PLearn 0.1
|
Generate samples from a mixture of two gaussians. More...
#include <AnalyzeFieldStats.h>
Public Member Functions | |
AnalyzeFieldStats () | |
Default constructor. | |
int | outputsize () const |
SUBCLASS WRITING: override this so that it returns the size of this learner's output, as a function of its inputsize(), targetsize() and set options. | |
void | train () |
*** SUBCLASS WRITING: *** | |
void | computeOutput (const Vec &, Vec &) const |
*** SUBCLASS WRITING: *** | |
void | computeCostsFromOutputs (const Vec &, const Vec &, const Vec &, Vec &) const |
*** SUBCLASS WRITING: *** | |
TVec< string > | getTestCostNames () const |
*** SUBCLASS WRITING: *** | |
TVec< string > | getTrainCostNames () const |
*** SUBCLASS WRITING: *** | |
virtual string | classname () const |
virtual OptionList & | getOptionList () const |
virtual OptionMap & | getOptionMap () const |
virtual RemoteMethodMap & | getRemoteMethodMap () const |
virtual AnalyzeFieldStats * | 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 | min_number_of_samples |
### declare public option fields (such as build options) here Start your comments with Doxygen-compatible comments such as //! | |
int | max_number_of_samples |
The maximum number of samples used to train the learner. | |
VMat | targeted_set |
The train and test data sets with the target field. | |
PP< PTester > | cond_mean_template |
The template of the script to learn the conditional mean. | |
TVec< string > | fields |
The field name of the variable to be analyzed. | |
Static Public Attributes | |
static StaticInitializer | _static_initializer_ |
Static Protected Member Functions | |
static void | declareOptions (OptionList &ol) |
Declares the class options. | |
Private Types | |
typedef PLearner | inherited |
Private Member Functions | |
void | build_ () |
This does the actual building. | |
void | analyzeVariableStats () |
void | createHeaderFile () |
void | getHeaderRecord () |
void | updateHeaderRecord (int var_col) |
void | reviewGlobalStats () |
Private Attributes | |
int | main_width |
TVec< string > | main_names |
StatsCollector | main_stats |
PPath | main_metadata |
TVec< int > | main_ins |
real | main_total |
real | main_missing |
real | main_present |
int | targeted_length |
int | targeted_width |
Vec | targeted_input |
TVec< string > | targeted_names |
StatsCollector | targeted_stats |
PPath | targeted_metadata |
real | targeted_missing |
PPath | header_file_name |
VMat | header_file |
Vec | header_record |
int | fields_col |
int | fields_width |
TVec< int > | fields_selected |
int | to_deal_with_total |
int | to_deal_with_next |
real | to_deal_with_value |
string | to_deal_with_name |
int | ind_next |
int | output_length |
int | output_width |
int | output_col |
string | output_path |
TVec< string > | output_names |
Vec | output_vec |
TVec< int > | output_variable_src |
VMat | output_file |
int | train_test_length |
string | train_test_path |
TVec< int > | train_test_variable_src |
VMat | train_test_file |
PPath | results_file_name |
VMat | results_file |
int | results_length |
real | results_nstages |
real | results_mse |
real | results_std_err |
PPath | test_output_file_name |
VMat | test_output_file |
int | test_output_length |
Generate samples from a mixture of two gaussians.
Definition at line 54 of file AnalyzeFieldStats.h.
typedef PLearner PLearn::AnalyzeFieldStats::inherited [private] |
Reimplemented from PLearn::PLearner.
Definition at line 56 of file AnalyzeFieldStats.h.
PLearn::AnalyzeFieldStats::AnalyzeFieldStats | ( | ) |
Default constructor.
Definition at line 60 of file AnalyzeFieldStats.cc.
: min_number_of_samples(5000), max_number_of_samples(50000) { }
string PLearn::AnalyzeFieldStats::_classname_ | ( | ) | [static] |
Reimplemented from PLearn::PLearner.
Definition at line 55 of file AnalyzeFieldStats.cc.
