This commit is contained in:
2026-04-25 17:57:19 +09:00
parent 956c53ba23
commit 9962544bf5
37 changed files with 11666665 additions and 146 deletions

181
script/compare_factor.ts Normal file
View File

@@ -0,0 +1,181 @@
import Bun from 'bun';
import path from 'node:path';
import { parseArgs } from 'node:util';
import fs from 'node:fs';
const { values } = parseArgs({
args: Bun.argv,
options: {
workingDir: { type: "string" },
dataDir: { type: "string" },
script: { type: "string" },
},
strict: true,
allowPositionals: true,
});
if (!values.workingDir || !values.dataDir || !values.script) {
console.error("Usage: bun run script/compare_factor.ts --workingDir <dir> --dataDir <dir> --script <python_script>");
process.exit(1);
}
const workingDir = values.workingDir;
const dataDir = values.dataDir;
const predictScript = values.script;
const tempFileName = "temp.json";
const tempFilePath = path.join(workingDir, tempFileName);
// 1. 전처리 실행 (Factor 기반)
console.log("Step 1: Running factor preprocessing to temp.json...");
const preprocessResult = Bun.spawnSync([
"bun", "run", "script/preprocess_factor.ts",
"--workingDir", workingDir,
"--dataDir", dataDir,
"--fileName", tempFileName
]);
if (!preprocessResult.success) {
console.error("Preprocessing failed");
console.error(preprocessResult.stderr.toString());
process.exit(1);
}
// 2. measure.csv 로드
console.log("Step 2: Loading measure.csv...");
const measurePath = path.join(dataDir, "measure.csv");
const measureContent = fs.readFileSync(measurePath, "utf-8");
const measureMap = new Map<string, number>();
measureContent.split("\n").forEach((line, index) => {
if (index === 0 || !line.trim()) return;
const parts = line.split(",");
if (parts.length >= 3) {
const constant = parts[0];
const songno = parts[1];
const diff = parts[2];
measureMap.set(`${songno.trim()}_${diff.trim()}`, parseFloat(constant));
}
});
// 3. temp.json 로드하여 대상 곡 목록 추출
const factors = JSON.parse(fs.readFileSync(tempFilePath, "utf-8"));
const uniqueSongnos = Array.from(new Set(factors.map((f: any) => f.songno)));
// 4. 예측 및 비교
console.log(`Step 3: Predicting and comparing ${uniqueSongnos.length} songs (Factor-based)...`);
const comparisonResults: any[] = [];
let processedCount = 0;
for (const songno of uniqueSongnos) {
try {
const predictProcess = Bun.spawnSync([
"python3", predictScript,
"--workingDir", workingDir,
"--songno", songno as string,
"--factor", tempFilePath // 파이썬 스크립트 인자명이 --factor로 고정되어 있는 경우를 가정
]);
if (!predictProcess.success) {
console.error(`\n[ERROR] Failed to predict songno ${songno}`);
processedCount++;
continue;
}
const output = predictProcess.stdout.toString().trim();
const jsonStart = output.indexOf('[');
const jsonEnd = output.lastIndexOf(']') + 1;
if (jsonStart !== -1 && jsonEnd !== 0) {
const predictions = JSON.parse(output.substring(jsonStart, jsonEnd));
