FST::Result_Weighter_Sampled< RETURNTYPE, IDXTYPE, DIMTYPE, SUBSET >::FeatureStat Struct Reference

Per-feature accumulators, one instance per feature index, updated by flush_batch(). m_is/m_isnot are adaptive-rate running means of the batch z-score, one side for evaluations in which the feature was selected ('is') and one for evaluations in which it was not ('isnot'); score() in STATS_ZCONTRAST mode returns their difference. raw_sum_is/raw_cnt_is accumulate the STATS_RAWMEAN statistic instead. n_is/n_isnot count how many evaluations landed on each side — also the exploration counts exposed via count_is()/count_isnot(). More...

#include <result_weighter_sampled.hpp>

Public Attributes
RETURNTYPE	m_is
	adaptive-rate mean of batch-z over evaluations where the feature was selected (STATS_ZCONTRAST score source)
RETURNTYPE	m_isnot
	adaptive-rate mean of batch-z over evaluations where the feature was not selected (STATS_ZCONTRAST score source)
RETURNTYPE	v_is
	adaptive-rate mean of z^2 on the 'is' side; maintained as a dispersion estimate but not read by score()
RETURNTYPE	raw_sum_is
	1/|S|-weighted sum of raw criterion values over 'is' evaluations (STATS_RAWMEAN score source)
RETURNTYPE	raw_cnt_is
	matching 1/|S|-weighted normalizer for raw_sum_is
IDXTYPE	n_is
	number of evaluations in which the feature was selected (exploration count, see count_is())
IDXTYPE	n_isnot
	number of evaluations in which the feature was not selected (exploration count, see count_isnot())

Detailed Description

template<class RETURNTYPE, typename IDXTYPE, typename DIMTYPE, class SUBSET>
struct FST::Result_Weighter_Sampled< RETURNTYPE, IDXTYPE, DIMTYPE, SUBSET >::FeatureStat

Per-feature accumulators, one instance per feature index, updated by flush_batch(). m_is/m_isnot are adaptive-rate running means of the batch z-score, one side for evaluations in which the feature was selected ('is') and one for evaluations in which it was not ('isnot'); score() in STATS_ZCONTRAST mode returns their difference. raw_sum_is/raw_cnt_is accumulate the STATS_RAWMEAN statistic instead. n_is/n_isnot count how many evaluations landed on each side — also the exploration counts exposed via count_is()/count_isnot().

---

The documentation for this struct was generated from the following file:

• /Users/psms/dev/devtest1/_src_search/result_weighter_sampled.hpp