OptionList & PLearn::AnalyzeFieldStats::_getOptionList_ | ( | ) | [static] |
Reimplemented from PLearn::PLearner.
Definition at line 55 of file AnalyzeFieldStats.cc.
RemoteMethodMap & PLearn::AnalyzeFieldStats::_getRemoteMethodMap_ | ( | ) | [static] |
Reimplemented from PLearn::PLearner.
Definition at line 55 of file AnalyzeFieldStats.cc.
Reimplemented from PLearn::PLearner.
Definition at line 55 of file AnalyzeFieldStats.cc.
Object * PLearn::AnalyzeFieldStats::_new_instance_for_typemap_ | ( | ) | [static] |
Reimplemented from PLearn::Object.
Definition at line 55 of file AnalyzeFieldStats.cc.
StaticInitializer AnalyzeFieldStats::_static_initializer_ & PLearn::AnalyzeFieldStats::_static_initialize_ | ( | ) | [static] |
Reimplemented from PLearn::PLearner.
Definition at line 55 of file AnalyzeFieldStats.cc.
void PLearn::AnalyzeFieldStats::analyzeVariableStats | ( | ) | [private] |
Definition at line 133 of file AnalyzeFieldStats.cc.
References PLearn::TVec< T >::clear(), createHeaderFile(), PLearn::endl(), fields, fields_col, fields_selected, fields_width, getHeaderRecord(), header_file_name, header_record, ind_next, PLearn::is_missing(), PLearn::isfile(), PLearn::TVec< T >::length(), PLearn::VMat::length(), main_metadata, main_missing, main_names, main_present, main_stats, main_total, main_width, PLearn::manual_seed(), max_number_of_samples, PLearn::StatsCollector::n(), PLearn::StatsCollector::nmissing(), output_col, output_file, output_length, output_names, output_path, output_variable_src, output_vec, output_width, PLERROR, PLearn::TVec< T >::resize(), reviewGlobalStats(), PLearn::shuffleElements(), PLearn::TVec< T >::size(), targeted_input, targeted_length, targeted_metadata, targeted_names, targeted_set, targeted_width, to_deal_with_name, to_deal_with_next, to_deal_with_total, to_deal_with_value, PLearn::PLearner::train_set, train_test_file, train_test_length, train_test_path, train_test_variable_src, PLearn::ProgressBar::update(), updateHeaderRecord(), and PLearn::VMat::width().
Referenced by build_().
{ // initialize primary dataset int main_length = train_set->length(); main_width = train_set->width(); Vec main_input; main_input.resize(main_width); main_names.resize(main_width); main_names << train_set->fieldNames(); main_metadata = train_set->getMetaDataDir(); // validate the field instructions fields_width = fields.size(); fields_selected.resize(main_width); fields_selected.clear(); for (fields_col = 0; fields_col < fields_width; fields_col++) { int main_col; for (main_col = 0; main_col < main_width; main_col++) { if (fields[fields_col] == main_names[main_col]) break; } if (main_col >= main_width) PLERROR("In AnalyzeFieldStats::analyzeVariableStats() no field with this name in input dataset: %s", (fields[fields_col]).c_str()); fields_selected[main_col] = 1; } // initialize targeted datasets cout << "initialize train_test datasets" << endl; targeted_length = targeted_set->length(); targeted_width = targeted_set->width(); targeted_input.resize(targeted_width); targeted_names.resize(targeted_width); targeted_names << targeted_set->fieldNames(); targeted_metadata = targeted_set->getMetaDataDir(); // initialize the header file cout << "initialize the header file" << endl; train_set->lockMetaDataDir(); header_record.resize(main_width); header_file_name = targeted_metadata + "/TreeCondMean/header.pmat"; if (!isfile(header_file_name)) createHeaderFile(); else getHeaderRecord(); // choose variable to build a conditionnal function for cout << "choose variable to build a conditionnal function for" << endl; TVec<int> indices; to_deal_with_total = 0; to_deal_with_next = -1; for (int main_col = 0; main_col < main_width; main_col++) { if (header_record[main_col] != 2.0) continue; to_deal_with_total += 1; if (to_deal_with_next < 0) to_deal_with_next = main_col; } if (to_deal_with_next < 0) { train_set->unlockMetaDataDir(); reviewGlobalStats(); PLERROR("AnalyzeFieldStats::analyzeVariableStats() we are done here"); } to_deal_with_name = main_names[to_deal_with_next]; cout << "total number of variable left to deal with: " << to_deal_with_total << endl; cout << "next variable to deal with: " << main_names[to_deal_with_next] << endl; updateHeaderRecord(to_deal_with_next); train_set->unlockMetaDataDir(); // find