mirror of
https://github.com/johnkerl/miller.git
synced 2026-07-18 00:45:47 +00:00
* Tier-2 structured verb options: OptionSpec, initial migration (#2098) PR 3 of the AI-friendly roadmap (plans/plan-2098-llm.md). Infrastructure: - Add OptionSpec{Flag,Arg,Type,Desc,Repeatable,Values} to pkg/transformers/aaa_record_transformer.go alongside TransformerSetup. Type is one of: bool, string, int, float, csv-list, regex, filename, format, enum. For type=="enum", Values lists the valid choices. - Add Options []OptionSpec to TransformerSetup (nil = not yet migrated). - Emit Options in VerbInfoForJSON (omitempty so unmigrated verbs stay backward-compatible; agents check key presence for Tier-2 availability). UsageText is always present as the Tier-1 prose fallback. - Add VerbOptionsNilCheck() in aaa_verb_options_check.go: progress report of migrated vs. unmigrated verbs, analogous to FLAG_TABLE.NilCheck(). - Wire verb-options-nil-check into mlr help (internal/docgen section). Initial migration (5/70 verbs): - nothing: empty Options (no verb-specific options, explicitly migrated) - cat: -n (bool), -N (string), -g (csv-list), --filename, --filenum (bool) - head: -g (csv-list), -n (int) - tail: -g (csv-list), -n (int) - tee: -a, -p (bool) Tests: - 5 new unit tests in aaa_transformer_json_test.go covering migrated/ unmigrated paths, field population, JSON round-trip, and key-presence. - Regression test case 0003: mlr help verb-options-nil-check golden output. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com> * Migrate all 70 verbs to structured OptionSpec; bump catalog schema to v2 Completes the Tier-2 migration started in the previous commit. Every verb in TRANSFORMER_LOOKUP_TABLE now has a non-nil Options field. - Workflow-migrated all 65 remaining verbs. Each Setup var now carries Options: []OptionSpec{...} with Flag/Arg/Type/Desc fields. Verbs with no verb-specific options (altkv, check, group-like, nothing, etc.) use an empty slice to signal "migrated but no options." - Drop `omitempty` from VerbInfoForJSON.Options: empty slices were silently dropped, making migrated-no-option verbs indistinguishable from unmigrated ones in JSON. Without omitempty: null=unmigrated, []=migrated-no-options, [...]= migrated-with-options. Bump catalogSchemaVersion 1→2 for this shape change. - Replace the two "unmigrated-verb" unit tests (which used stats1 as an example) with TestAllVerbsFullyMigrated (asserts every verb has non-nil Options) and TestAllVerbsHaveOptionsKeyInJSON (asserts every migrated verb emits the "options" key in JSON). - Regenerate test/cases/cli-help/0003/expout: now reads "Verb options migration: 70/70 migrated." Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com> * remove a transitional helper * git rms * Render verb usage Options blocks from structured OptionSpec Each verb's usage message and its Tier-2 OptionSpec list previously duplicated the option text. New WriteVerbOptions (aaa_verb_usage.go) renders the "Options:" block from the specs: aligned flag column, descriptions word-wrapped at 80, uniform trailing -h|--help line. - OptionSpec gains Aliases (JSON "aliases") so long-form spellings like join's --lk|--left-keep-field-names survive in both outputs - All 70 verbs migrated; options literals hoisted to package-level vars (usage funcs can't reference their Setup var without a Go init cycle) - Hand-written per-option details the specs had condensed away are merged into Desc, enriching the JSON catalog - Non-option prose (examples, cross-references, dynamic accumulator listings) kept verbatim - Regenerated the six usage-embedding regression expectations and the two affected doc pages Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Fix pre-existing usage-text bugs surfaced by the OptionSpec migration - gap: usage said "One of -f or -g is required" but the parser takes -n or -g - seqgen: drop description line copy-pasted from cat ("Passes input records directly to output...") which contradicted "Discards the input record stream" - utf8-to-latin1: description read inverted ("from Latin-1 to UTF-8") - sec2gmtdate: usage said "../c/mlr" instead of "mlr" - top: document the accepted-but-undocumented --max flag - stats2: add linreg-pca to the -a enum values, matching the runtime accumulator table Regression expectations and docs regenerated accordingly. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Fix check usage sentence order; stats1 usage blank line to usage stream - check: the description's second and third lines were swapped, reading "Consumes records without printing any output, / Useful for doing a well-formatted check on input data. / with the exception that warnings are printed to stderr." - stats1: a bare fmt.Println() in the usage func wrote its blank line to process stdout instead of the usage output stream Regression expectation and docs regenerated. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
168 lines
4.5 KiB
Go
168 lines
4.5 KiB
Go
package transformers
|
|
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
"strings"
|
|
|
|
"github.com/johnkerl/miller/v6/pkg/cli"
|
|
"github.com/johnkerl/miller/v6/pkg/mlrval"
|
|
"github.com/johnkerl/miller/v6/pkg/types"
|
|
"github.com/kshedden/statmodel/duration"
|
|
"github.com/kshedden/statmodel/statmodel"
|
|
)
|
|
|
|
const verbNameSurv = "surv"
|
|
|
|
var survOptions = []OptionSpec{
|
|
{Flag: "-d", Arg: "{field}", Type: "string", Desc: "Name of duration field (time-to-event or censoring)."},
|
|
{Flag: "-s", Arg: "{field}", Type: "string", Desc: "Name of status field (0=censored, 1=event)."},
|
|
}
|
|
|
|
// SurvSetup defines the surv verb: Kaplan-Meier survival curve.
