How to do an upsert with SqlAlchemy?

Question

I have a record that I want to exist in the database if it is not there, and if it is there already (primary key exists) I want the fields to be updated to the current state

Answer 1

The below works fine for me with redshift database and will also work for combined primary key constraint.

SOURCE : this

Just few modifications required for creating SQLAlchemy engine in the function def start_engine()

from sqlalchemy import Column, Integer, Date ,Metadata
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.dialects.postgresql import insert
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from sqlalchemy.dialects import postgresql

Base = declarative_base()

def start_engine():
    engine = create_engine(os.getenv('SQLALCHEMY_URI', 
    'postgresql://localhost:5432/upsert'))
     connect = engine.connect()
    meta = MetaData(bind=engine)
    meta.reflect(bind=engine)
    return engine


class DigitalSpend(Base):
    __tablename__ = 'digital_spend'
    report_date = Column(Date, nullable=False)
    day = Column(Date, nullable=False, primary_key=True)
    impressions = Column(Integer)
    conversions = Column(Integer)

    def __repr__(self):
        return str([getattr(self, c.name, None) for c in self.__table__.c])


def compile_query(query):
    compiler = query.compile if not hasattr(query, 'statement') else 
  query.statement.compile
    return compiler(dialect=postgresql.dialect())


def upsert(session, model, rows, as_of_date_col='report_date', no_update_cols=[]):
    table = model.__table__

    stmt = insert(table).values(rows)

    update_cols = [c.name for c in table.c
                   if c not in list(table.primary_key.columns)
                   and c.name not in no_update_cols]

    on_conflict_stmt = stmt.on_conflict_do_update(
        index_elements=table.primary_key.columns,
        set_={k: getattr(stmt.excluded, k) for k in update_cols},
        index_where=(getattr(model, as_of_date_col) < getattr(stmt.excluded, as_of_date_col))
        )

    print(compile_query(on_conflict_stmt))
    session.execute(on_conflict_stmt)


session = start_engine()
upsert(session, DigitalSpend, initial_rows, no_update_cols=['conversions'])