the available targeted records for this variable ProgressBar* pb = 0; main_stats = train_set->getStats(to_deal_with_next); main_total = main_stats.n(); main_missing = main_stats.nmissing(); main_present = main_total - main_missing; indices.resize((int) main_present); ind_next = 0; pb = new ProgressBar( "Building the indices for " + to_deal_with_name, main_length); for (int main_row = 0; main_row < main_length; main_row++) { to_deal_with_value = train_set->get(main_row, to_deal_with_next); if (is_missing(to_deal_with_value)) continue; if (ind_next >= indices.length()) PLERROR("AnalyzeFieldStats::analyzeVariableStats() There seems to be more present values than indicated by the stats file"); indices[ind_next] = main_row; ind_next += 1; pb->update( main_row ); } delete pb; // shuffle the indices. manual_seed(123456); shuffleElements(indices); // initialize output datasets output_length = (int) main_present; if (output_length > max_number_of_samples) output_length = max_number_of_samples; output_width = 0; for (int main_col = 0; main_col < main_width; main_col++) { if (header_record[main_col] != 1) output_width += 1; } output_variable_src.resize(output_width); output_names.resize(output_width); output_vec.resize(output_width); output_path = main_metadata + "condmean_" + to_deal_with_name + ".pmat"; output_col = 0; for (fields_col = 0; fields_col < fields_width; fields_col++) { int main_col; for (main_col = 0; main_col < main_width; main_col++) { if (fields[fields_col] == main_names[main_col]) break; } if (main_col >= main_width) PLERROR("In AnalyzeFieldStats::analyzeVariableStats() no field with this name in input dataset: %s", (fields[fields_col]).c_str()); if (fields_col != to_deal_with_next && header_record[main_col] != 1) { output_variable_src[output_col] = main_col; output_names[output_col] = fields[fields_col]; output_col += 1; } } output_variable_src[output_col] = to_deal_with_next; output_names[output_col] = to_deal_with_name; output_file = new MemoryVMatrix(output_length, output_width); output_file->declareFieldNames(output_names); output_file->defineSizes(output_width - 1, 1, 0); //Now, we can build the training file pb = new ProgressBar( "Building the training file for " + to_deal_with_name, output_length); for (int main_row = 0; main_row < output_length; main_row++) { train_set->getRow(indices[main_row], main_input); for (output_col = 0; output_col < output_width; output_col++) { output_vec[output_col] = main_input[output_variable_src[output_col]]; } output_file->putRow(main_row, output_vec); pb->update( main_row ); } delete pb; // initialize train_test datasets train_test_length = targeted_length; train_test_variable_src.resize(output_width); train_test_path = targeted_metadata + "targeted_" + to_deal_with_name + ".pmat"; output_col = 0; for (fields_col = 0; fields_col < fields_width; fields_col++) { int main_col; for (main_col = 0; main_col < targeted_width; main_col++) { if (fields[fields_col] == targeted_names[main_col]) break; } if (main_col >= targeted_width) PLERROR("In AnalyzeFieldStats::analyzeVariableStats() no field with this name in targeted dataset: %s", (fields[fields_col]).c_str()); if (fields_col != to_deal_with_next && header_record[main_col] != 1) { train_test_variable_src[output_col] = main_col; output_col += 1; } } train_test_variable_src[output_col] = to_deal_with_next; train_test_file = new MemoryVMatrix(train_test_length, output_width); train_test_file->declareFieldNames(output_names); train_test_file->defineSizes(output_width - 1, 1, 0); //Now, we can build the targeted file pb = new ProgressBar( "Building the targeted file for " + to_deal_with_name, train_test_length); for (int main_row = 0; main_row < train_test_length; main_row++) { targeted_set->getRow(main_row, targeted_input); for (output_col = 0; output_col < output_width; output_col++) { output_vec[output_col] = targeted_input[train_test_variable_src[output_col]]; } train_test_file->putRow(main_row, output_vec); pb->update( main_row ); } delete pb; }
void PLearn::AnalyzeFieldStats::build | ( | ) | [virtual] |
Finish building the object; just call inherited::build followed by build_()
Reimplemented from PLearn::PLearner.