predictions.forEach((pred: any) => {
const key = `${pred.songno}_${pred.diff}`;
const actual = measureMap.get(key);
if (actual !== undefined) {
comparisonResults.push({
songno: pred.songno,
diff: pred.diff,
actual: actual,
predicted: pred.predicted,
error: Math.abs(actual - pred.predicted)
});
}
});
}
processedCount++;
if (processedCount % 10 === 0 || processedCount === uniqueSongnos.length) {
const percent = ((processedCount / uniqueSongnos.length) * 100).toFixed(1);
process.stdout.write(`\rProgress: ${processedCount}/${uniqueSongnos.length} (${percent}%) `);
}
} catch (err) {
console.error(`\nError processing songno ${songno}:`, err);
processedCount++;
}
}
console.log("\nPrediction finished.");
const avgError = comparisonResults.reduce((acc, curr) => acc + curr.error, 0) / comparisonResults.length;
const resultData = {
summary: {
total_compared: comparisonResults.length,
average_absolute_error: avgError,
timestamp: new Date().toISOString(),
script_used: predictScript,
type: "factor"
},
details: comparisonResults.sort((a, b) => b.error - a.error)
};
const comparePath = path.join(workingDir, "compare.json");
fs.writeFileSync(comparePath, JSON.stringify(resultData, null, 2), "utf-8");
console.log(`\nComparison complete! Results saved to: ${comparePath}`);
// 6. 결과 시각화 (compare.png 생성)
if (comparisonResults.length > 0) {
console.log("Step 4: Generating comparison plot (compare.png)...");
const plotPythonCode = `
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import json
import os
with open('${comparePath}', 'r', encoding='utf-8') as f:
data = json.load(f)
if not data['details']:
print("No details to plot.")
exit(0)
df = pd.DataFrame(data['details'])
df['abs_error'] = (df['actual'] - df['predicted']).abs()
df = df.sort_values('abs_error', ascending=False).reset_index(drop=True)
plt.figure(figsize=(12, 6))
plt.switch_backend('Agg')
sns.scatterplot(x=df.index, y=df['abs_error'], alpha=0.6, s=20, color='royalblue')
plt.axhline(0.2, color='green', linestyle='--', linewidth=0.8, alpha=0.5, label='Target (0.2)')
plt.axhline(0.5, color='blue', linestyle='--', linewidth=0.8, alpha=0.5)
plt.axhline(1.0, color='red', linestyle='--', linewidth=0.8, alpha=0.5)
plt.ylim(0, max(3.5, df['abs_error'].max() + 0.5) if not df.empty else 3.5)
plt.title('Comparison Absolute Error Distribution (Feature-based)', fontsize=14)
plt.xlabel('Samples (Sorted by Error Magnitude)', fontsize=12)
plt.ylabel('Absolute Error', fontsize=12)
plt.grid(True, axis='y', alpha=0.3)
plot_path = os.path.join('${workingDir}', 'compare.png')
plt.savefig(plot_path)
print(f"Plot saved to: {plot_path}")
`;
const plotProc = Bun.spawnSync(["python3", "-c", plotPythonCode]);
if (plotProc.success) {
console.log(plotProc.stdout.toString().trim());
} else {
console.error("Failed to generate plot:");
console.error(plotProc.stderr.toString());
}
}

