Create utils.py

lib/utils.py

@@ -0,0 +1,18 @@
+from datetime import datetime
+import pandas as pd
+import os
+
+def now_utc_str() -> str:
+    return datetime.utcnow().strftime("%Y%m%dT%H%M%SZ")
+
+def text_clean(s: str) -> str:
+    s = (s or "").strip()
+    # 軽めのクレンジング
+    s = s.replace("\u3000", " ").replace("\n", " ")
+    return " ".join(s.split())
+
+def load_sample_df() -> pd.DataFrame:
+    path = "data/sample_multilingual_reviews.csv"
+    if not os.path.exists(path):
+        return pd.DataFrame({"text": ["音質は良いがアプリが使いづらい", "Great battery life, app UX is confusing"]})
+    return pd.read_csv(path)