PLearn 0.1
Public Member Functions | Static Public Member Functions | Static Public Attributes | Private Types | Private Member Functions | Private Attributes
PLearn::RegressionTreeQueue Class Reference

#include <RegressionTreeQueue.h>

Inheritance diagram for PLearn::RegressionTreeQueue:
Inheritance graph
[legend]
Collaboration diagram for PLearn::RegressionTreeQueue:
Collaboration graph
[legend]

List of all members.

Public Member Functions

 RegressionTreeQueue ()
 RegressionTreeQueue (int verbosity, int maximum_number_of_nodes)
virtual ~RegressionTreeQueue ()
virtual string classname () const
virtual OptionListgetOptionList () const
virtual OptionMapgetOptionMap () const
virtual RemoteMethodMapgetRemoteMethodMap () const
virtual RegressionTreeQueuedeepCopy (CopiesMap &copies) const
virtual void makeDeepCopyFromShallowCopy (CopiesMap &copies)
 Does the necessary operations to transform a shallow copy (this) into a deep copy by deep-copying all the members that need to be.
virtual void build ()
 Post-constructor.
void addHeap (PP< RegressionTreeNode > new_node)
PP< RegressionTreeNodepopHeap ()
PP< RegressionTreeNodeupHeap (PP< RegressionTreeNode > new_node, int node_ind)
PP< RegressionTreeNodedownHeap (PP< RegressionTreeNode > new_node, int node_ind)
int isEmpty ()
int compareNode (PP< RegressionTreeNode > node1, PP< RegressionTreeNode > node2)

Static Public Member Functions

static string _classname_ ()
static OptionList_getOptionList_ ()
static RemoteMethodMap_getRemoteMethodMap_ ()
static Object_new_instance_for_typemap_ ()
static bool _isa_ (const Object *o)
static void _static_initialize_ ()
static const PPathdeclaringFile ()
static void declareOptions (OptionList &ol)
 Declare options (data fields) for the class.

Static Public Attributes

static StaticInitializer _static_initializer_

Private Types

typedef Object inherited

Private Member Functions

void build_ ()
 Object-specific post-constructor.
void verbose (string msg, int level)

Private Attributes

int verbosity
int maximum_number_of_nodes
int next_available_node
TVec< PP< RegressionTreeNode > > nodes

Detailed Description

Definition at line 51 of file RegressionTreeQueue.h.


Member Typedef Documentation

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.h.


Constructor & Destructor Documentation

PLearn::RegressionTreeQueue::RegressionTreeQueue ( )

Definition at line 55 of file RegressionTreeQueue.cc.

References build().

Here is the call graph for this function:

PLearn::RegressionTreeQueue::RegressionTreeQueue ( int  verbosity,
int  maximum_number_of_nodes 
)

Definition at line 62 of file RegressionTreeQueue.cc.

References build().

    : verbosity(verbosity_),
      maximum_number_of_nodes(maximum_number_of_nodes_),
      next_available_node(0)
{
    build();
}

Here is the call graph for this function:

PLearn::RegressionTreeQueue::~RegressionTreeQueue ( ) [virtual]

Definition at line 70 of file RegressionTreeQueue.cc.

{
}

Member Function Documentation

string PLearn::RegressionTreeQueue::_classname_ ( ) [static]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

OptionList & PLearn::RegressionTreeQueue::_getOptionList_ ( ) [static]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

RemoteMethodMap & PLearn::RegressionTreeQueue::_getRemoteMethodMap_ ( ) [static]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

bool PLearn::RegressionTreeQueue::_isa_ ( const Object o) [static]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

Object * PLearn::RegressionTreeQueue::_new_instance_for_typemap_ ( ) [static]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

StaticInitializer RegressionTreeQueue::_static_initializer_ & PLearn::RegressionTreeQueue::_static_initialize_ ( ) [static]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

void PLearn::RegressionTreeQueue::addHeap ( PP< RegressionTreeNode new_node)

Definition at line 108 of file RegressionTreeQueue.cc.

References maximum_number_of_nodes, next_available_node, nodes, PLERROR, PLearn::tostring(), and upHeap().

{
    if (new_node->getErrorImprovment() < 0.0)
    {
        return;
    }
    if (next_available_node >= maximum_number_of_nodes){
        string s = "RegressionTreeQueue: maximum number of entries exceeded ("
            +tostring(maximum_number_of_nodes)+")";
        PLERROR(s.c_str());
    }
    nodes[next_available_node] = upHeap(new_node, next_available_node);
    next_available_node += 1;
}

Here is the call graph for this function:

void PLearn::RegressionTreeQueue::build ( ) [virtual]

Post-constructor.