View File

@@ -15,7 +15,7 @@ const { values } = parseArgs({
});
if (!values.workingDir || !values.dataDir || !values.script) {
console.error("Usage: bun run script/compare.ts --workingDir <dir> --dataDir <dir> --script <python_script>");
console.error("Usage: bun run script/compare_feature.ts --workingDir <dir> --dataDir <dir> --script <python_script>");
process.exit(1);
}
@@ -25,10 +25,10 @@ const predictScript = values.script;
const tempFileName = "temp.json";
const tempFilePath = path.join(workingDir, tempFileName);
// 1. 전처리 실행 (temp.json 생성하여 기존 features.json 보존)
console.log("Step 1: Running preprocessing to temp.json...");
// 1. 전처리 실행 (Feature 기반)
console.log("Step 1: Running feature preprocessing to temp.json...");
const preprocessResult = Bun.spawnSync([
"bun", "run", "script/preprocess.ts",
"bun", "run", "script/preprocess_feature.ts",
"--workingDir", workingDir,
"--dataDir", dataDir,
"--fileName", tempFileName
@@ -62,7 +62,7 @@ const features = JSON.parse(fs.readFileSync(tempFilePath, "utf-8"));
const uniqueSongnos = Array.from(new Set(features.map((f: any) => f.songno)));
// 4. 예측 및 비교
console.log(`Step 3: Predicting and comparing ${uniqueSongnos.length} songs...`);
console.log(`Step 3: Predicting and comparing ${uniqueSongnos.length} songs (Feature-based)...`);
const comparisonResults: any[] = [];
let processedCount = 0;
@@ -77,39 +77,31 @@ for (const songno of uniqueSongnos) {
if (!predictProcess.success) {
console.error(`\n[ERROR] Failed to predict songno ${songno}`);
console.error(predictProcess.stderr.toString());
processedCount++;
continue;
}
const output = predictProcess.stdout.toString().trim();
// JSON 부분만 추출 (경고문 등이 섞여있을 경우 대비)
const jsonStart = output.indexOf('[');
const jsonEnd = output.lastIndexOf(']') + 1;
if (jsonStart === -1 || jsonEnd === 0) {
console.error(`\n[ERROR] Invalid output format for songno ${songno}`);
processedCount++;
continue;
if (jsonStart !== -1 && jsonEnd !== 0) {
const predictions = JSON.parse(output.substring(jsonStart, jsonEnd));
predictions.forEach((pred: any) => {
const key = `${pred.songno}_${pred.diff}`;
const actual = measureMap.get(key);
if (actual !== undefined) {
comparisonResults.push({
songno: pred.songno,
diff: pred.diff,
actual: actual,
predicted: pred.predicted,
error: Math.abs(actual - pred.predicted)
});
}
});
}
const predictions = JSON.parse(output.substring(jsonStart, jsonEnd));
predictions.forEach((pred: any) => {
const key = `${pred.songno}_${pred.diff}`;
const actual = measureMap.get(key);
if (actual !== undefined) {
comparisonResults.push({
songno: pred.songno,
diff: pred.diff,
actual: actual,
predicted: pred.predicted,
error: Math.abs(actual - pred.predicted)
});
}
});
processedCount++;
if (processedCount % 10 === 0 || processedCount === uniqueSongnos.length) {
const percent = ((processedCount / uniqueSongnos.length) * 100).toFixed(1);
@@ -122,27 +114,68 @@ for (const songno of uniqueSongnos) {
}
console.log("\nPrediction finished.");
// 5. 결과 분석 및 저장
if (comparisonResults.length === 0) {
console.error("No comparison results were generated.");
process.exit(1);
}
const avgError = comparisonResults.reduce((acc, curr) => acc + curr.error, 0) / comparisonResults.length;
const resultData = {
summary: {
total_compared: comparisonResults.length,
average_absolute_error: avgError,
timestamp: new Date().toISOString(),
script_used: predictScript
script_used: predictScript,
type: "feature"
},
details: comparisonResults.sort((a, b) => b.error - a.error)
};
const comparePath = path.join(workingDir, "compare.json");
const comparePath = path.join(workingDir, "compare_feature.json");
fs.writeFileSync(comparePath, JSON.stringify(resultData, null, 2), "utf-8");
console.log(`\nComparison complete!`);
console.log(`Total compared: ${comparisonResults.length}`);
console.log(`Average Error: ${avgError.toFixed(4)}`);
console.log(`Results saved to: ${comparePath}`);
console.log(`\nComparison complete! Results saved to: ${comparePath}`);
// 6. 결과 시각화 (compare.png 생성)
if (comparisonResults.length > 0) {
console.log("Step 4: Generating comparison plot (compare.png)...");
const plotPythonCode = `
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import json
import os
with open('${comparePath}', 'r', encoding='utf-8') as f:
data = json.load(f)
if not data['details']:
print("No details to plot.")
exit(0)
df = pd.DataFrame(data['details'])
df['abs_error'] = (df['actual'] - df['predicted']).abs()
df = df.sort_values('abs_error', ascending=False).reset_index(drop=True)
plt.figure(figsize=(12, 6))
plt.switch_backend('Agg')
sns.scatterplot(x=df.index, y=df['abs_error'], alpha=0.6, s=20, color='royalblue')
plt.axhline(0.2, color='green', linestyle='--', linewidth=0.8, alpha=0.5, label='Target (0.2)')
plt.axhline(0.5, color='blue', linestyle='--', linewidth=0.8, alpha=0.5)
plt.axhline(1.0, color='red', linestyle='--', linewidth=0.8, alpha=0.5)
plt.ylim(0, max(3.5, df['abs_error'].max() + 0.5) if not df.empty else 3.5)
plt.title('Comparison Absolute Error Distribution (Feature-based)', fontsize=14)
plt.xlabel('Samples (Sorted by Error Magnitude)', fontsize=12)
plt.ylabel('Absolute Error', fontsize=12)
plt.grid(True, axis='y', alpha=0.3)
plot_path = os.path.join('${workingDir}', 'compare.png')
plt.savefig(plot_path)
print(f"Plot saved to: {plot_path}")
`;
const plotProc = Bun.spawnSync(["python3", "-c", plotPythonCode]);
if (plotProc.success) {
console.log(plotProc.stdout.toString().trim());
} else {
console.error("Failed to generate plot:");
console.error(plotProc.stderr.toString());
}
}

