xgboost

script/compare.ts

@@ -0,0 +1,25 @@
+import Bun from 'bun';
+import { parseArgs } from 'node:util';
+
+const { values } = parseArgs({
+    args: Bun.argv,
+    options: {
+        workingDir: {
+            type: "string"
+        },
+        tja: {
+            type: "string"
+        },
+        predictScript: {
+            type: "string"
+        },
+    },
+    allowPositionals: true,
+});
+
+if (!values.tja || !values.workingDir || !values.predictScript) {
+    console.error("--workingDir --dataDir --trainDir");
+    process.exit(1);
+}
+
+const songno = "temp";

script/preprocess.ts

@@ -2,14 +2,13 @@ import Bun from 'bun';
 import path from 'node:path';
 import { parseArgs } from 'node:util';
 import fs, { mkdirSync } from 'node:fs';
-import { Song } from 'tja-parser';
 import { featurize } from '../preprocess/featurize';
 import { parseTja } from '../preprocess/parse'
 
 const { values } = parseArgs({
     args: Bun.argv,
     options: {
-        outputDir: {
+        workingDir: {
             type: "string"
         },
         dataDir: {
@@ -20,13 +19,13 @@ const { values } = parseArgs({
     allowPositionals: true,
 })
 
-if (!values.dataDir || !values.outputDir) {
-    console.error("--outputDir --dataDir");
+if (!values.dataDir || !values.workingDir) {
+    console.error("--workingDir --dataDir");
     process.exit(1);
 }
 
-const outputDir = values.outputDir ?? '';
-if (!fs.existsSync(outputDir)) mkdirSync(outputDir)
+const workingDir = values.workingDir ?? '';
+if (!fs.existsSync(workingDir)) mkdirSync(workingDir)
 const dataDir = values.dataDir ?? '';
 
 const tjaDir = path.join(dataDir, 'tja');
@@ -61,5 +60,5 @@ for (const file of files) {
     }
 }
 
-const featurePath = path.join(outputDir, 'features.json');
+const featurePath = path.join(workingDir, 'features.json');
 fs.writeFileSync(featurePath, JSON.stringify(features, null, 2), 'utf-8');

script/train.ts

@@ -0,0 +1,91 @@
+import Bun from 'bun';
+import { execSync, spawn, spawnSync } from 'node:child_process';
+import { parseArgs } from 'node:util';
+import fs from 'fs';
+import path from 'path';
+import { featurize } from '../preprocess/featurize';
+import { parseTja } from '../preprocess/parse'
+
+const { values } = parseArgs({
+    args: Bun.argv,
+    options: {
+        workingDir: {
+            type: "string"
+        },
+        dataDir: {
+            type: "string"
+        },
+        trainScript: {
+            type: "string"
+        },
+        trainSize: {
+            type: 'string'
+        },
+        validSize: {
+            type: 'string'
+        }
+    },
+    allowPositionals: true,
+});
+
+if (!values.dataDir || !values.workingDir || !values.trainScript) {
+    console.error("--workingDir --dataDir --trainDir");
+    process.exit(1);
+}
+
+generateFeatures();
+const child = spawn("python3", [values.trainScript,
+    "--workingDir", values.workingDir,
+    "--dataDir", values.dataDir,
+    "--trainSize", (Number(values.trainSize) || 500).toString(),
+    "--validSize", (Number(values.validSize) || 100).toString(),
+]);
+child.stdout.pipe(process.stdout);
+child.stderr.pipe(process.stderr);
+child.on("close", () => {
+    process.exit()
+})
+
+// funcs
+function generateFeatures() {
+    const workingDir = values.workingDir ?? '';
+    if (!fs.existsSync(workingDir)) fs.mkdirSync(workingDir);
+    const featurePath = path.join(workingDir, 'features.json');
+    if (fs.existsSync(featurePath)) return;
+    const dataDir = values.dataDir ?? '';
+
+    const tjaDir = path.join(dataDir, 'tja');
+    const files = fs.readdirSync(tjaDir);
+
+    const features: ({ songno: string, difficulty: 'oni' | 'ura' } & {})[] = [];
+    for (const file of files) {
+        const tja = fs.readFileSync(path.join(tjaDir, file), 'utf-8');
+        const songno = path.basename(file, '.tja');
+        try {
+            const parsed = parseTja(tja);
+            const oni = parsed?.oni;
+            const edit = parsed?.edit;
+            if (oni) {
+                features.push({
+                    songno,
+                    difficulty: 'oni',
+                    ...featurize(oni)
+                })
+            }
+            if (edit) {
+                features.push({
+                    songno,
+                    difficulty: 'ura',
+                    ...featurize(edit)
+                })
+            }
+        }
+        catch (err) {
+            console.error(err);
+            console.error(file);
+        }
+    }
+
+    fs.writeFileSync(featurePath, JSON.stringify(features, null, 2), 'utf-8');
+    console.log('features.json generated')
+}