The normal implementation should call simply inherited::build(), then this class's build_(). This method should be callable again at later times, after modifying some option fields to change the "architecture" of the object.

Reimplemented from PLearn::Object.

Definition at line 97 of file RegressionTreeQueue.cc.

References PLearn::Object::build(), and build_().

Referenced by RegressionTreeQueue().

Here is the call graph for this function:

Here is the caller graph for this function:

void PLearn::RegressionTreeQueue::build_ ( ) [private]

Object-specific post-constructor.

This method should be redefined in subclasses and do the actual building of the object according to previously set option fields. Constructors can just set option fields, and then call build_. This method is NOT virtual, and will typically be called only from three places: a constructor, the public virtual build() method, and possibly the public virtual read method (which calls its parent's read). build_() can assume that its parent's build_() has already been called.

Reimplemented from PLearn::Object.

Definition at line 103 of file RegressionTreeQueue.cc.

References maximum_number_of_nodes, nodes, and PLearn::TVec< T >::resize().

Referenced by build().

Here is the call graph for this function:

Here is the caller graph for this function:

string PLearn::RegressionTreeQueue::classname ( ) const [virtual]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

int PLearn::RegressionTreeQueue::compareNode ( PP< RegressionTreeNode node1,
PP< RegressionTreeNode node2 
)

Definition at line 177 of file RegressionTreeQueue.cc.

Referenced by downHeap(), and upHeap().

{
    if (node1->getErrorImprovment() > node2->getErrorImprovment()) return -1;
    if (node1->getErrorImprovment() < node2->getErrorImprovment()) return +1;
    if (node1->getSplitBalance() < node2->getSplitBalance()) return -1;
    return +1;
}

Here is the caller graph for this function:

void PLearn::RegressionTreeQueue::declareOptions ( OptionList ol) [static]

Declare options (data fields) for the class.

Redefine this in subclasses: call declareOption(...) for each option, and then call inherited::declareOptions(options). Please call the inherited method AT THE END to get the options listed in a consistent order (from most recently defined to least recently defined).

  static void MyDerivedClass::declareOptions(OptionList& ol)
  {
      declareOption(ol, "inputsize", &MyObject::inputsize_,
                    OptionBase::buildoption,
                    "The size of the input; it must be provided");
      declareOption(ol, "weights", &MyObject::weights,
                    OptionBase::learntoption,
                    "The learned model weights");
      inherited::declareOptions(ol);
  }
Parameters:
olList of options that is progressively being constructed for the current class.

Reimplemented from PLearn::Object.

Definition at line 74 of file RegressionTreeQueue.cc.

References PLearn::OptionBase::buildoption, PLearn::declareOption(), PLearn::Object::declareOptions(), PLearn::OptionBase::learntoption, maximum_number_of_nodes, next_available_node, nodes, and verbosity.

{ 
    declareOption(ol, "verbosity", &RegressionTreeQueue::verbosity, OptionBase::buildoption,
                  "The desired level of verbosity\n");
    declareOption(ol, "maximum_number_of_nodes", &RegressionTreeQueue::maximum_number_of_nodes, OptionBase::buildoption,
                  "The maximum number of entries in the heap\n");
 
    declareOption(ol, "next_available_node", &RegressionTreeQueue::next_available_node, OptionBase::learntoption,
                  "The next available entry in the heap to add a node\n");
    declareOption(ol, "nodes", &RegressionTreeQueue::nodes, OptionBase::learntoption,
                  "The table of nodes kept with the best possible one to split on top\n");
    inherited::declareOptions(ol);
}

Here is the call graph for this function:

static const PPath& PLearn::RegressionTreeQueue::declaringFile ( ) [inline, static]

Reimplemented from PLearn::Object.

Definition at line 77 of file RegressionTreeQueue.h.

:
    void         build_();
RegressionTreeQueue * PLearn::RegressionTreeQueue::deepCopy ( CopiesMap copies) const [virtual]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

PP< RegressionTreeNode > PLearn::RegressionTreeQueue::downHeap ( PP< RegressionTreeNode new_node,
int  node_ind 
)

Definition at line 147 of file RegressionTreeQueue.cc.

References compareNode(), next_available_node, and nodes.

Referenced by popHeap().