View File

@@ -1,94 +0,0 @@
import Bun from 'bun';
import path from 'node:path';
import { parseArgs } from 'node:util';
import fs from 'node:fs';
import { featurize } from '../preprocess/featurize';
import { parseTja } from '../preprocess/parse';
const { values } = parseArgs({
args: Bun.argv,
options: {
tja: {
type: "string"
},
workingDir: {
type: "string"
},
script: {
type: "string"
}
},
allowPositionals: true,
});
if (!values.tja || !values.workingDir || !values.script) {
console.error("Usage: bun script/predict_tja.ts --tja <path_to_tja> [--workingDir <dir>] [--script <python_script>]");
process.exit(1);
}
const tjaPath = values.tja;
if (!fs.existsSync(tjaPath)) {
console.error(`File not found: ${tjaPath}`);
process.exit(1);
}
const workingDir = values.workingDir!;
const pythonScript = values.script!;
if (!fs.existsSync(pythonScript)) {
console.error(`Python script not found: ${pythonScript}`);
process.exit(1);
}
// 1. TJA 파싱 및 피처 추출
const tjaContent = fs.readFileSync(tjaPath, 'utf-8');
const songno = path.basename(tjaPath, '.tja');
const parsed = parseTja(tjaContent);
const features: any[] = [];
if (parsed.oni) {
features.push({
songno,
difficulty: 'oni',
...featurize(parsed.oni)
});
}
if (parsed.edit) {
features.push({
songno,
difficulty: 'ura',
...featurize(parsed.edit)
});
}
if (features.length === 0) {
console.error("No Oni or Ura difficulty found in the TJA file.");
process.exit(1);
}
// 2. 임시 피처 파일 저장
const tempFeaturePath = path.join(workingDir, `temp_predict_${Date.now()}.json`);
fs.writeFileSync(tempFeaturePath, JSON.stringify(features, null, 2), 'utf-8');
try {
// 3. Python 예측 스크립트 실행
const proc = Bun.spawnSync([
"python3",
pythonScript,
"--workingDir", workingDir,
"--feature", tempFeaturePath,
"--songno", songno
]);
if (proc.success) {
console.log(proc.stdout.toString());
} else {
console.error("Prediction failed:");
console.error(proc.stderr.toString());
}
} finally {
// 4. 임시 파일 삭제
if (fs.existsSync(tempFeaturePath)) {
fs.unlinkSync(tempFeaturePath);
}
}

