update rule unit

routes/predict.py

@@ -4,6 +4,7 @@ import shutil
 import pandas as pd
 import traceback
 import sys
+import numpy as np
 from pathlib import Path
 from fastapi import APIRouter, UploadFile, File, HTTPException, Depends, Body
 from fastapi.responses import FileResponse
@@ -319,7 +320,11 @@ async def predict(
 
         # 出力_集計用単位 mapping - use unit mapper result
         if "出力_集計用単位" in df_output_data.columns:
-            df_output_data["出力_集計用単位"] = df_output_data["出力_集計用単位"]
+            df_output_data["出力_集計用単位"] = np.where(
+                df_output_data["集計単位"] != "",
+                df_output_data["集計単位"],
+                df_output_data["出力_集計用単位"]
+            )
 
         # 出力_確率度 mapping - use the name similarity as main probability
         if "出力_名称類似度" in df_output_data.columns:
@@ -339,28 +344,6 @@ async def predict(
         # Debug: Print available columns to see what we have
         print(f"Available columns after processing: {list(df_output_data.columns)}")
 
-        # Final check and fallback for missing output columns
-        # if (
-        #     "出力_中科目" not in df_output_data.columns
-        #     or df_output_data["出力_中科目"].eq("").all()
-        # ):
-        #     df_output_data["出力_中科目"] = df_output_data.get("中科目", "")
-
-        # if (
-        #     "出力_項目名" not in df_output_data.columns
-        #     or df_output_data["出力_項目名"].eq("").all()
-        # ):
-        #     df_output_data["出力_項目名"] = df_output_data.get("名称", "")
-
-        # if (
-        #     "出力_単位" not in df_output_data.columns
-        #     or df_output_data["出力_単位"].eq("").all()
-        # ):
-        #     df_output_data["出力_単位"] = df_output_data.get("単位", "")
-
-        # if "出力_確率度" not in df_output_data.columns:
-        #     df_output_data["出力_確率度"] = 0  # Default confidence score
-
         # Define output columns in exact order as shown in Excel
         output_columns = [
             "ID",