Bulk Insert A Pandas DataFrame Using SQLAlchemy

Question

I have some rather large pandas DataFrames and I\'d like to use the new bulk SQL mappings to upload them to a Microsoft SQL Server via SQL Alchemy. The pandas.to_sql method,

Answer 1

This might have been answered by then, but I found the solution by collating different answers on this site and aligning with SQLAlchemy's doc.

1. The table needs to already exist in db1; with an index set up with auto_increment on.
2. The Class Current needs to align with the dataframe imported in the CSV and the table in the db1.

Hope this helps whoever comes here and wants to mix Panda and SQLAlchemy in a quick way.

from urllib import quote_plus as urlquote
import sqlalchemy
from sqlalchemy import create_engine
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy import Column, Integer, String, Numeric
from sqlalchemy.orm import sessionmaker
import pandas as pd


# Set up of the engine to connect to the database
# the urlquote is used for passing the password which might contain special characters such as "/"
engine = create_engine('mysql://root:%s@localhost/db1' % urlquote('weirdPassword*withsp€cialcharacters'), echo=False)
conn = engine.connect()
Base = declarative_base()

#Declaration of the class in order to write into the database. This structure is standard and should align with SQLAlchemy's doc.
class Current(Base):
    __tablename__ = 'tableName'

    id = Column(Integer, primary_key=True)
    Date = Column(String(500))
    Type = Column(String(500))
    Value = Column(Numeric())

    def __repr__(self):
        return "(id='%s', Date='%s', Type='%s', Value='%s')" % (self.id, self.Date, self.Type, self.Value)

# Set up of the table in db and the file to import
fileToRead = 'file.csv'
tableToWriteTo = 'tableName'

# Panda to create a lovely dataframe
df_to_be_written = pd.read_csv(fileToRead)
# The orient='records' is the key of this, it allows to align with the format mentioned in the doc to insert in bulks.
listToWrite = df_to_be_written.to_dict(orient='records')

metadata = sqlalchemy.schema.MetaData(bind=engine,reflect=True)
table = sqlalchemy.Table(tableToWriteTo, metadata, autoload=True)

# Open the session
Session = sessionmaker(bind=engine)
session = Session()

# Inser the dataframe into the database in one bulk
conn.execute(table.insert(), listToWrite)

# Commit the changes
session.commit()

# Close the session
session.close()