Feature_t &
>(
pr.features());
1144 ArrayVector<Int32>::iterator
1147 if(rf.ext_param_.actual_msample_ <
pr.features().shape(0)- 10000)
1151 for(
int ii = 0;
ii <
pr.features().shape(0); ++
ii)
1152 indices.push_back(
ii); ;
1153 std::random_device rd;
1154 std::mt19937 g(rd());
1155 std::shuffle(indices.
begin(), indices.
end(), g);
1156 for(
int ii = 0;
ii < rf.ext_param_.row_count_; ++
ii)
1158 if(!
sm.is_used()[indices[
ii]] &&
cts[
pr.response()(indices[
ii], 0)] < 3000)
1161 ++
cts[
pr.response()(indices[
ii], 0)];
1167 for(
int ii = 0;
ii < rf.ext_param_.row_count_; ++
ii)
1168 if(!
sm.is_used()[
ii])
1187 .predictLabel(rowVector(features, *iter))
1188 ==
pr.response()(*iter, 0))
1224 template<
class RF,
class PR,
class SM,
class ST>
1232 template<
class RF,
class PR>
1272template<
class FeatureT,
class ResponseT>
1280 opt.tree_count(100);
1281 if(features.shape(0) > 40000)
1282 opt.samples_per_tree(20000).use_stratification(RF_EQUAL);
1288 RF.learn(features, response,
1290 distance =
missc.distance;
1317template<
class FeatureT,
class ResponseT>
1327template<
class Array1,
class Vector1>
1330 std::map<double, int>
mymap;
1333 for(std::map<double, int>::reverse_iterator iter =
mymap.rbegin(); iter!=
mymap.rend(); ++iter)
1335 out.push_back(iter->second);
void reshape(const difference_type &shape)
Definition multi_array.hxx:2863
Topology_type column_data() const
Definition rf_nodeproxy.hxx:159
INT & typeID()
Definition rf_nodeproxy.hxx:136
NodeBase()
Definition rf_nodeproxy.hxx:237
Parameter_type parameters_begin() const
Definition rf_nodeproxy.hxx:207
Class for a single RGB value.
Definition rgbvalue.hxx:128
Options object for the random forest.
Definition rf_common.hxx:171
size_type size() const
Definition tinyvector.hxx:913
iterator end()
Definition tinyvector.hxx:864
iterator begin()
Definition tinyvector.hxx:861
Class for fixed size vectors.
Definition tinyvector.hxx:1008
Definition rf_algorithm.hxx:1067
MultiArray< 2, double > cluster_importance_
Definition rf_algorithm.hxx:1075
MultiArray< 2, int > variables
Definition rf_algorithm.hxx:1072
void visit_at_end(RF &rf, PR &)
Definition rf_algorithm.hxx:1233
void visit_after_tree(RF &rf, PR &pr, SM &sm, ST &st, int index)
Definition rf_algorithm.hxx:1225
MultiArray< 2, double > cluster_stdev_
Definition rf_algorithm.hxx:1078
void after_tree_ip_impl(RF &rf, PR &pr, SM &sm, ST &, int index)
Definition rf_algorithm.hxx:1131
void visit_at_beginning(RF const &rf, PR const &)
Definition rf_algorithm.hxx:1106
Definition rf_algorithm.hxx:996
Definition rf_algorithm.hxx:1024
Definition rf_algorithm.hxx:963
MultiArrayView< 2, int > variables
Definition rf_algorithm.hxx:968
Definition rf_algorithm.hxx:638
void iterate(Functor &tester)
Definition rf_algorithm.hxx:655
void cluster(MultiArrayView< 2, T, C > distance)
Definition rf_algorithm.hxx:732
void breadth_first_traversal(Functor &tester)
Definition rf_algorithm.hxx:678
Definition rf_algorithm.hxx:847
NormalizeStatus(double m)
Definition rf_algorithm.hxx:853
Definition rf_algorithm.hxx:872
Definition rf_algorithm.hxx:85
double operator()(Feature_t const &features, Response_t const &response)
Definition rf_algorithm.hxx:102
RFErrorCallback(RandomForestOptions opt=RandomForestOptions())
Definition rf_algorithm.hxx:94
Definition rf_algorithm.hxx:118
double no_features
Definition rf_algorithm.hxx:152
ErrorList_t errors
Definition rf_algorithm.hxx:147
FeatureList_t selected
Definition rf_algorithm.hxx:134
bool init(FeatureT const &all_features, ResponseT const &response, ErrorRateCallBack errorcallback)
Definition rf_algorithm.hxx:206
Definition rf_visitors.hxx:1494
Definition rf_visitors.hxx:865
Definition rf_visitors.hxx:1458
Definition rf_visitors.hxx:103
void backward_elimination(FeatureT const &features, ResponseT const &response, VariableSelectionResult &result, ErrorRateCallBack errorcallback)
Definition rf_algorithm.hxx:397
void rank_selection(FeatureT const &features, ResponseT const &response, VariableSelectionResult &result, ErrorRateCallBack errorcallback)
Definition rf_algorithm.hxx:494
void forward_selection(FeatureT const &features, ResponseT const &response, VariableSelectionResult &result, ErrorRateCallBack errorcallback)
Definition rf_algorithm.hxx:295
void cluster_permutation_importance(FeatureT const &features, ResponseT const &response, HClustering &linkage, MultiArray< 2, double > &distance)
Definition rf_algorithm.hxx:1273
detail::VisitorNode< A > create_visitor(A &a)
Definition rf_visitors.hxx:345
void writeHDF5(...)
Store array data in an HDF5 file.
detail::SelectIntegerType< 32, detail::SignedIntTypes >::type Int32
32-bit signed int
Definition sized_int.hxx:175
Definition metaprogramming.hxx:123
Definition rf_algorithm.hxx:611