PIbd-42_SSPR/db/csv_to_db.py

57 lines
1.9 KiB
Python

import pandas as pd
from sqlalchemy.ext.asyncio import create_async_engine, async_sessionmaker
from sqlalchemy import insert
from db.config import settings
from db.models.base import Base
from db.models.experiment_data_model import ExperimentData
from db.models.experiment_parameters_model import ExperimentParameters
from db.models.load_parameters_model import LoadParameters
from db.models.recycling_parameters_model import RecyclingParameters
import asyncio
engine = create_async_engine(url=settings.db_url_asyncpg, echo=True)
async_session = async_sessionmaker(engine)
async def create_all_tables():
async with engine.begin() as conn:
await conn.run_sync(Base.metadata.create_all)
async def drop_all_tables():
async with engine.begin() as conn:
await conn.run_sync(Base.metadata.drop_all)
async def load_data_to_db(file: str, model_class):
async with async_session() as session:
df = pd.read_csv(file).dropna()
# Преобразование данных из DataFrame в формат, подходящий для SQLAlchemy
data_records = df.to_dict(orient='records')
# Пакетная вставка всех записей
stmt = insert(model_class).values(data_records)
await session.execute(stmt)
await session.commit()
async def main():
# await drop_all_tables()
# await create_all_tables()
await load_data_to_db('./files/experiment_data.csv', ExperimentData)
# await load_data_to_db('./files/load_parameters.csv', LoadParameters)
# await load_data_to_db('./files/recycling_parameters.csv', RecyclingParameters)
# await load_data_to_db('./files/experiment_parameters.csv', ExperimentParameters)
if __name__ == '__main__':
asyncio.run(main())
# df = pd.read_csv('./files/experiment_data.csv')
# headers = df.columns.tolist()
# print(headers)
#
# for header in headers:
# column_type = df[header].dtype
# print(column_type)