lightgbm

script/compare.ts

@@ -1,25 +1,148 @@
 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"
-        },
-        tja: {
-            type: "string"
-        },
-        predictScript: {
-            type: "string"
-        },
+        workingDir: { type: "string" },
+        dataDir: { type: "string" },
+        script: { type: "string" },
     },
+    strict: true,
     allowPositionals: true,
 });
 
-if (!values.tja || !values.workingDir || !values.predictScript) {
-    console.error("--workingDir --dataDir --trainDir");
+if (!values.workingDir || !values.dataDir || !values.script) {
+    console.error("Usage: bun run script/compare.ts --workingDir <dir> --dataDir <dir> --script <python_script>");
     process.exit(1);
 }
 
-const songno = "temp";
+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 (temp.json 생성하여 기존 features.json 보존)
+console.log("Step 1: Running preprocessing to temp.json...");
+const preprocessResult = Bun.spawnSync([
+    "bun", "run", "script/preprocess.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 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...`);
+const comparisonResults: any[] = [];
+let processedCount = 0;
+
+for (const songno of uniqueSongnos) {
+    try {
+        const predictProcess = Bun.spawnSync([
+            "python3", predictScript,
+            "--workingDir", workingDir,
+            "--songno", songno as string,
+            "--feature", tempFilePath
+        ]);
+
+        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 ${songno}`);
+            processedCount++;
+            continue;
+        }
+
+        const predictions = JSON.parse(output.substring(jsonStart, jsonEnd));
+
+        predictions.forEach((pred: any) => {
+            const key = `${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.");
+
+// 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
+    },
+    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!`);
+console.log(`Total compared: ${comparisonResults.length}`);
+console.log(`Average Error: ${avgError.toFixed(4)}`);
+console.log(`Results saved to: ${comparePath}`);

script/preprocess.ts

@@ -13,9 +13,11 @@ const { values } = parseArgs({
         },
         dataDir: {
             type: "string"
+        },
+        fileName: {
+            type: "string"
         }
     },
-    strict: true,
     allowPositionals: true,
 })
 
@@ -60,5 +62,5 @@ for (const file of files) {
     }
 }
 
-const featurePath = path.join(workingDir, 'features.json');
+const featurePath = path.join(workingDir, values.fileName ?? 'features.json');
 fs.writeFileSync(featurePath, JSON.stringify(features, null, 2), 'utf-8');