PLearn 0.1
|
The first sentence should be a BRIEF DESCRIPTION of what the class does. More...
#include <KFoldLogisticClassifier.h>
Public Member Functions | |
KFoldLogisticClassifier () | |
Default constructor. | |
virtual int | outputsize () const |
Returns the size of this learner's output, (which typically may depend on its inputsize(), targetsize() and set options). | |
virtual void | forget () |
(Re-)initializes the PLearner in its fresh state (that state may depend on the 'seed' option) and sets 'stage' back to 0 (this is the stage of a fresh learner!). | |
virtual void | train () |
The role of the train method is to bring the learner up to stage==nstages, updating the train_stats collector with training costs measured on-line in the process. | |
virtual void | computeOutput (const Vec &input, Vec &output) const |
Computes the output from the input. | |
virtual void | computeCostsFromOutputs (const Vec &input, const Vec &output, const Vec &target, Vec &costs) const |
Computes the costs from already computed output. | |
virtual TVec< std::string > | getTestCostNames () const |
Returns the names of the costs computed by computeCostsFromOutpus (and thus the test method). | |
virtual TVec< std::string > | getTrainCostNames () const |
Returns the names of the objective costs that the train method computes and for which it updates the VecStatsCollector train_stats. | |
virtual string | classname () const |
virtual OptionList & | getOptionList () const |
virtual OptionMap & | getOptionMap () const |
virtual RemoteMethodMap & | getRemoteMethodMap () const |
virtual KFoldLogisticClassifier * | deepCopy (CopiesMap &copies) const |
virtual void | build () |
Finish building the object; just call inherited::build followed by build_() | |
virtual void | makeDeepCopyFromShallowCopy (CopiesMap &copies) |
Transforms a shallow copy into a deep copy. | |
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 PPath & | declaringFile () |
Public Attributes | |
int | kfold |
int | max_degraded_steps |
int | max_epochs |
int | step_size |
Static Public Attributes | |
static StaticInitializer | _static_initializer_ |
Static Protected Member Functions | |
static void | declareOptions (OptionList &ol) |
Declares the class options. | |
Protected Attributes | |
Vec | store_output |
Used to store outputs. | |
TVec< PP< PLearner > > | log_net |
Private Types | |
typedef PLearner | inherited |
Private Member Functions | |
void | build_ () |
This does the actual building. |
The first sentence should be a BRIEF DESCRIPTION of what the class does.
Place the rest of the class programmer documentation here. Doxygen supports Javadoc-style comments. See http://www.doxygen.org/manual.html
Definition at line 57 of file KFoldLogisticClassifier.h.
typedef PLearner PLearn::KFoldLogisticClassifier::inherited [private] |
Reimplemented from PLearn::PLearner.
Definition at line 59 of file KFoldLogisticClassifier.h.
PLearn::KFoldLogisticClassifier::KFoldLogisticClassifier | ( | ) |
Default constructor.
Definition at line 65 of file KFoldLogisticClassifier.cc.
: kfold(5), max_degraded_steps(20), max_epochs(500), step_size(1) { }
string PLearn::KFoldLogisticClassifier::_classname_ | ( | ) | [static] |
Reimplemented from PLearn::PLearner.
Definition at line 60 of file KFoldLogisticClassifier.cc.
OptionList & PLearn::KFoldLogisticClassifier::_getOptionList_ | ( | ) | [static] |
Reimplemented from PLearn::PLearner.
Definition at line 60 of file KFoldLogisticClassifier.cc.
RemoteMethodMap & PLearn::KFoldLogisticClassifier::_getRemoteMethodMap_ | ( | ) | [static] |
Reimplemented from PLearn::PLearner.
Definition at line 60 of file KFoldLogisticClassifier.cc.
Reimplemented from PLearn::PLearner.
Definition at line 60 of file KFoldLogisticClassifier.cc.
Object * PLearn::KFoldLogisticClassifier::_new_instance_for_typemap_ | ( | ) | [static] |
Reimplemented from PLearn::Object.
Definition at line 60 of file KFoldLogisticClassifier.cc.
StaticInitializer KFoldLogisticClassifier::_static_initializer_ & PLearn::KFoldLogisticClassifier::_static_initialize_ | ( | ) | [static] |
Reimplemented from PLearn::PLearner.
