119 lines
5.1 KiB
TypeScript
119 lines
5.1 KiB
TypeScript
import { parseTja } from './parse';
|
|
import { factorize, Factors } from './factorize';
|
|
import { join } from 'path';
|
|
import { readFileSync, writeFileSync, readdirSync } from 'fs';
|
|
import { parse } from 'csv-parse/sync';
|
|
|
|
async function train() {
|
|
const args = process.argv.slice(2);
|
|
const workingDir = args[0];
|
|
const scriptDir = args[1];
|
|
const dataDir = args[2];
|
|
const trainCount = parseInt(args[3]) || 100;
|
|
const validateCount = parseInt(args[4]) || 20;
|
|
const margin = parseFloat(args[5]) || 0.1;
|
|
|
|
const factorJsonPath = join(scriptDir, 'factor.json');
|
|
// 항상 script/ 위치 참조
|
|
let weights: Factors = JSON.parse(readFileSync(factorJsonPath, 'utf-8'));
|
|
|
|
// 결과물(로그 등)을 저장할 경로 (필요 시 활용)
|
|
const logPath = join(workingDir, 'training_log.txt');
|
|
|
|
const measureCsv = readFileSync(join(dataDir, 'measure.csv'), 'utf-8');
|
|
const records = parse(measureCsv, { columns: true, skip_empty_lines: true });
|
|
|
|
const tjaFiles = readdirSync(join(dataDir, 'tja')).filter(f => f.endsWith('.tja'));
|
|
const shuffled = tjaFiles.sort(() => 0.5 - Math.random());
|
|
const trainFiles = shuffled.slice(0, trainCount);
|
|
const validateFiles = shuffled.slice(trainCount, trainCount + validateCount);
|
|
|
|
console.log(`Training with ${trainFiles.length} files...`);
|
|
|
|
// 학습 로직 (Sigmoid + [1, 12] scaling)
|
|
const sigmoid = (x: number) => 1 / (1 + Math.exp(-x));
|
|
|
|
let error = Infinity;
|
|
let iterations = 0;
|
|
while (error > margin && iterations < 10) { // Spec에 따라 10번 반복
|
|
let totalError = 0;
|
|
let count = 0;
|
|
|
|
for (const file of trainFiles) {
|
|
const songno = file.replace(/\D/g, '');
|
|
const tjaContent = readFileSync(join(dataDir, 'tja', file), 'utf-8');
|
|
const parsed = parseTja(tjaContent);
|
|
if (!parsed) continue;
|
|
|
|
for (const diff of ['oni', 'edit'] as const) {
|
|
const course = parsed[diff];
|
|
if (!course) continue;
|
|
|
|
const target = records.find((r: any) => r.songno === songno && (r.diff === (diff === 'oni' ? 'oni' : 'ura')));
|
|
if (!target) continue;
|
|
|
|
const factors = factorize(course);
|
|
// 가중치 적용 전 정규화 (임의 값으로 가정)
|
|
const normalizedFactors = {
|
|
physical_density: Math.min(factors.physical_density / 20, 1),
|
|
stamina_requirement: Math.min(factors.stamina_requirement, 1),
|
|
pattern_complexity: Math.min(factors.pattern_complexity, 1),
|
|
rhythmic_complexity: Math.min(factors.rhythmic_complexity, 1),
|
|
reading_gimmick: Math.min(factors.reading_gimmick, 1)
|
|
};
|
|
|
|
const rawPrediction = Object.keys(normalizedFactors).reduce((sum, key) =>
|
|
sum + (normalizedFactors[key as keyof Factors] * weights[key as keyof Factors]), 0);
|
|
|
|
const prediction = (sigmoid(rawPrediction) * 11) + 1; // [1, 12]
|
|
|
|
const targetValue = parseFloat(target.상수);
|
|
const diff_val = targetValue - prediction;
|
|
totalError += Math.abs(diff_val);
|
|
count++;
|
|
|
|
// 가중치 업데이트 (간단한 경사 하강법)
|
|
for (const key in weights) {
|
|
const k = key as keyof Factors;
|
|
weights[k] += diff_val * normalizedFactors[k] * 0.01;
|
|
}
|
|
}
|
|
}
|
|
error = totalError / (count || 1);
|
|
console.log(`Iteration ${iterations}: Mean Error = ${error.toFixed(4)}`);
|
|
iterations++;
|
|
}
|
|
|
|
writeFileSync(factorJsonPath, JSON.stringify(weights, null, 2));
|
|
writeFileSync(join(workingDir, 'training_result.json'), JSON.stringify({ finalError: error, weights }, null, 2));
|
|
console.log(`Training complete. Weights saved to ${factorJsonPath}, result saved to ${workingDir}`);
|
|
|
|
// 검증 로직
|
|
console.log('\nValidation Results:');
|
|
for (const file of validateFiles) {
|
|
const songno = file.replace(/\D/g, '');
|
|
const tjaContent = readFileSync(join(dataDir, 'tja', file), 'utf-8');
|
|
const parsed = parseTja(tjaContent);
|
|
if (!parsed) continue;
|
|
|
|
for (const diff of ['oni', 'edit'] as const) {
|
|
const course = parsed[diff];
|
|
if (!course) continue;
|
|
|
|
const target = records.find((r: any) => r.songno === songno && (r.diff === (diff === 'oni' ? 'oni' : 'ura')));
|
|
if (!target) {
|
|
console.log(`[!] No match for ${songno} diff=${diff === 'oni' ? 'oni' : 'ura'}`);
|
|
continue;
|
|
}
|
|
|
|
const factors = factorize(course);
|
|
const prediction = Object.keys(factors).reduce((sum, key) =>
|
|
sum + (factors[key as keyof Factors] * weights[key as keyof Factors]), 0);
|
|
|
|
console.log(`[${songno}] Target: ${target.상수}, Predicted: ${prediction.toFixed(2)}, Diff: ${Math.abs(parseFloat(target.상수) - prediction).toFixed(2)}`);
|
|
}
|
|
}
|
|
}
|
|
|
|
train();
|