View File

@@ -0,0 +1,68 @@
import Bun from 'bun';
import path from 'node:path';
import { parseArgs } from 'node:util';
import fs from 'node:fs';
import { factorize } from '../preprocess/factorize';
import { parseTja } from '../preprocess/parse';
const { values } = parseArgs({
args: Bun.argv,
options: {
tja: { type: "string" },
workingDir: { type: "string" },
script: { type: "string" }
},
allowPositionals: true,
});
if (!values.tja || !values.workingDir || !values.script) {
console.error("Usage: bun script/predict_tja_factor.ts --tja <path_to_tja> --workingDir <dir> --script <python_script>");
process.exit(1);
}
const tjaPath = values.tja;
const workingDir = values.workingDir!;
const pythonScript = values.script!;
const tjaContent = fs.readFileSync(tjaPath, 'utf-8');
const songno = path.basename(tjaPath, '.tja');
const parsed = parseTja(tjaContent);
const factors: any[] = [];
if (parsed.oni) {
factors.push({
songno,
difficulty: 'oni',
factors: factorize(parsed.oni)
});
}
if (parsed.edit) {
factors.push({
songno,
difficulty: 'ura',
factors: factorize(parsed.edit)
});
}
if (factors.length === 0) {
console.error("No Oni or Ura difficulty found.");
process.exit(1);
}
const tempFactorPath = path.join(workingDir, `temp_predict_fact_${Date.now()}.json`);
fs.writeFileSync(tempFactorPath, JSON.stringify(factors, null, 2), 'utf-8');
try {
const proc = Bun.spawnSync([
"python3",
pythonScript,
"--workingDir", workingDir,
"--feature", tempFactorPath, // 파이썬 스크립트 인자명이 --feature로 고정되어 있다고 가정
"--songno", songno
]);
if (proc.success) console.log(proc.stdout.toString());
else console.error("Prediction failed:", proc.stderr.toString());
} finally {
if (fs.existsSync(tempFactorPath)) fs.unlinkSync(tempFactorPath);
}

View File

@@ -0,0 +1,49 @@
import Bun from 'bun';
import path from 'node:path';
import { parseArgs } from 'node:util';
import fs from 'node:fs';
import { featurize } from '../preprocess/featurize';
import { parseTja } from '../preprocess/parse';
const { values } = parseArgs({
args: Bun.argv,
options: {
tja: { type: "string" },
workingDir: { type: "string" },
script: { type: "string" }
},
allowPositionals: true,
});
if (!values.tja || !values.workingDir || !values.script) {
console.error("Usage: bun script/predict_tja_feature.ts --tja <path_to_tja> --workingDir <dir> --script <python_script>");
process.exit(1);
}
const tjaPath = values.tja;
const workingDir = values.workingDir!;
const pythonScript = values.script!;
const tjaContent = fs.readFileSync(tjaPath, 'utf-8');
const songno = path.basename(tjaPath, '.tja');
const parsed = parseTja(tjaContent);
const features: any[] = [];
if (parsed.oni) features.push({ songno, difficulty: 'oni', ...featurize(parsed.oni) });
if (parsed.edit) features.push({ songno, difficulty: 'ura', ...featurize(parsed.edit) });
if (features.length === 0) {
console.error("No Oni or Ura difficulty found.");
process.exit(1);
}
const tempFeaturePath = path.join(workingDir, `temp_predict_feat_${Date.now()}.json`);
fs.writeFileSync(tempFeaturePath, JSON.stringify(features, null, 2), 'utf-8');
try {
const proc = Bun.spawnSync(["python3", pythonScript, "--workingDir", workingDir, "--feature", tempFeaturePath, "--songno", songno]);
if (proc.success) console.log(proc.stdout.toString());
else console.error("Prediction failed:", proc.stderr.toString());
} finally {
if (fs.existsSync(tempFeaturePath)) fs.unlinkSync(tempFeaturePath);
}