Definition at line 108 of file AnalyzeFieldStats.cc.
References PLearn::PLearner::build(), and build_().
{ // ### Nothing to add here, simply calls build_(). inherited::build(); build_(); }
void PLearn::AnalyzeFieldStats::build_ | ( | ) | [private] |
This does the actual building.
Reimplemented from PLearn::PLearner.
Definition at line 118 of file AnalyzeFieldStats.cc.
References analyzeVariableStats(), PLearn::endl(), PLERROR, train(), PLearn::PLearner::train_set, and PLearn::VMat::width().
Referenced by build().
{ MODULE_LOG << "build_() called" << endl; if (train_set) { for (int iteration = 1; iteration <= train_set->width(); iteration++) { cout << "In AnalyzeFieldStats, Iteration # " << iteration << endl; analyzeVariableStats(); train(); } PLERROR("AnalyzeFieldStats::build_() we are done here"); } }
string PLearn::AnalyzeFieldStats::classname | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 55 of file AnalyzeFieldStats.cc.
void PLearn::AnalyzeFieldStats::computeCostsFromOutputs | ( | const Vec & | input, |
const Vec & | output, | ||
const Vec & | target, | ||
Vec & | costs | ||
) | const [virtual] |
*** SUBCLASS WRITING: ***
This should be defined in subclasses to compute the weighted costs from already computed output. The costs should correspond to the cost names returned by getTestCostNames().
NOTE: In exotic cases, the cost may also depend on some info in the input, that's why the method also gets so see it.
Implements PLearn::PLearner.
Definition at line 433 of file AnalyzeFieldStats.cc.
{}
*** SUBCLASS WRITING: ***
This should be defined in subclasses to compute the output from the input.
Reimplemented from PLearn::PLearner.
Definition at line 432 of file AnalyzeFieldStats.cc.
{}
void PLearn::AnalyzeFieldStats::createHeaderFile | ( | ) | [private] |
Definition at line 314 of file AnalyzeFieldStats.cc.
References fields_selected, header_file, header_file_name, header_record, main_missing, main_names, main_present, main_stats, main_total, main_width, min_number_of_samples, PLearn::StatsCollector::n(), PLearn::StatsCollector::nmissing(), targeted_missing, targeted_set, targeted_stats, and PLearn::PLearner::train_set.
Referenced by analyzeVariableStats().
{ for (int main_col = 0; main_col < main_width; main_col++) { targeted_stats = targeted_set->getStats(main_col); targeted_missing = targeted_stats.nmissing(); main_stats = train_set->getStats(main_col); main_total = main_stats.n(); main_missing = main_stats.nmissing(); main_present = main_total - main_missing; if (fields_selected[main_col] < 1) header_record[main_col] = 1; // delete column, field not selected else if (targeted_missing <= 0) header_record[main_col] = 0; // nothing to do else if (main_present < min_number_of_samples) header_record[main_col] = 1; // delete column else header_record[main_col] = 2; // build tree } header_file = new FileVMatrix(header_file_name, 1, main_names); header_file->putRow(0, header_record); }
void PLearn::AnalyzeFieldStats::declareOptions | ( | OptionList & | ol | ) | [static, protected] |
Declares the class options.
Reimplemented from PLearn::PLearner.