Definition at line 60 of file KFoldLogisticClassifier.cc.
void PLearn::KFoldLogisticClassifier::build | ( | ) | [virtual] |
Finish building the object; just call inherited::build followed by build_()
Reimplemented from PLearn::PLearner.
Definition at line 120 of file KFoldLogisticClassifier.cc.
References PLearn::PLearner::build(), and build_().
{ inherited::build(); build_(); }
void PLearn::KFoldLogisticClassifier::build_ | ( | ) | [private] |
This does the actual building.
Reimplemented from PLearn::PLearner.
Definition at line 113 of file KFoldLogisticClassifier.cc.
Referenced by build().
{ }
string PLearn::KFoldLogisticClassifier::classname | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 60 of file KFoldLogisticClassifier.cc.
void PLearn::KFoldLogisticClassifier::computeCostsFromOutputs | ( | const Vec & | input, |
const Vec & | output, | ||
const Vec & | target, | ||
Vec & | costs | ||
) | const [virtual] |
Computes the costs from already computed output.
Implements PLearn::PLearner.
Definition at line 295 of file KFoldLogisticClassifier.cc.
References PLearn::argmax(), PLearn::is_equal(), PLearn::TVec< T >::length(), pl_log, PLASSERT, PLearn::TVec< T >::resize(), and PLearn::sum().
{ int t = int(round(target[0])); costs.resize(2); if (output.length() == 1) { // Binary classification. PLASSERT(output[0] >= 0 && output[0] <= 1); if (t == 1) costs[0] = - pl_log(output[0]); else { PLASSERT(t == 0); costs[0] = - pl_log(1 - output[0]); } costs[1] = (output[0] - 0.5) * (2 * target[0] - 1) >= 0 ? 0 : 1; } else { // More than two targets. PLASSERT(is_equal(sum(output), 1)); costs[0] = - pl_log(output[t]); costs[1] = argmax(output) == t ? 0 : 1; } }
void PLearn::KFoldLogisticClassifier::computeOutput | ( | const Vec & | input, |
Vec & | output | ||
) | const [virtual] |
Computes the output from the input.
Reimplemented from PLearn::PLearner.
Definition at line 280 of file KFoldLogisticClassifier.cc.
References PLearn::TVec< T >::isEmpty(), PLearn::TVec< T >::length(), log_net, PLCHECK, PLearn::TVec< T >::resize(), and store_output.
{ PLCHECK(!log_net.isEmpty()); log_net[0]->computeOutput(input, output); store_output.resize(output.length()); for (int k = 1; k < log_net.length(); k++) { log_net[k]->computeOutput(input, store_output); output += store_output; } output /= real(log_net.length()); }
void PLearn::KFoldLogisticClassifier::declareOptions | ( | OptionList & | ol | ) | [static, protected] |
Declares the class options.
Reimplemented from PLearn::PLearner.
Definition at line 76 of file KFoldLogisticClassifier.cc.
References PLearn::OptionBase::buildoption, PLearn::declareOption(), PLearn::PLearner::declareOptions(), kfold, PLearn::OptionBase::learntoption, log_net, max_degraded_steps, max_epochs, and step_size.
{ // Build options. declareOption(ol, "kfold", &KFoldLogisticClassifier::kfold, OptionBase::buildoption, "Number of splits of the data (and of classifiers being trained)."); declareOption(ol, "max_degraded_steps", &KFoldLogisticClassifier::max_degraded_steps, OptionBase::buildoption, "Maximum number of optimization steps performed after finding a\n" "candidate for early stopping."); declareOption(ol, "max_epochs", &KFoldLogisticClassifier::max_epochs, OptionBase::buildoption, "Maximum number of epochs when training logistic classifiers\n"); declareOption(ol, "step_size", &KFoldLogisticClassifier::step_size, OptionBase::buildoption, "Measure performance every 'step_size' epochs."); // Learnt options. declareOption(ol, "log_net", &KFoldLogisticClassifier::log_net, OptionBase::learntoption, "Underlying logistic classifiers."); // Now call the parent class' declareOptions inherited::declareOptions(ol); }
static const PPath& PLearn::KFoldLogisticClassifier::declaringFile | ( | ) | [inline, static] |
KFoldLogisticClassifier * PLearn::KFoldLogisticClassifier::deepCopy | ( | CopiesMap & | copies | ) | const [virtual] |
Reimplemented from PLearn::PLearner.
