From 2a6003c4e56406937e85ace966bb3c8f7e9b3ca9 Mon Sep 17 00:00:00 2001
From: Fisherlen <fisherlen.yu@163.com>
Date: Sun, 15 Mar 2026 11:05:57 +0800
Subject: [PATCH] Add dataset download scripts

---
 download_dataset.py | 14 ++++++++++++++
 extract_zips.py     | 16 ++++++++++++++++
 2 files changed, 30 insertions(+)
 create mode 100644 download_dataset.py
 create mode 100644 extract_zips.py

diff --git a/download_dataset.py b/download_dataset.py
new file mode 100644
index 000000000..24b46c051
--- /dev/null
+++ b/download_dataset.py
@@ -0,0 +1,14 @@
+from datasets import load_dataset
+import pandas as pd
+import os
+
+# 确保dataset目录存在
+os.makedirs('dataset', exist_ok=True)
+
+# 加载ETTh1数据集
+dataset = load_dataset('thuml/Time-Series-Library', 'ETTh1')
+
+# 将训练集保存为CSV
+print("Saving ETTh1 dataset...")
+dataset['train'].to_csv('dataset/ETTh1.csv', index=False)
+print("Dataset saved successfully!")
\ No newline at end of file
diff --git a/extract_zips.py b/extract_zips.py
new file mode 100644
index 000000000..7cfaee131
--- /dev/null
+++ b/extract_zips.py
@@ -0,0 +1,16 @@
+import zipfile
+import os
+from pathlib import Path
+
+def extract_all_zips(root_dir):
+    for path in Path(root_dir).rglob('*.zip'):
+        print(f"Extracting {path}...")
+        try:
+            with zipfile.ZipFile(path, 'r') as zip_ref:
+                zip_ref.extractall(path.parent)
+            print(f"Successfully extracted {path}")
+        except Exception as e:
+            print(f"Error extracting {path}: {e}")
+
+if __name__ == "__main__":
+    extract_all_zips('dataset')
\ No newline at end of file