Janady13/missionmatch / internal/platform/learn/dataset.go

Source identity

Field	Recorded value
Source type	GitHub source
Original record	Janady13/missionmatch / internal/platform/learn/dataset.go
Date	Not specified in source
Repository	Janady13/missionmatch
Revision	720d47fae476b0d38477ae4401697d372b1ea2bc
Branch	feature/opportunity-to-outcome
Path or archive member	internal/platform/learn/dataset.go
Original SHA-256	c3d8663742cef243432d197449c930a7a04f1a9b0ab84b85b8c5b38e3484119f
Git blob SHA	064724001bd594c918b7679060b92c1457823344
Reading-copy SHA-256	c3d8663742cef243432d197449c930a7a04f1a9b0ab84b85b8c5b38e3484119f

Original source ↗

Every recorded occurrence

These 10 records contain identical original source bytes. Their paths and revisions remain part of the archive.

Original record	Branch or archive	Revision / identifier	Original location
Janady13/missionmatch / internal/platform/learn/dataset.go	feature/opportunity-to-outcome	720d47fae476b0d38477ae4401697d372b1ea2bc	Open original
Janady13/missionmatch / internal/platform/learn/dataset.go	collision-deconfliction	4ee5a09972608ed89f8377c6665542d5f450f0a6	Open original
Janady13/missionmatch / internal/platform/learn/dataset.go	master	1e9249840a4302ec82e123b9c9cb6f75badea3e4	Open original
Janady13/missionmatch / internal/platform/learn/dataset.go	mag-substrate	b82c7100a492dec67dfd1eda6b3f53def859be35	Open original
Janady13/missionmatch / internal/platform/learn/dataset.go	time-to-fill-survival	b66e1e505863d4f17741a4b9ede73509e45bd6c6	Open original
Janady13/missionmatch / internal/platform/learn/dataset.go	presentation-readiness	eb574acaa29d71ce4d0f852572e87c275c79fdb7	Open original
Janady13/missionmatch / internal/platform/learn/dataset.go	vendor-intelligence	fe9796a19c261951d3f2565206c0c1b5ac294465	Open original
Janady13/missionmatch / internal/platform/learn/dataset.go	phase2-connectors	e038d4c687aec16f8bd9bc4d907eea14d91f8704	Open original
Janady13/missionmatch / internal/platform/learn/dataset.go	feature/aioe-upgrade	2178e7298d0e5d9af83afa12402fd587f0ba6ed8	Open original
Janady13/missionmatch / internal/platform/learn/dataset.go	capture-readiness	bae6af7cb2997e819174a9e9cfff5e16067a1975	Open original

Recovered source transcript

Download complete source text ↓70 lines · 2.8 KB

package learn

import "sort"

// Result values a bid label can carry, mirroring the bid_outcomes.result CHECK. Only win and loss are decided
// labels a fit consumes; pending and no_bid are dropped by BuildDataset (an undecided bid is not a training
// example). These are the exact strings the ledger stores, so a raw scan maps straight onto them.
const (
	ResultWin     = "win"
	ResultLoss    = "loss"
	ResultNoBid   = "no_bid"
	ResultPending = "pending"
)

// LabeledRow is one bid from the ledger: its decided Result and the named feature values of the segment the
// bid was for (market structure only, NEVER a protected attribute or a per candidate score). BuildDataset
// keeps only the rows whose Result is win or loss; everything else is an undecided bid and is dropped.
type LabeledRow struct {
	Result   string             // one of the Result constants; only win and loss survive into the matrix
	Features map[string]float64 // named segment feature values for this bid
}

// IsDecided reports whether a result is a decided label (a win or a loss). A pending or no_bid row carries no
// outcome to learn from and is excluded from the training matrix.
func IsDecided(result string) bool {
	return result == ResultWin || result == ResultLoss
}

// BuildDataset assembles the labeled feature matrix from the decided bids. It drops every undecided row
// (pending, no_bid, or an unrecognized result), maps win to label 1 and loss to label 0, and returns the
// feature matrix x (one row per decided bid, one column per feature), the labels y, and the feature names in a
// STABLE order (the sorted union of every feature key across the decided rows). A row missing a feature the
// union contains contributes 0.0 for that column, so a ragged input still yields a rectangular matrix; the
// stable ordering means the same ledger always produces the same column layout, which the trainer relies on to
// pair a fitted coefficient with its feature name. No database, no I/O: this is pure over an in memory rowset.
func BuildDataset(rows []LabeledRow) (x [][]float64, y []int, featureNames []string) {
	// The sorted union of feature names across the decided rows: the stable column layout.
	nameSet := map[string]struct{}{}
	for _, r := range rows {
		if !IsDecided(r.Result) {
			continue
		}
		for name := range r.Features {
			nameSet[name] = struct{}{}
		}
	}
	featureNames = make([]string, 0, len(nameSet))
	for name := range nameSet {
		featureNames = append(featureNames, name)
	}
	sort.Strings(featureNames)

	for _, r := range rows {
		if !IsDecided(r.Result) {
			continue
		}
		row := make([]float64, len(featureNames))
		for j, name := range featureNames {
			row[j] = r.Features[name] // a missing feature is the zero column, the documented default
		}
		x = append(x, row)
		if r.Result == ResultWin {
			y = append(y, 1)
		} else {
			y = append(y, 0)
		}
	}
	return x, y, featureNames
}