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()

Answer 2

My postgres specific solution below auto-creates the database table using your pandas dataframe, and performs a fast bulk insert using the postgres COPY my_table FROM ...

import io

import pandas as pd
from sqlalchemy import create_engine

def write_to_table(df, db_engine, schema, table_name, if_exists='fail'):
    string_data_io = io.StringIO()
    df.to_csv(string_data_io, sep='|', index=False)
    pd_sql_engine = pd.io.sql.pandasSQL_builder(db_engine, schema=schema)
    table = pd.io.sql.SQLTable(table_name, pd_sql_engine, frame=df,
                               index=False, if_exists=if_exists, schema=schema)
    table.create()
    string_data_io.seek(0)
    string_data_io.readline()  # remove header
    with db_engine.connect() as connection:
        with connection.connection.cursor() as cursor:
            copy_cmd = "COPY %s.%s FROM STDIN HEADER DELIMITER '|' CSV" % (schema, table_name)
            cursor.copy_expert(copy_cmd, string_data_io)
        connection.connection.commit()

Answer 3

for people like me who are trying to implement the aforementioned solutions:

Pandas 0.24.0 has now to_sql with chunksize and method='multi' option that inserts in bulk...

Answer 4

For anyone facing this problem and having the destination DB as Redshift, note that Redshift does not implement the full set of Postgres commands, and so some of the answers using either Postgres' COPY FROM or copy_from() will not work. psycopg2.ProgrammingError: syntax error at or near "stdin" error when trying to copy_from redshift

Solution for speeding up the INSERTs to Redshift is to use a file ingest or Odo.

Reference:
About Odo http://odo.pydata.org/en/latest/perf.html
Odo with Redshift
https://github.com/blaze/odo/blob/master/docs/source/aws.rst
Redshift COPY (from S3 file)
https://docs.aws.amazon.com/redshift/latest/dg/r_COPY.html

Answer 5

I ran into a similar issue with pd.to_sql taking hours to upload data. The below code bulk inserted the same data in a few seconds.

from sqlalchemy import create_engine
import psycopg2 as pg
#load python script that batch loads pandas df to sql
import cStringIO

address = 'postgresql://<username>:<pswd>@<host>:<port>/<database>'
engine = create_engine(address)
connection = engine.raw_connection()
cursor = connection.cursor()

#df is the dataframe containing an index and the columns "Event" and "Day"
#create Index column to use as primary key
df.reset_index(inplace=True)
df.rename(columns={'index':'Index'}, inplace =True)

#create the table but first drop if it already exists
command = '''DROP TABLE IF EXISTS localytics_app2;
CREATE TABLE localytics_app2
(
"Index" serial primary key,
"Event" text,
"Day" timestamp without time zone,
);'''
cursor.execute(command)
connection.commit()

#stream the data using 'to_csv' and StringIO(); then use sql's 'copy_from' function
output = cStringIO.StringIO()
#ignore the index
df.to_csv(output, sep='\t', header=False, index=False)
#jump to start of stream
output.seek(0)
contents = output.getvalue()
cur = connection.cursor()
#null values become ''
cur.copy_from(output, 'localytics_app2', null="")    
connection.commit()
cur.close()

Answer 6

This worked for me to connect to Oracle Database using cx_Oracle and SQLALchemy

import sqlalchemy
import cx_Oracle
from sqlalchemy import create_engine
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy import Column, String
from sqlalchemy.orm import sessionmaker
import pandas as pd

# credentials
username = "username"
password = "password"
connectStr = "connection:/string"
tableName = "tablename"

t0 = time.time()

# connection
dsn = cx_Oracle.makedsn('host','port',service_name='servicename')

Base = declarative_base()

class LANDMANMINERAL(Base):
    __tablename__ = 'tablename'

    DOCUMENTNUM = Column(String(500), primary_key=True)
    DOCUMENTTYPE = Column(String(500))
    FILENUM = Column(String(500))
    LEASEPAYOR = Column(String(500))
    LEASESTATUS = Column(String(500))
    PROSPECT = Column(String(500))
    SPLIT = Column(String(500))
    SPLITSTATUS = Column(String(500))

engine = create_engine('oracle+cx_oracle://%s:%s@%s' % (username, password, dsn))
conn = engine.connect()  

Base.metadata.bind = engine

# Creating the session

DBSession = sessionmaker(bind=engine)

session = DBSession()

# Bulk insertion
data = pd.read_csv('data.csv')
lists = data.to_dict(orient='records')


table = sqlalchemy.Table('landmanmineral', Base.metadata, autoreload=True)
conn.execute(table.insert(), lists)

session.commit()

session.close() 

print("time taken %8.8f seconds" % (time.time() - t0) )