Definition at line 60 of file KFoldLogisticClassifier.cc.
void PLearn::KFoldLogisticClassifier::forget | ( | ) | [virtual] |
(Re-)initializes the PLearner in its fresh state (that state may depend on the 'seed' option) and sets 'stage' back to 0 (this is the stage of a fresh learner!).
(Re-)initialize the PLearner in its fresh state (that state may depend on the 'seed' option) and sets 'stage' back to 0 (this is the stage of a fresh learner!)
A typical forget() method should do the following:
Reimplemented from PLearn::PLearner.
Definition at line 157 of file KFoldLogisticClassifier.cc.
References PLearn::PLearner::forget(), log_net, and PLearn::TVec< T >::resize().
{ inherited::forget(); log_net.resize(0); }
OptionList & PLearn::KFoldLogisticClassifier::getOptionList | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 60 of file KFoldLogisticClassifier.cc.
OptionMap & PLearn::KFoldLogisticClassifier::getOptionMap | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 60 of file KFoldLogisticClassifier.cc.
RemoteMethodMap & PLearn::KFoldLogisticClassifier::getRemoteMethodMap | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 60 of file KFoldLogisticClassifier.cc.
TVec< string > PLearn::KFoldLogisticClassifier::getTestCostNames | ( | ) | const [virtual] |
Returns the names of the costs computed by computeCostsFromOutpus (and thus the test method).
Implements PLearn::PLearner.
Definition at line 321 of file KFoldLogisticClassifier.cc.
References PLearn::TVec< T >::append(), and PLearn::TVec< T >::isEmpty().
{ static TVec<string> costs; if (costs.isEmpty()) { costs.append("nll"); costs.append("class_error"); } return costs; }
TVec< string > PLearn::KFoldLogisticClassifier::getTrainCostNames | ( | ) | const [virtual] |
Returns the names of the objective costs that the train method computes and for which it updates the VecStatsCollector train_stats.
Implements PLearn::PLearner.
Definition at line 334 of file KFoldLogisticClassifier.cc.
{
return TVec<string>();
}
void PLearn::KFoldLogisticClassifier::makeDeepCopyFromShallowCopy | ( | CopiesMap & | copies | ) | [virtual] |
Transforms a shallow copy into a deep copy.
Reimplemented from PLearn::PLearner.
Definition at line 129 of file KFoldLogisticClassifier.cc.
References PLearn::PLearner::makeDeepCopyFromShallowCopy(), and PLERROR.
{ inherited::makeDeepCopyFromShallowCopy(copies); // ### Call deepCopyField on all "pointer-like" fields // ### that you wish to be deepCopied rather than // ### shallow-copied. // ### ex: // deepCopyField(trainvec, copies); // ### Remove this line when you have fully implemented this method. PLERROR("KFoldLogisticClassifier::makeDeepCopyFromShallowCopy not fully (correctly) implemented yet!"); }
int PLearn::KFoldLogisticClassifier::outputsize | ( | ) | const [virtual] |
Returns the size of this learner's output, (which typically may depend on its inputsize(), targetsize() and set options).
Implements PLearn::PLearner.
Definition at line 146 of file KFoldLogisticClassifier.cc.
References PLearn::TVec< T >::isEmpty(), and log_net.
void PLearn::KFoldLogisticClassifier::train | ( | ) | [virtual] |
The role of the train method is to bring the learner up to stage==nstages, updating the train_stats collector with training costs measured on-line in the process.
Implements PLearn::PLearner.
Definition at line 176 of file KFoldLogisticClassifier.cc.
References PLearn::TVec< T >::append(), PLearn::TVec< T >::find(), PLearn::get_pointer(), PLearn::VMat::getExample(), i, PLearn::PLearner::initTrain(), j, kfold, PLearn::TVec< T >::length(), PLearn::VMat::length(), log_net, max_degraded_steps, max_epochs, PLCHECK, PLearn::PLearner::report_progress, PLearn::TVec< T >::resize(), PLearn::PLearner::seed_, PLearn::PLearner::stage, step_size, and PLearn::PLearner::train_set.
