Vu Minh Chien commited on
Commit
3197697
·
1 Parent(s): e9a14f9

update rule unit

Browse files
Files changed (1) hide show
  1. routes/predict.py +6 -23
routes/predict.py CHANGED
@@ -4,6 +4,7 @@ import shutil
4
  import pandas as pd
5
  import traceback
6
  import sys
 
7
  from pathlib import Path
8
  from fastapi import APIRouter, UploadFile, File, HTTPException, Depends, Body
9
  from fastapi.responses import FileResponse
@@ -319,7 +320,11 @@ async def predict(
319
 
320
  # 出力_集計用単位 mapping - use unit mapper result
321
  if "出力_集計用単位" in df_output_data.columns:
322
- df_output_data["出力_集計用単位"] = df_output_data["出力_集計用単位"]
 
 
 
 
323
 
324
  # 出力_確率度 mapping - use the name similarity as main probability
325
  if "出力_名称類似度" in df_output_data.columns:
@@ -339,28 +344,6 @@ async def predict(
339
  # Debug: Print available columns to see what we have
340
  print(f"Available columns after processing: {list(df_output_data.columns)}")
341
 
342
- # Final check and fallback for missing output columns
343
- # if (
344
- # "出力_中科目" not in df_output_data.columns
345
- # or df_output_data["出力_中科目"].eq("").all()
346
- # ):
347
- # df_output_data["出力_中科目"] = df_output_data.get("中科目", "")
348
-
349
- # if (
350
- # "出力_項目名" not in df_output_data.columns
351
- # or df_output_data["出力_項目名"].eq("").all()
352
- # ):
353
- # df_output_data["出力_項目名"] = df_output_data.get("名称", "")
354
-
355
- # if (
356
- # "出力_単位" not in df_output_data.columns
357
- # or df_output_data["出力_単位"].eq("").all()
358
- # ):
359
- # df_output_data["出力_単位"] = df_output_data.get("単位", "")
360
-
361
- # if "出力_確率度" not in df_output_data.columns:
362
- # df_output_data["出力_確率度"] = 0 # Default confidence score
363
-
364
  # Define output columns in exact order as shown in Excel
365
  output_columns = [
366
  "ID",
 
4
  import pandas as pd
5
  import traceback
6
  import sys
7
+ import numpy as np
8
  from pathlib import Path
9
  from fastapi import APIRouter, UploadFile, File, HTTPException, Depends, Body
10
  from fastapi.responses import FileResponse
 
320
 
321
  # 出力_集計用単位 mapping - use unit mapper result
322
  if "出力_集計用単位" in df_output_data.columns:
323
+ df_output_data["出力_集計用単位"] = np.where(
324
+ df_output_data["集計単位"] != "",
325
+ df_output_data["集計単位"],
326
+ df_output_data["出力_集計用単位"]
327
+ )
328
 
329
  # 出力_確率度 mapping - use the name similarity as main probability
330
  if "出力_名称類似度" in df_output_data.columns:
 
344
  # Debug: Print available columns to see what we have
345
  print(f"Available columns after processing: {list(df_output_data.columns)}")
346
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
347
  # Define output columns in exact order as shown in Excel
348
  output_columns = [
349
  "ID",