Definition at line 69 of file AnalyzeFieldStats.cc.
References PLearn::OptionBase::buildoption, cond_mean_template, PLearn::declareOption(), PLearn::PLearner::declareOptions(), fields, max_number_of_samples, min_number_of_samples, and targeted_set.
{ declareOption(ol, "min_number_of_samples", &AnalyzeFieldStats::min_number_of_samples, OptionBase::buildoption, "The minimum number of samples required to train the learner."); declareOption(ol, "max_number_of_samples", &AnalyzeFieldStats::max_number_of_samples, OptionBase::buildoption, "The maximum number of samples used to train the learner"); declareOption(ol, "targeted_set", &AnalyzeFieldStats::targeted_set, OptionBase::buildoption, "The train and test data sets with the target field."); declareOption(ol, "cond_mean_template", &AnalyzeFieldStats::cond_mean_template, OptionBase::buildoption, "The template of the script to learn the conditional mean."); declareOption(ol, "fields", &AnalyzeFieldStats::fields, OptionBase::buildoption, "The vector of fields to consider by names."); inherited::declareOptions(ol); }
static const PPath& PLearn::AnalyzeFieldStats::declaringFile | ( | ) | [inline, static] |
Reimplemented from PLearn::PLearner.
Definition at line 96 of file AnalyzeFieldStats.h.
:
//##### Protected Member Functions ######################################
AnalyzeFieldStats * PLearn::AnalyzeFieldStats::deepCopy | ( | CopiesMap & | copies | ) | const [virtual] |
Reimplemented from PLearn::PLearner.
Definition at line 55 of file AnalyzeFieldStats.cc.
void PLearn::AnalyzeFieldStats::getHeaderRecord | ( | ) | [private] |
Definition at line 333 of file AnalyzeFieldStats.cc.
References fields_selected, header_file, header_file_name, header_record, main_missing, main_present, main_stats, main_total, main_width, min_number_of_samples, PLearn::StatsCollector::n(), PLearn::StatsCollector::nmissing(), and PLearn::PLearner::train_set.
Referenced by analyzeVariableStats().
{ header_file = new FileVMatrix(header_file_name, true); header_file->getRow(0, header_record); for (int main_col = 0; main_col < main_width; main_col++) { if (header_record[main_col] == 0) continue; if (header_record[main_col] == 2) continue; if (header_record[main_col] == 1 && fields_selected[main_col] < 1) continue; if (header_record[main_col] == 1) { main_stats = train_set->getStats(main_col); main_total = main_stats.n(); main_missing = main_stats.nmissing(); main_present = main_total - main_missing; if (main_present >= min_number_of_samples) header_record[main_col] = 2; continue; } } }
OptionList & PLearn::AnalyzeFieldStats::getOptionList | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 55 of file AnalyzeFieldStats.cc.
OptionMap & PLearn::AnalyzeFieldStats::getOptionMap | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 55 of file AnalyzeFieldStats.cc.
RemoteMethodMap & PLearn::AnalyzeFieldStats::getRemoteMethodMap | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 55 of file AnalyzeFieldStats.cc.
TVec< string > PLearn::AnalyzeFieldStats::getTestCostNames | ( | ) | const [virtual] |
*** SUBCLASS WRITING: ***
This should return the names of the costs computed by computeCostsFromOutputs.
Implements PLearn::PLearner.
Definition at line 434 of file AnalyzeFieldStats.cc.
References PLearn::TVec< T >::append().
{ TVec<string> result; result.append( "MSE" ); return result; }
TVec< string > PLearn::AnalyzeFieldStats::getTrainCostNames | ( | ) | const [virtual] |
*** SUBCLASS WRITING: ***
This should return 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 440 of file AnalyzeFieldStats.cc.
References PLearn::TVec< T >::append().
{ TVec<string> result; result.append( "MSE" ); return result; }
void PLearn::AnalyzeFieldStats::makeDeepCopyFromShallowCopy | ( | CopiesMap & | copies | ) | [virtual] |
Transforms a shallow copy into a deep copy.
