phase 1

scripts/prepare_dataset.ts

@@ -0,0 +1,26 @@
+import { readFile, writeFile, readdir } from "node:fs/promises";
+import { join, basename } from "node:path";
+
+async function prepare() {
+  const csvContent = await readFile("measure.csv", "utf-8");
+  const lines = csvContent.split("\n").slice(1);
+  const factorizeDir = "sample/output/factorize";
+  const files = (await readdir(factorizeDir)).filter(f => f.endsWith(".json"));
+  const dataset: any[] = [];
+
+  for (const file of files) {
+    const data = JSON.parse(await readFile(join(factorizeDir, file), "utf-8"));
+    const songno = basename(file, ".json");
+    
+    const match = lines.find(l => l.split(",")[1] == songno);
+    if (match) {
+      const constant = parseFloat(match.split(",")[0]);
+      for (const analysis of data.analysis) {
+        dataset.push({ x: Object.values(analysis.factors), y: constant });
+      }
+    }
+  }
+  await writeFile("sample/dataset/dataset.json", JSON.stringify(dataset));
+  console.log(`Dataset prepared with ${dataset.length} samples.`);
+}
+prepare().catch(console.error);