|
|
var SurvSetup = TransformerSetup{
|
|
Verb: verbNameSurv,
|
|
UsageFunc: transformerSurvUsage,
|
|
ParseCLIFunc: transformerSurvParseCLI,
|
|
IgnoresInput: false,
|
|
Options: survOptions,
|
|
}
|
|
|
|
func transformerSurvUsage(o *os.File) {
|
|
fmt.Fprintf(o, "Usage: %s %s -d {duration-field} -s {status-field}\n", "mlr", verbNameSurv)
|
|
fmt.Fprint(o, "\nEstimate Kaplan-Meier survival curve (right-censored).\n")
|
|
WriteVerbOptions(o, survOptions)
|
|
}
|
|
|
|
func transformerSurvParseCLI(
|
|
pargi *int,
|
|
argc int,
|
|
args []string,
|
|
_ *cli.TOptions,
|
|
doConstruct bool,
|
|
) (RecordTransformer, error) {
|
|
argi := *pargi
|
|
verb := args[argi]
|
|
argi++
|
|
|
|
var durationField, statusField string
|
|
|
|
loop:
|
|
for argi < argc {
|
|
opt := args[argi]
|
|
if !strings.HasPrefix(opt, "-") {
|
|
break
|
|
}
|
|
switch opt {
|
|
case "-h", "--help":
|
|
transformerSurvUsage(os.Stdout)
|
|
return nil, cli.ErrHelpRequested
|
|
case "-d":
|
|
if argi+1 >= argc {
|
|
return nil, cli.VerbErrorf(verb, "-d requires an argument")
|
|
}
|
|
argi++
|
|
durationField = args[argi]
|
|
argi++
|
|
case "-s":
|
|
if argi+1 >= argc {
|
|
return nil, cli.VerbErrorf(verb, "-s requires an argument")
|
|
}
|
|
argi++
|
|
statusField = args[argi]
|
|
argi++
|
|
default:
|
|
break loop
|
|
}
|
|
}
|
|
*pargi = argi
|
|
if !doConstruct {
|
|
return nil, nil
|
|
}
|
|
if durationField == "" {
|
|
return nil, fmt.Errorf("mlr %s: -d option is required", verb)
|
|
}
|
|
if statusField == "" {
|
|
return nil, fmt.Errorf("mlr %s: -s option is required", verb)
|
|
}
|
|
return NewTransformerSurv(durationField, statusField)
|
|
}
|
|
|
|
// TransformerSurv holds fields for surv verb.
|
|
type TransformerSurv struct {
|
|
durationField string
|
|
statusField string
|
|
times []float64
|
|
events []bool
|
|
}
|
|
|
|
// NewTransformerSurv constructs a new surv transformer.
|
|
func NewTransformerSurv(durationField, statusField string) (*TransformerSurv, error) {
|
|
return &TransformerSurv{
|
|
durationField: durationField,
|
|
statusField: statusField,
|
|
times: []float64{},
|
|
events: []bool{},
|
|
}, nil
|
|
}
|
|
|
|
// Transform processes each record or emits results at end-of-stream.
|
|
func (tr *TransformerSurv) Transform(
|
|
inrecAndContext *types.RecordAndContext,
|
|
outputRecordsAndContexts *[]*types.RecordAndContext,
|
|
inputDownstreamDoneChannel <-chan bool,
|
|
outputDownstreamDoneChannel chan<- bool,
|
|
) {
|
|
HandleDefaultDownstreamDone(inputDownstreamDoneChannel, outputDownstreamDoneChannel)
|
|
if !inrecAndContext.EndOfStream {
|
|
rec := inrecAndContext.Record
|
|
mvDur := rec.Get(tr.durationField)
|
|
if mvDur == nil {
|
|
// Skip records missing the duration field
|
|
return
|
|
}
|
|
duration := mvDur.GetNumericToFloatValueOrDie()
|
|
mvStat := rec.Get(tr.statusField)
|
|
if mvStat == nil {
|
|
// Skip records missing the status field
|
|
return
|
|
}
|
|
status := mvStat.GetNumericToFloatValueOrDie() != 0
|
|
tr.times = append(tr.times, duration)
|
|
tr.events = append(tr.events, status)
|
|
} else {
|
|
// Compute survival using kshedden/statmodel
|
|
n := len(tr.times)
|
|
if n == 0 {
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
|
|
return
|
|
}
|
|
durations := tr.times
|
|
statuses := make([]float64, n)
|
|
for i, ev := range tr.events {
|
|
if ev {
|
|
statuses[i] = 1.0
|
|
} else {
|
|
statuses[i] = 0.0
|
|
}
|
|
}
|
|
dataCols := [][]float64{durations, statuses}
|
|
names := []string{tr.durationField, tr.statusField}
|
|
ds := statmodel.NewDataset(dataCols, names)
|
|
sf, err := duration.NewSurvfuncRight(ds, tr.durationField, tr.statusField, &duration.SurvfuncRightConfig{})
|
|
if err != nil {
|
|
fmt.Fprintf(os.Stderr, "mlr surv: %v\n", err)
|
|
os.Exit(1)
|
|
}
|
|
sf.Fit()
|
|
times := sf.Time()
|
|
survProbs := sf.SurvProb()
|
|
for i, t := range times {
|
|
newrec := mlrval.NewMlrmapAsRecord()
|
|
newrec.PutCopy("time", mlrval.FromFloat(t))
|
|
newrec.PutCopy("survival", mlrval.FromFloat(survProbs[i]))
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, types.NewRecordAndContext(newrec, &inrecAndContext.Context))
|
|
}
|
|
*outputRecordsAndContexts = append(*outputRecordsAndContexts, inrecAndContext)
|
|
}
|
|
}
|