Reimplemented from PLearn::PLearner.
Definition at line 94 of file AnalyzeFieldStats.cc.
References cond_mean_template, PLearn::deepCopyField(), fields, PLearn::PLearner::makeDeepCopyFromShallowCopy(), max_number_of_samples, min_number_of_samples, and targeted_set.
{ deepCopyField(min_number_of_samples, copies); deepCopyField(max_number_of_samples, copies); deepCopyField(targeted_set, copies); deepCopyField(cond_mean_template, copies); deepCopyField(fields, copies); inherited::makeDeepCopyFromShallowCopy(copies); }
int PLearn::AnalyzeFieldStats::outputsize | ( | ) | const [virtual] |
SUBCLASS WRITING: override this so that it returns the size of this learner's output, as a function of its inputsize(), targetsize() and set options.
Implements PLearn::PLearner.
Definition at line 431 of file AnalyzeFieldStats.cc.
{return 0;}
void PLearn::AnalyzeFieldStats::reviewGlobalStats | ( | ) | [private] |
Definition at line 359 of file AnalyzeFieldStats.cc.
References PLearn::endl(), fields_selected, header_file, header_record, PLearn::isfile(), PLearn::left(), PLearn::VMat::length(), main_missing, main_names, main_present, main_stats, main_total, main_width, PLearn::StatsCollector::n(), PLearn::StatsCollector::nmissing(), results_file, results_file_name, results_length, results_mse, results_nstages, results_std_err, targeted_metadata, test_output_file, test_output_file_name, test_output_length, and PLearn::PLearner::train_set.
Referenced by analyzeVariableStats().
{ cout << "There is no more variable to deal with." << endl; for (int main_col = 0; main_col < main_width; main_col++) { if (header_record[main_col] == 0) { cout << setiosflags(ios::left) << setw(30) << main_names[main_col]; cout << " : no missing values for this variable in the targeted files." << endl; continue; } if (header_record[main_col] == 1 && fields_selected[main_col] < 1) { cout << setiosflags(ios::left) << setw(30) << main_names[main_col]; cout << " : field not selected." << endl; continue; } if (header_record[main_col] == 1) { main_stats = train_set->getStats(main_col); main_total = main_stats.n(); main_missing = main_stats.nmissing(); main_present = main_total - main_missing; cout << setiosflags(ios::left) << setw(30) << main_names[main_col]; cout << " : field deleted, only " << setw(6) << main_present << " records to train with." << endl; continue; } results_file_name = targeted_metadata + "/TreeCondMean/dir/" + main_names[main_col] + "/Split0/LearnerExpdir/Strat0results.pmat"; if (!isfile(results_file_name)) { header_file->put(0, main_col, 2.0); cout << setiosflags(ios::left) << setw(30) << main_names[main_col]; cout << " : missing results file." << endl; continue; } test_output_file_name = targeted_metadata + "/TreeCondMean/dir/" + main_names[main_col] + "/Split0/test1_outputs.pmat"; if (!isfile(test_output_file_name)) { header_file->put(0, main_col, 2.0); cout << setiosflags(ios::left) << setw(30) << main_names[main_col]; cout << " : missing test output file." << endl; continue; } results_file = new FileVMatrix(results_file_name); results_length = results_file->length(); results_nstages = results_file->get(results_length - 1, 2); results_mse = results_file->get(results_length - 1, 6); results_std_err = results_file->get(results_length - 1, 7); test_output_file = new FileVMatrix(test_output_file_name); test_output_length = test_output_file->length(); cout << setiosflags(ios::left) << setw(30) << main_names[main_col]; cout << " : tree built with " << setw(2) << (int) results_nstages << " leaves, " << setw(6) << test_output_length << " test output records found, " << "performance: " << setiosflags(ios::fixed) << setprecision(4) << results_mse << " +/- " << setiosflags(ios::fixed) << setprecision(4) << results_std_err << endl; } }
void PLearn::AnalyzeFieldStats::train | ( | ) | [virtual] |
*** SUBCLASS WRITING: ***
The role of the train method is to bring the learner up to stage==nstages, updating the stats with training costs measured on-line in the process.
TYPICAL CODE:
static Vec input; // static so we don't reallocate/deallocate memory each time... static Vec target; // (but be careful that static means shared!) input.resize(inputsize()); // the train_set's inputsize() target.resize(targetsize()); // the train_set's targetsize() real weight; if(!train_stats) // make a default stats collector, in case there's none train_stats = new VecStatsCollector(); if(nstages<stage) // asking to revert to a previous stage! forget(); // reset the learner to stage=0 while(stage<nstages) { // clear statistics of previous epoch train_stats->forget(); //... train for 1 stage, and update train_stats, // using train_set->getSample(input, target, weight); // and train_stats->update(train_costs) ++stage; train_stats->finalize(); // finalize statistics for this epoch }
Implements PLearn::PLearner.
Definition at line 417 of file AnalyzeFieldStats.cc.
References cond_mean_template, PLearn::deepCopy(), output_file, targeted_metadata, to_deal_with_name, and train_test_file.
Referenced by build_().
{ PP<ExplicitSplitter> explicit_splitter = new ExplicitSplitter(); explicit_splitter->splitsets.resize(1,2); explicit_splitter->splitsets(0,0) = output_file; explicit_splitter->splitsets(0,1) = train_test_file; PP<PTester> cond_mean = ::PLearn::deepCopy(cond_mean_template); cond_mean->setOption("expdir", targeted_metadata + "/TreeCondMean/dir/" + to_deal_with_name); cond_mean->splitter = new ExplicitSplitter(); cond_mean->splitter = explicit_splitter; cond_mean->build(); Vec results = cond_mean->perform(true); }
void PLearn::AnalyzeFieldStats::updateHeaderRecord | ( | int | var_col | ) | [private] |
Definition at line 354 of file AnalyzeFieldStats.cc.
References header_file.
Referenced by analyzeVariableStats().
{ header_file->put(0, var_col, 3.0); }
Reimplemented from PLearn::PLearner.
Definition at line 96 of file AnalyzeFieldStats.h.
The template of the script to learn the conditional mean.
Definition at line 72 of file AnalyzeFieldStats.h.
Referenced by declareOptions(), makeDeepCopyFromShallowCopy(), and train().
The field name of the variable to be analyzed.
Definition at line 74 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), declareOptions(), and makeDeepCopyFromShallowCopy().
int PLearn::AnalyzeFieldStats::fields_col [private] |
Definition at line 145 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
TVec<int> PLearn::AnalyzeFieldStats::fields_selected [private] |
Definition at line 147 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), createHeaderFile(), getHeaderRecord(), and reviewGlobalStats().
int PLearn::AnalyzeFieldStats::fields_width [private] |
Definition at line 146 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
VMat PLearn::AnalyzeFieldStats::header_file [private] |
Definition at line 143 of file AnalyzeFieldStats.h.
Referenced by createHeaderFile(), getHeaderRecord(), reviewGlobalStats(), and updateHeaderRecord().
Definition at line 142 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), createHeaderFile(), and getHeaderRecord().
Vec PLearn::AnalyzeFieldStats::header_record [private] |
Definition at line 144 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), createHeaderFile(), getHeaderRecord(), and reviewGlobalStats().
int PLearn::AnalyzeFieldStats::ind_next [private] |
Definition at line 152 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
TVec<int> PLearn::AnalyzeFieldStats::main_ins [private] |
Definition at line 131 of file AnalyzeFieldStats.h.
Definition at line 130 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
real PLearn::AnalyzeFieldStats::main_missing [private] |
Definition at line 133 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), createHeaderFile(), getHeaderRecord(), and reviewGlobalStats().
TVec<string> PLearn::AnalyzeFieldStats::main_names [private] |
Definition at line 128 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), createHeaderFile(), and reviewGlobalStats().
real PLearn::AnalyzeFieldStats::main_present [private] |
Definition at line 134 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), createHeaderFile(), getHeaderRecord(), and reviewGlobalStats().