View File

@@ -0,0 +1,65 @@
import Bun from 'bun';
import path from 'node:path';
import { parseArgs } from 'node:util';
import fs, { mkdirSync } from 'node:fs';
import { factorize } from '../preprocess/factorize';
import { parseTja } from '../preprocess/parse'
const { values } = parseArgs({
args: Bun.argv,
options: {
workingDir: {
type: "string"
},
dataDir: {
type: "string"
},
fileName: {
type: "string"
}
},
allowPositionals: true,
})
if (!values.dataDir || !values.workingDir) {
console.error("--workingDir --dataDir --fileName");
process.exit(1);
}
const workingDir = values.workingDir ?? '';
if (!fs.existsSync(workingDir)) mkdirSync(workingDir)
const dataDir = values.dataDir ?? '';
const tjaDir = path.join(dataDir, 'tja');
const files = fs.readdirSync(tjaDir);
const results: any[] = [];
for (const file of files) {
if (!file.endsWith('.tja')) continue;
const tja = fs.readFileSync(path.join(tjaDir, file), 'utf-8');
const songno = path.basename(file, '.tja');
try {
const parsed = parseTja(tja);
const courses = [
{ diff: 'oni', data: parsed?.oni },
{ diff: 'ura', data: parsed?.edit }
];
for (const course of courses) {
if (course.data) {
results.push({
songno,
difficulty: course.diff,
factors: factorize(course.data)
});
}
}
}
catch (err) {
console.error(`[Error] ${file}:`, err);
}
}
const outputPath = path.join(workingDir, values.fileName ?? 'factors.json');
fs.writeFileSync(outputPath, JSON.stringify(results, null, 2), 'utf-8');
console.log(`Successfully saved factors to ${outputPath}`);

106
script/train_factor.ts Normal file
View File

@@ -0,0 +1,106 @@
import Bun from 'bun';
import { spawn } from 'node:child_process';
import { parseArgs } from 'node:util';
import fs from 'fs';
import path from 'path';
import { factorize } from '../preprocess/factorize';
import { parseTja } from '../preprocess/parse'
const { values } = parseArgs({
args: Bun.argv,
options: {
workingDir: {
type: "string"
},
dataDir: {
type: "string"
},
script: {
type: "string"
},
trainSize: {
type: 'string'
},
validSize: {
type: 'string'
}
},
allowPositionals: true,
});
if (!values.dataDir || !values.workingDir || !values.script) {
console.error("Usage: bun run script/train_factor.ts --workingDir <dir> --dataDir <dir> --script <python_script> --trainSize <num> --validSize <num>");
process.exit(1);
}
// 1. factors.json 생성 (없을 경우)
generateFactors();
// 2. 파이썬 학습 스크립트 실행
console.log(`Starting training with factor-based script: ${values.script}`);
const child = spawn("python3", [
values.script,
"--workingDir", values.workingDir,
"--dataDir", values.dataDir,
"--trainSize", (Number(values.trainSize) || 1000).toString(),
"--validSize", (Number(values.validSize) || 200).toString(),
]);
child.stdout.pipe(process.stdout);
child.stderr.pipe(process.stderr);
child.on("close", (code) => {
console.log(`Training process exited with code ${code}`);
process.exit(code || 0);
});
// functions
function generateFactors() {
const workingDir = values.workingDir ?? '';
if (!fs.existsSync(workingDir)) fs.mkdirSync(workingDir, { recursive: true });
const factorsPath = path.join(workingDir, 'factors.json');
if (fs.existsSync(factorsPath)) {
console.log('factors.json already exists, skipping generation.');
return;
}
const dataDir = values.dataDir ?? '';
const tjaDir = path.join(dataDir, 'tja');
if (!fs.existsSync(tjaDir)) {
console.error(`TJA directory not found: ${tjaDir}`);
return;
}
const files = fs.readdirSync(tjaDir).filter(f => f.endsWith('.tja'));
console.log(`Generating factors from ${files.length} TJA files...`);
const results: any[] = [];
for (const file of files) {
try {
const tja = fs.readFileSync(path.join(tjaDir, file), 'utf-8');
const songno = path.basename(file, '.tja');
const parsed = parseTja(tja);
const courses = [
{ diff: 'oni', data: parsed?.oni },
{ diff: 'ura', data: parsed?.edit }
];
for (const course of courses) {
if (course.data) {
results.push({
songno,
difficulty: course.diff,
factors: factorize(course.data)
});
}
}
} catch (err) {
console.error(`Error processing ${file}:`, err);
}
}
fs.writeFileSync(factorsPath, JSON.stringify(results, null, 2), 'utf-8');
console.log(`factors.json generated at ${factorsPath}`);
}