■ DataFrame 클래스의 read_csv/to_csv 메소드를 사용해 계층적 데이터 CSV 파일을 변환하는 방법을 보여준다.
▶ main.py
|
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 |
import pandas as pd def transformCategoryData(sourceDataFrame): targetRowValueListList = [] currentRowValueDictionary = { "구분1" : "", "구분2" : "", "구분3" : "", "구분4" : "", "구분5" : "" } for _, rowSeries in sourceDataFrame.iterrows(): for columnName in ["구분1", "구분2", "구분3", "구분4", "구분5"]: if pd.notna(rowSeries[columnName]) and rowSeries[columnName] != "": currentRowValueDictionary[columnName] = rowSeries[columnName] for lowerColumnName in list(currentRowValueDictionary.keys())[list(currentRowValueDictionary.keys()).index(columnName) + 1:]: currentRowValueDictionary[lowerColumnName] = "" if pd.notna(rowSeries["비용코드"]) and rowSeries["비용코드"] != "": newRowValueDictionary = currentRowValueDictionary.copy() newRowValueDictionary["비용코드"] = rowSeries["비용코드"] targetRowValueListList.append(newRowValueDictionary) else: if any(currentRowValueDictionary.values()): newRowValueDictionary = currentRowValueDictionary.copy() newRowValueDictionary["비용코드"] = "" targetRowValueListList.append(newRowValueDictionary) targetDataFrame = pd.DataFrame(targetRowValueListList) return targetDataFrame def transformCategoryFile(sourceFilePath, targetFilePath): sourceDataFrame = pd.read_csv(sourceFilePath) targetDataFrame = transformCategoryData(sourceDataFrame) targetDataFrame.to_csv(targetFilePath, encoding = "utf-8-sig", index = False) # encoding 인자를 utf-8-sig로 설정한 이유는 엑셀에서 로드시 한글 깨짐 방지 transformCategoryFile("source.csv", "target.csv") |
▶ requirements.txt
|
1 2 3 4 5 6 7 8 |
numpy==2.2.0 pandas==2.2.3 python-dateutil==2.9.0.post0 pytz==2024.2 six==1.17.0 tzdata==2024.2 |
※ pip install pandas 명령을 실행한다.
