使用SQLAlchemy批量插入Pandas DataFrame

Question

我有一些相当大的pandas DataFrames,我想使用新的批量SQL映射通过SQL Alchemy将它们上传到Microsoft SQL Server.pandas.to_sql方法虽然不错,但速度很慢.

我在编写代码时遇到了麻烦......

我希望能够将这个函数传递给我正在调用的pandas DataFrame,我正在调用table的模式名称schema,以及我正在调用的表名name.理想情况下,该函数将1.)删除表,如果它已经存在.2.)创建一个新表3.)创建一个mapper和4.)使用mapper和pandas数据批量插入.我被困在第3部分.

这是我的(诚然粗糙的)代码.我正在努力解决如何让mapper函数与我的主键一起工作.我真的不需要主键,但映射器功能需要它.

感谢您的见解.

from sqlalchemy import create_engine Table, Column, MetaData
from sqlalchemy.orm import mapper, create_session
from sqlalchemy.ext.declarative import declarative_base
from pandas.io.sql import SQLTable, SQLDatabase

def bulk_upload(table, schema, name):
    e = create_engine('mssql+pyodbc://MYDB')
    s = create_session(bind=e)
    m = MetaData(bind=e,reflect=True,schema=schema)
    Base = declarative_base(bind=e,metadata=m)
    t = Table(name,m)
    m.remove(t)
    t.drop(checkfirst=True)
    sqld = SQLDatabase(e, schema=schema,meta=m)
    sqlt = SQLTable(name, sqld, table).table
    sqlt.metadata = m
    m.create_all(bind=e,tables=[sqlt])    
    class MyClass(Base):
        return
    mapper(MyClass, sqlt)    

    s.bulk_insert_mappings(MyClass, table.to_dict(orient='records'))
    return

Answer 1

我遇到了类似的问题,pd.to_sql需要花费数小时才能上传数据.以下代码批量在几秒钟内插入相同的数据.

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 2

这可能已经得到了回答,但我通过在此站点上整理不同的答案并与SQLAlchemy的doc对齐来找到解决方案.

1. 该表必须已经存在于db1中; 使用auto_increment on设置索引.
2. Class Current需要与CSV中导入的数据帧和db1中的表一致.

希望这有助于任何来到这里并想要快速混合Panda和SQLAlchemy的人.

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 3

基于@ansonw答案:

def to_sql(engine, df, table, if_exists='fail', sep='\t', encoding='utf8'):
    # Create Table
    df[:0].to_sql(table, engine, if_exists=if_exists)

    # Prepare data
    output = cStringIO.StringIO()
    df.to_csv(output, sep=sep, header=False, encoding=encoding)
    output.seek(0)

    # Insert data
    connection = engine.raw_connection()
    cursor = connection.cursor()
    cursor.copy_from(output, table, sep=sep, null='')
    connection.commit()
    cursor.close()

我在5秒而不是4分钟内插入200000行

Answer 4

Pandas 0.25.1 有一个参数可以进行多次插入，因此不再需要使用 SQLAlchemy 来解决这个问题。

method='multi'调用时设置pandas.DataFrame.to_sql。

在这个例子中，它将是 df.to_sql(table, schema=schema, con=e, index=False, if_exists='replace', method='multi')

答案来自此处的文档

值得注意的是，我只用 Redshift 对此进行了测试。请让我知道它在其他数据库上的运行情况，以便我可以更新此答案。

Answer 5

由于这是 I/O 繁重的工作负载，您还可以通过multiprocessing.dummy使用 python 线程模块。这对我来说加快了速度：

import math
from multiprocessing.dummy import Pool as ThreadPool

...

def insert_df(df, *args, **kwargs):
    nworkers = 4

    chunksize = math.floor(df.shape[0] / nworkers)
    chunks = [(chunksize * i, (chunksize * i) + chunksize) for i in range(nworkers)]
    chunks.append((chunksize * nworkers, df.shape[0]))
    pool = ThreadPool(nworkers)

    def worker(chunk):
        i, j = chunk
        df.iloc[i:j, :].to_sql(*args, **kwargs)

    pool.map(worker, chunks)
    pool.close()
    pool.join()


....

insert_df(df, "foo_bar", engine, if_exists='append')

Answer 6

下面我的 postgres 特定解决方案使用 pandas 数据框自动创建数据库表，并使用 postgres 执行快速批量插入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 7

对于像我这样尝试实施上述解决方案的人：

Pandas 0.24.0 现在有 to_sql ，带有 chunksize 和 method='multi' 选项，可以批量插入...

Answer 8

这是简单的方法

.

下载用于 SQL 数据库连接的驱动程序

对于 Linux 和 Mac 操作系统：

https://docs.microsoft.com/en-us/sql/connect/odbc/linux-mac/installing-the-microsoft-odbc-driver-for-sql-server?view=sql-server-2017

对于 Windows：

https://www.microsoft.com/en-us/download/details.aspx?id=56567

创建连接

from sqlalchemy import create_engine 
import urllib
server = '*****'
database = '********'
username = '**********'
password = '*********'

params = urllib.parse.quote_plus(
'DRIVER={ODBC Driver 17 for SQL Server};'+ 
'SERVER='+server+';DATABASE='+database+';UID='+username+';PWD='+ password) 

engine = create_engine("mssql+pyodbc:///?odbc_connect=%s" % params) 

#Checking Connection 
connected = pd.io.sql._is_sqlalchemy_connectable(engine)

print(connected)   #Output is True if connection established successfully

数据插入

df.to_sql('Table_Name', con=engine, if_exists='append', index=False)


"""
if_exists: {'fail', 'replace', 'append'}, default 'fail'
     fail: If table exists, do nothing.
     replace: If table exists, drop it, recreate it, and insert data.
     append: If table exists, insert data. Create if does not exist.
"""

如果有很多记录

# limit based on sp_prepexec parameter count
tsql_chunksize = 2097 // len(bd_pred_score_100.columns)
# cap at 1000 (limit for number of rows inserted by table-value constructor)
tsql_chunksize = 1000 if tsql_chunksize > 1000 else tsql_chunksize
print(tsql_chunksize)


df.to_sql('table_name', con = engine, if_exists = 'append', index= False, chunksize=tsql_chunksize)

PS：您可以根据需要更改参数。