{
    int left_child_node;
    int right_child_node;
    int smallest_child_node;
    PP<RegressionTreeNode> saved_node;
    left_child_node = 2 * node_ind + 1;
    if (left_child_node >= next_available_node) return new_node;
    right_child_node = 2 * node_ind + 2;
    smallest_child_node = left_child_node;
    if (right_child_node < next_available_node)
    {
        if (compareNode(nodes[left_child_node], nodes[right_child_node]) > 0)
        {
            smallest_child_node = right_child_node;
        }
    }
    if (compareNode(new_node, nodes[smallest_child_node]) > 0)    
    {
        saved_node = nodes[smallest_child_node];
        nodes[smallest_child_node] = downHeap(new_node, smallest_child_node);
        return saved_node;      
    }
    return new_node;
}

Here is the call graph for this function:

Here is the caller graph for this function:

OptionList & PLearn::RegressionTreeQueue::getOptionList ( ) const [virtual]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

OptionMap & PLearn::RegressionTreeQueue::getOptionMap ( ) const [virtual]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

RemoteMethodMap & PLearn::RegressionTreeQueue::getRemoteMethodMap ( ) const [virtual]

Reimplemented from PLearn::Object.

Definition at line 53 of file RegressionTreeQueue.cc.

int PLearn::RegressionTreeQueue::isEmpty ( )

Definition at line 172 of file RegressionTreeQueue.cc.

References next_available_node.

{
    return next_available_node;
}
void PLearn::RegressionTreeQueue::makeDeepCopyFromShallowCopy ( CopiesMap copies) [virtual]

Does the necessary operations to transform a shallow copy (this) into a deep copy by deep-copying all the members that need to be.

This needs to be overridden by every class that adds "complex" data members to the class, such as Vec, Mat, PP<Something>, etc. Typical implementation:

  void CLASS_OF_THIS::makeDeepCopyFromShallowCopy(CopiesMap& copies)
  {
      inherited::makeDeepCopyFromShallowCopy(copies);
      deepCopyField(complex_data_member1, copies);
      deepCopyField(complex_data_member2, copies);
      ...
  }
Parameters:
copiesA map used by the deep-copy mechanism to keep track of already-copied objects.

Reimplemented from PLearn::Object.

Definition at line 88 of file RegressionTreeQueue.cc.

References PLearn::deepCopyField(), PLearn::Object::makeDeepCopyFromShallowCopy(), maximum_number_of_nodes, next_available_node, nodes, and verbosity.

Here is the call graph for this function:

PP< RegressionTreeNode > PLearn::RegressionTreeQueue::popHeap ( )

Definition at line 123 of file RegressionTreeQueue.cc.

References downHeap(), next_available_node, and nodes.

{
    PP<RegressionTreeNode> return_value;
    return_value = nodes[0];
    next_available_node -= 1;
    nodes[0] = downHeap(nodes[next_available_node], 0);
    return return_value;
}

Here is the call graph for this function:

PP< RegressionTreeNode > PLearn::RegressionTreeQueue::upHeap ( PP< RegressionTreeNode new_node,
int  node_ind 
)

Definition at line 132 of file RegressionTreeQueue.cc.

References compareNode(), and nodes.

Referenced by addHeap().

{
    int parent_node;
    PP<RegressionTreeNode> saved_node;
    if (node_ind == 0) return new_node;
    parent_node = (node_ind - 1) / 2;
    if (compareNode(new_node, nodes[parent_node]) < 0)
    {
        saved_node = nodes[parent_node];
        nodes[parent_node] = upHeap(new_node, parent_node);
        return saved_node;      
    }
    return new_node;
}

Here is the call graph for this function:

Here is the caller graph for this function:

void PLearn::RegressionTreeQueue::verbose ( string  msg,
int  level 
) [private]

Definition at line 185 of file RegressionTreeQueue.cc.

References PLearn::endl(), and verbosity.

{
    if (verbosity >= the_level)
        cout << the_msg << endl;
}

Here is the call graph for this function:


Member Data Documentation

Reimplemented from PLearn::Object.

Definition at line 77 of file RegressionTreeQueue.h.

Definition at line 62 of file RegressionTreeQueue.h.

Referenced by addHeap(), build_(), declareOptions(), and makeDeepCopyFromShallowCopy().

Definition at line 61 of file RegressionTreeQueue.h.

Referenced by declareOptions(), makeDeepCopyFromShallowCopy(), and verbose().


The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines