best_constant.h File Reference

#include <float.h>
#include "vw.h"

Go to the source code of this file.

Functions
void	count_label (shared_data *sd, float l)
bool	get_best_constant (vw &all, float &best_constant, float &best_constant_loss)

Function Documentation

count_label()

void count_label ( shared_data *  sd, float  l  )

inline

Definition at line 5 of file best_constant.h.

References shared_data::first_observed_label, get_best_constant(), shared_data::is_more_than_two_labels_observed, and shared_data::second_observed_label.

Referenced by bufread_simple_label(), LabelObjectState< audit >::EndObject(), and parse_simple_label().

{
  if (sd->is_more_than_two_labels_observed || l == FLT_MAX)
    return;

  if (sd->first_observed_label != FLT_MAX)
  {
    if (sd->first_observed_label != l)
    {
      if (sd->second_observed_label != FLT_MAX)
      {
        if (sd->second_observed_label != l)
          sd->is_more_than_two_labels_observed = true;
      }
      else
        sd->second_observed_label = l;
    }
  }
  else
    sd->first_observed_label = l;
}

get_best_constant()

bool get_best_constant	(	vw &	all,
		float &	best_constant,
		float &	best_constant_loss
	)

Definition at line 3 of file best_constant.cc.

References shared_data::first_observed_label, VW::config::options_i::get_typed_option(), loss_function::getLoss(), loss_function::getType(), shared_data::is_more_than_two_labels_observed, vw::loss, vw::options, vw::sd, shared_data::second_observed_label, VW::config::options_i::was_supplied(), shared_data::weighted_labeled_examples, and shared_data::weighted_labels.

Referenced by count_label(), and VW::finish().

{
  if (all.sd->first_observed_label == FLT_MAX ||  // no non-test labels observed or function was never called
      (all.loss == nullptr) || (all.sd == nullptr))
    return false;

  float label1 = all.sd->first_observed_label;  // observed labels might be inside [sd->Min_label, sd->Max_label], so
                                                // can't use Min/Max
  float label2 = (all.sd->second_observed_label == FLT_MAX)
      ? 0
      : all.sd->second_observed_label;  // if only one label observed, second might be 0
  if (label1 > label2)
  {
    float tmp = label1;
    label1 = label2;
    label2 = tmp;
  }  // as don't use min/max - make sure label1 < label2

  float label1_cnt;
  float label2_cnt;

  if (label1 != label2)
  {
    label1_cnt = (float)(all.sd->weighted_labels - label2 * all.sd->weighted_labeled_examples) / (label1 - label2);
    label2_cnt = (float)all.sd->weighted_labeled_examples - label1_cnt;
  }
  else
    return false;

  if ((label1_cnt + label2_cnt) <= 0.)
    return false;

  auto funcName = all.loss->getType();
  if (funcName.compare("squared") == 0 || funcName.compare("Huber") == 0 || funcName.compare("classic") == 0)
    best_constant = (float)all.sd->weighted_labels / (float)(all.sd->weighted_labeled_examples);
  else if (all.sd->is_more_than_two_labels_observed)
  {
    // loss functions below don't have generic formuas for constant yet.
    return false;
  }
  else if (funcName.compare("hinge") == 0)
  {
    best_constant = label2_cnt <= label1_cnt ? -1.f : 1.f;
  }
  else if (funcName.compare("logistic") == 0)
  {
    label1 = -1.;  // override {-50, 50} to get proper loss
    label2 = 1.;

    if (label1_cnt <= 0)
      best_constant = 1.;
    else if (label2_cnt <= 0)
      best_constant = -1.;
    else
      best_constant = log(label2_cnt / label1_cnt);
  }
  else if (funcName.compare("quantile") == 0 || funcName.compare("pinball") == 0 || funcName.compare("absolute") == 0)
  {
    float tau = 0.5;

    if (all.options->was_supplied("quantile_tau"))
      tau = all.options->get_typed_option<float>("quantile_tau").value();

    float q = tau * (label1_cnt + label2_cnt);
    if (q < label2_cnt)
      best_constant = label2;
    else
      best_constant = label1;
  }
  else
    return false;

  if (!all.sd->is_more_than_two_labels_observed)
  {
    best_constant_loss = (label1_cnt > 0) ? all.loss->getLoss(all.sd, best_constant, label1) * label1_cnt : 0.0f;
    best_constant_loss += (label2_cnt > 0) ? all.loss->getLoss(all.sd, best_constant, label2) * label2_cnt : 0.0f;
    best_constant_loss /= label1_cnt + label2_cnt;
  }
  else
    best_constant_loss = FLT_MIN;

  return true;
}