{ if (!initTrain()) return; PLCHECK( stage == 0 ); // Find out the number of classes in the dataset. TVec<bool> all_classes; Vec input, target; real weight; PLCHECK(train_set->targetsize() == 1); for (int i = 0; i < train_set->length(); i++) { train_set->getExample(i, input, target, weight); int t = int(round(target[0])); if (t >= all_classes.length()) { int n_to_add = t - all_classes.length() + 1; for (int j = 0; j < n_to_add; j++) all_classes.append(false); } all_classes[t] = true; } int n_classes = all_classes.length(); PLCHECK(n_classes >= 2); PLCHECK(all_classes.find(false) == -1); // Split the data. PP<KFoldSplitter> splitter = new KFoldSplitter(); splitter->K = this->kfold; splitter->build(); splitter->setDataSet(train_set); // Create logistic regressors. log_net.resize(0); string cost_func; for (int k = 0; k < kfold; k++) { PP<ConjGradientOptimizer> opt = new ConjGradientOptimizer(); opt->build(); PP<NNet> nnet = new NNet(); nnet->optimizer = opt; nnet->seed_ = this->seed_; nnet->report_progress = this->report_progress; if (n_classes == 2) { cost_func = "stable_cross_entropy"; nnet->output_transfer_func = "sigmoid"; nnet->noutputs = 1; } else { cost_func = "NLL"; nnet->output_transfer_func = "softmax"; nnet->noutputs = n_classes; } nnet->cost_funcs = TVec<string>(1, cost_func); nnet->batch_size = 0; nnet->build(); log_net.append(get_pointer(nnet)); } // Train logistic regressors. for (int k = 0; k < log_net.length(); k++) { // Initialize the hyper-learning framework for early stopping. // Splitter. PP<ExplicitSplitter> hsplitter = new ExplicitSplitter(); hsplitter->splitsets = TMat<VMat>(1, 2); hsplitter->splitsets(0) << splitter->getSplit(k); hsplitter->build(); // PTester. PP<PTester> htester = new PTester(); htester->splitter = hsplitter; string cost = "E[test.E[" + cost_func + "]]"; htester->setStatNames(TVec<string>(1, cost), false); htester->build(); // Oracle. PP<EarlyStoppingOracle> early_stop = new EarlyStoppingOracle(); early_stop->max_degraded_steps = this->max_degraded_steps; early_stop->range = TVec<double>(3, this->step_size); early_stop->range[1] = this->max_epochs + 1; early_stop->option = "nstages"; early_stop->build(); // Strategy. PP<HyperOptimize> strategy = new HyperOptimize(); strategy->oracle = early_stop; strategy->which_cost = "0"; strategy->build(); // HyperLearner. PP<HyperLearner> hyper = new HyperLearner(); hyper->dont_restart_upon_change = TVec<string>(1, "nstages"); hyper->learner_ = log_net[k]; hyper->option_fields = hyper->dont_restart_upon_change; hyper->save_final_learner = false; hyper->strategy = TVec< PP<HyperCommand> >(1, get_pointer(strategy)); hyper->tester = htester; hyper->verbosity = 0; // Get rid of useless output. hyper->build(); // Perform training. hyper->train(); // Make sure we keep only the best model. log_net[k] = hyper->getLearner(); } this->stage = 1; }
Reimplemented from PLearn::PLearner.
Definition at line 138 of file KFoldLogisticClassifier.h.
Definition at line 64 of file KFoldLogisticClassifier.h.
Referenced by declareOptions(), and train().
TVec< PP<PLearner> > PLearn::KFoldLogisticClassifier::log_net [protected] |
Definition at line 154 of file KFoldLogisticClassifier.h.
Referenced by computeOutput(), declareOptions(), forget(), outputsize(), and train().
Definition at line 65 of file KFoldLogisticClassifier.h.
Referenced by declareOptions(), and train().
Definition at line 66 of file KFoldLogisticClassifier.h.
Referenced by declareOptions(), and train().
Definition at line 67 of file KFoldLogisticClassifier.h.
Referenced by declareOptions(), and train().
Vec PLearn::KFoldLogisticClassifier::store_output [mutable, protected] |
Used to store outputs.
Definition at line 150 of file KFoldLogisticClassifier.h.
Referenced by computeOutput().