Spaces:
Running
Running
File size: 3,738 Bytes
b77c0a2 840b33e 887cb19 b77c0a2 b6b3214 887cb19 b77c0a2 887cb19 b77c0a2 ced3dcd b77c0a2 887cb19 b77c0a2 b6b3214 b77c0a2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 |
import os
import time
import shutil
from pathlib import Path
from fastapi import APIRouter, UploadFile, File, HTTPException, Depends
from fastapi.responses import FileResponse
from auth import get_current_user
from services.sentence_transformer_service import SentenceTransformerService, sentence_transformer_service
from data_lib.input_name_data import InputNameData
from data_lib.base_name_data import COL_NAME_SENTENCE
from mapping_lib.name_mapper import NameMapper
from config import UPLOAD_DIR, OUTPUT_DIR
router = APIRouter()
@router.post("/predict")
async def predict(
current_user=Depends(get_current_user),
file: UploadFile = File(...),
sentence_service: SentenceTransformerService = Depends(lambda: sentence_transformer_service)
):
"""
Process an input CSV file and return standardized names (requires authentication)
"""
if not file.filename.endswith(".csv"):
raise HTTPException(status_code=400, detail="Only CSV files are supported")
# Save uploaded file
timestamp = int(time.time())
input_file_path = os.path.join(UPLOAD_DIR, f"input_{timestamp}_{current_user.username}.csv")
output_file_path = os.path.join(OUTPUT_DIR, f"output_{timestamp}_{current_user.username}.csv")
try:
with open(input_file_path, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
finally:
file.file.close()
try:
# Process input data
start_time = time.time()
try:
inputData = InputNameData(sentence_service.dic_standard_subject)
inputData.load_data_from_csv(input_file_path)
inputData.process_data(sentence_service.sentenceTransformerHelper)
except Exception as e:
print(f"Error processing input data: {e}")
raise HTTPException(status_code=500, detail=str(e))
# Map standard names
try:
nameMapper = NameMapper(
sentence_service.sentenceTransformerHelper,
sentence_service.standardNameMapData,
top_count=3
)
df_predicted = nameMapper.predict(inputData)
except Exception as e:
print(f"Error mapping standard names: {e}")
raise HTTPException(status_code=500, detail=str(e))
# Create output dataframe and save to CSV
# column_to_keep = ['ファイル名', 'シート名', '行', '科目', '中科目', '分類', '名称', '摘要', '備考']
column_to_keep = ['シート名', '行', '科目', '中科目', '分類', '名称', '摘要', '備考']
output_df = inputData.dataframe[column_to_keep].copy()
output_df.reset_index(drop=False, inplace=True)
output_df.loc[:, "出力_科目"] = df_predicted["標準科目"]
output_df.loc[:, "出力_項目名"] = df_predicted["標準項目名"]
output_df.loc[:, "出力_確率度"] = df_predicted["基準名称類似度"]
# Save with utf_8_sig encoding for Japanese Excel compatibility
output_df.to_csv(output_file_path, index=False, encoding="utf_8_sig")
end_time = time.time()
execution_time = end_time - start_time
print(f"Execution time: {execution_time} seconds")
return FileResponse(
path=output_file_path,
filename=f"output_{Path(file.filename).stem}.csv",
media_type="text/csv",
headers={
"Content-Disposition": f'attachment; filename="output_{Path(file.filename).stem}.csv"',
"Content-Type": "application/x-www-form-urlencoded",
},
)
except Exception as e:
print(f"Error processing file: {e}")
raise HTTPException(status_code=500, detail=str(e))
|