Definition at line 129 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), createHeaderFile(), getHeaderRecord(), and reviewGlobalStats().
real PLearn::AnalyzeFieldStats::main_total [private] |
Definition at line 132 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), createHeaderFile(), getHeaderRecord(), and reviewGlobalStats().
int PLearn::AnalyzeFieldStats::main_width [private] |
Definition at line 127 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), createHeaderFile(), getHeaderRecord(), and reviewGlobalStats().
The maximum number of samples used to train the learner.
Definition at line 68 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), declareOptions(), and makeDeepCopyFromShallowCopy().
### declare public option fields (such as build options) here Start your comments with Doxygen-compatible comments such as //!
The minimum number of samples required to train the learner.
Definition at line 66 of file AnalyzeFieldStats.h.
Referenced by createHeaderFile(), declareOptions(), getHeaderRecord(), and makeDeepCopyFromShallowCopy().
int PLearn::AnalyzeFieldStats::output_col [private] |
Definition at line 155 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
VMat PLearn::AnalyzeFieldStats::output_file [private] |
Definition at line 160 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), and train().
int PLearn::AnalyzeFieldStats::output_length [private] |
Definition at line 153 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
TVec<string> PLearn::AnalyzeFieldStats::output_names [private] |
Definition at line 157 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
string PLearn::AnalyzeFieldStats::output_path [private] |
Definition at line 156 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
Definition at line 159 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
Vec PLearn::AnalyzeFieldStats::output_vec [private] |
Definition at line 158 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
int PLearn::AnalyzeFieldStats::output_width [private] |
Definition at line 154 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
VMat PLearn::AnalyzeFieldStats::results_file [private] |
Definition at line 166 of file AnalyzeFieldStats.h.
Referenced by reviewGlobalStats().
Definition at line 165 of file AnalyzeFieldStats.h.
Referenced by reviewGlobalStats().
int PLearn::AnalyzeFieldStats::results_length [private] |
Definition at line 167 of file AnalyzeFieldStats.h.
Referenced by reviewGlobalStats().
real PLearn::AnalyzeFieldStats::results_mse [private] |
Definition at line 169 of file AnalyzeFieldStats.h.
Referenced by reviewGlobalStats().
Definition at line 168 of file AnalyzeFieldStats.h.
Referenced by reviewGlobalStats().
Definition at line 170 of file AnalyzeFieldStats.h.
Referenced by reviewGlobalStats().
Vec PLearn::AnalyzeFieldStats::targeted_input [private] |
Definition at line 137 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
Definition at line 135 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
Definition at line 140 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), reviewGlobalStats(), and train().
Definition at line 141 of file AnalyzeFieldStats.h.
Referenced by createHeaderFile().
TVec<string> PLearn::AnalyzeFieldStats::targeted_names [private] |
Definition at line 138 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
The train and test data sets with the target field.
Definition at line 70 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), createHeaderFile(), declareOptions(), and makeDeepCopyFromShallowCopy().
Definition at line 139 of file AnalyzeFieldStats.h.
Referenced by createHeaderFile().
int PLearn::AnalyzeFieldStats::targeted_width [private] |
Definition at line 136 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
Definition at line 172 of file AnalyzeFieldStats.h.
Referenced by reviewGlobalStats().
Definition at line 171 of file AnalyzeFieldStats.h.
Referenced by reviewGlobalStats().
Definition at line 173 of file AnalyzeFieldStats.h.
Referenced by reviewGlobalStats().
string PLearn::AnalyzeFieldStats::to_deal_with_name [private] |
Definition at line 151 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), and train().
Definition at line 149 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
Definition at line 148 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
Definition at line 150 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
Definition at line 164 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats(), and train().
Definition at line 161 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
string PLearn::AnalyzeFieldStats::train_test_path [private] |
Definition at line 162 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().
Definition at line 163 of file AnalyzeFieldStats.h.
Referenced by analyzeVariableStats().