How to write DataFrame to postgres table

Faster option:

The following code will copy your Pandas DF to postgres DB much faster than df.to_sql method and you won't need any intermediate csv file to store the df.

Create an engine based on your DB specifications.

Create a table in your postgres DB that has equal number of columns as the Dataframe (df).

Data in DF will get inserted in your postgres table.

from sqlalchemy import create_engine
import psycopg2 
import io

If you want to replace the table, we can replace it with normal to_sql method using headers from our df and then load the entire big time consuming df into DB.

engine = create_engine(
    'postgresql+psycopg2://username:password@host:port/database')

# Drop old table and create new empty table
df.head(0).to_sql('table_name', engine, if_exists='replace',index=False)

conn = engine.raw_connection()
cur = conn.cursor()
output = io.StringIO()
df.to_csv(output, sep='\t', header=False, index=False)
output.seek(0)
contents = output.getvalue()
cur.copy_from(output, 'table_name', null="") # null values become ''
conn.commit()
cur.close()
conn.close()

Pandas 0.24.0+ solution

In Pandas 0.24.0 a new feature was introduced specifically designed for fast writes to Postgres. You can learn more about it here: https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#io-sql-method

import csv
from io import StringIO

from sqlalchemy import create_engine

def psql_insert_copy(table, conn, keys, data_iter):
    # gets a DBAPI connection that can provide a cursor
    dbapi_conn = conn.connection
    with dbapi_conn.cursor() as cur:
        s_buf = StringIO()
        writer = csv.writer(s_buf)
        writer.writerows(data_iter)
        s_buf.seek(0)

        columns = ', '.join('"{}"'.format(k) for k in keys)
        if table.schema:
            table_name = '{}.{}'.format(table.schema, table.name)
        else:
            table_name = table.name

        sql = 'COPY {} ({}) FROM STDIN WITH CSV'.format(
            table_name, columns)
        cur.copy_expert(sql=sql, file=s_buf)

engine = create_engine('postgresql://myusername:mypassword@myhost:5432/mydatabase')
df.to_sql('table_name', engine, method=psql_insert_copy)

This is how I did it.

It may be faster because it is using execute_batch:

# df is the dataframe
if len(df) > 0:
    df_columns = list(df)
    # create (col1,col2,...)
    columns = ",".join(df_columns)

    # create VALUES('%s', '%s",...) one '%s' per column
    values = "VALUES({})".format(",".join(["%s" for _ in df_columns])) 

    #create INSERT INTO table (columns) VALUES('%s',...)
    insert_stmt = "INSERT INTO {} ({}) {}".format(table,columns,values)

    cur = conn.cursor()
    psycopg2.extras.execute_batch(cur, insert_stmt, df.values)
    conn.commit()
    cur.close()

Faster way to write a df to a table in a custom schema with/without index:

"""
Faster way to write df to table.
Slower way is to use df.to_sql()
"""

from io import StringIO

from pandas import DataFrame
from sqlalchemy.engine.base import Engine


class WriteDfToTableWithIndexMixin:
    @classmethod
    def write_df_to_table_with_index(
            cls,
            df: DataFrame,
            table_name: str,
            schema_name: str,
            engine: Engine
    ):
        """
        Truncate existing table and load df into table.
        Keep each column as string to avoid datatype conflicts.
        """
        df.head(0).to_sql(table_name, engine, if_exists='replace',
                          schema=schema_name, index=True, index_label='id')

        conn = engine.raw_connection()
        cur = conn.cursor()
        output = StringIO()
        df.to_csv(output, sep='\t', header=False,
                  index=True, index_label='id')
        output.seek(0)
        contents = output.getvalue()
        cur.copy_expert(f"COPY {schema_name}.{table_name} FROM STDIN", output)
        conn.commit()


class WriteDfToTableWithoutIndexMixin:
    @classmethod
    def write_df_to_table_without_index(
            cls,
            df: DataFrame,
            table_name: str,
            schema_name: str,
            engine: Engine
    ):
        """
        Truncate existing table and load df into table.
        Keep each column as string to avoid datatype conflicts.
        """
        df.head(0).to_sql(table_name, engine, if_exists='replace',
                          schema=schema_name, index=False)

        conn = engine.raw_connection()
        cur = conn.cursor()
        output = StringIO()
        df.to_csv(output, sep='\t', header=False, index=False)
        output.seek(0)
        contents = output.getvalue()
        cur.copy_expert(f"COPY {schema_name}.{table_name} FROM STDIN", output)
        conn.commit()

If you have JSON values in a column in your df then above method will still load all data correctly but the json column will have some weird format. So converting that json column to ::json may generate error. You have to use to_sql() . Add method=multi to speed things up and add chunksize to prevent your machine from freezing:

df.to_sql(table_name, engine, if_exists='replace', schema=schema_name, index=False, method='multi', chunksize=1000)

using psycopg2 you can use native sql commands to write data into a postgres table.

import psycopg2
import pandas as pd

conn = psycopg2.connect("dbname='{db}' user='{user}' host='{host}' port='{port}' password='{passwd}'".format(
            user=pg_user,
            passwd=pg_pass,
            host=pg_host,
            port=pg_port,
            db=pg_db))
cur = conn.cursor()    
def insertIntoTable(df, table):
        """
        Using cursor.executemany() to insert the dataframe
        """
        # Create a list of tupples from the dataframe values
        tuples = list(set([tuple(x) for x in df.to_numpy()]))
    
        # Comma-separated dataframe columns
        cols = ','.join(list(df.columns))
        # SQL query to execute
        query = "INSERT INTO %s(%s) VALUES(%%s,%%s,%%s,%%s)" % (
            table, cols)
    
        try:
            cur.executemany(query, tuples)
            conn.commit()

        except (Exception, psycopg2.DatabaseError) as error:
            print("Error: %s" % error)
            conn.rollback()
            return 1

For Python 2.7 and Pandas 0.24.2 and using Psycopg2

Psycopg2 Connection Module

def dbConnect (db_parm, username_parm, host_parm, pw_parm):
    # Parse in connection information
    credentials = {'host': host_parm, 'database': db_parm, 'user': username_parm, 'password': pw_parm}
    conn = psycopg2.connect(**credentials)
    conn.autocommit = True  # auto-commit each entry to the database
    conn.cursor_factory = RealDictCursor
    cur = conn.cursor()
    print ("Connected Successfully to DB: " + str(db_parm) + "@" + str(host_parm))
    return conn, cur

Connect to the database

conn, cur = dbConnect(databaseName, dbUser, dbHost, dbPwd)

Assuming dataframe to be present already as df

output = io.BytesIO() # For Python3 use StringIO
df.to_csv(output, sep='\t', header=True, index=False)
output.seek(0) # Required for rewinding the String object
copy_query = "COPY mem_info FROM STDOUT csv DELIMITER '\t' NULL ''  ESCAPE '\\' HEADER "  # Replace your table name in place of mem_info
cur.copy_expert(copy_query, output)
conn.commit()

Create engine (where dialect='postgres' or 'mysql', etc..):

from sqlalchemy import create_engine
engine = create_engine(f'{dialect}://{user_name}@{host}:{port}/{db_name}')
Session = sessionmaker(bind=engine) 

with Session() as session:
    df = pd.read_csv(path + f'/{file}') 
    df.to_sql('table_name', con=engine, if_exists='append',index=False)