5

大家好，Python Pandas 大师们。我正在寻找一种与 Python 并行运行一些 SQL 的方法，返回几个 Pandas 数据帧。我有类似于下面的代码，它针对 MS SQL 服务器数据库连续运行 4 个 SQL 查询。与 IO（网络）时间相比，其中两个查询的执行时间要长得多，因此我认为并行化会使代码运行速度快 2 倍。有没有一种简单的方法可以并行执行查询？

理想情况下，我希望能够读取项目子目录中的所有 *.sql 文件，然后触发查询以并行运行并以易于使用的格式（列表？）返回四个数据帧以供进一步使用操作（索引、连接、聚合）。

提前致谢， 兰德尔

# imports
import ceODBC
import numpy as np
import pandas as pd
import pandas.io.sql as psql
from ConfigParser import ConfigParser  
import os
import glob

# db connection string
cnxn = 'DRIVER={SQL Server Native Client 11.0}; SERVER=<servername>; DATABASE=<dname>; Trusted_Connection=Yes'

# directories (also should be moved to config)
dataDir = os.getcwd() + '\\data\\'
sqlDir = os.getcwd() + '\\sql\\'

# read sql from external .sql files. Possible to read all *.sql files in a sql dir into a list (or other structure...)?
with open(sqlDir + 'q1.sql', 'r') as f: q1sql = f.read()
with open(sqlDir + 'q2.sql', 'r') as f: q2sql = f.read()
with open(sqlDir + 'q3.sql', 'r') as f: q3sql = f.read()
with open(sqlDir + 'q4.sql', 'r') as f: q4sql = f.read()

# Connect to db, run SQL, assign result into dataframe, close connection. 
cnxn = ceODBC.connect(cnxn)
cursor = cnxn.cursor()

# execute the queries and close the connection. Parallelize?
df1 = psql.frame_query(q1sql, cnxn)
df2 = psql.frame_query(q2sql, cnxn) 
df3 = psql.frame_query(q3sql, cnxn)
df4 = psql.frame_query(q4sql, cnxn) 

# close connection
cnxn.close()
4

1 回答 1

3

在 N 个线程中使用 N 个连接。然后加入 theads 并处理结果。

# imports
import ceODBC
import numpy as np
import pandas as pd
import pandas.io.sql as psql
from ConfigParser import ConfigParser  
import os
import glob
import threading
enter code here


# db connection string
cnxn_string = 'DRIVER={SQL Server Native Client 11.0}; SERVER=<servername>; DATABASE=<dname>; Trusted_Connection=Yes'

# directories (also should be moved to config)
dataDir = os.getcwd() + '\\data\\'
sqlDir = os.getcwd() + '\\sql\\'

#variable to store results
responses={}
responses_lock=threading.Lock()

maxconnections = 8
pool_sema = BoundedSemaphore(value=maxconnections)


def task(fname):

    with open(fname, 'r') as f: sql = f.read()

    # Connect to db, run SQL, assign result into dataframe, close connection. 
    # to limit connections on DB used semaphore
    pool_sema.acquire()
    cnxn = ceODBC.connect(cnxn_string)
    cursor = cnxn.cursor()
    # execute the queries and close the connection. Parallelize?
    df = psql.frame_query(sql, cnxn)
    # close connection
    cnxn.close()
    pool_sema.release()

    # to ensure that only one thread can modify global variable
    responses_lock.acquire()
    responses[fname] = df
    responses_lock.release()


pool = []

#find sql files and spawn theads
for fname im glob.glob( os.path.join(sqlDir,'*sql')):
    #create new thread with task
    thread = threading.Thread(target=task,args=(fname,))
    thread.daemon = True
    # store thread in pool 
    pool.append(thread)
    #thread started
    thread.start()

#wait for all threads tasks done
for thread in pool:
    thread.join()

# results of each execution stored in responses dict

每个文件在单独的线程中执行。结果存储在一个变量中。

等效于带有with语句的函数：

def task(fname):

    with open(fname, 'r') as f: sql = f.read()

    # Connect to db, run SQL, assign result into dataframe, close connection. 
    # to limit connections on DB used semaphore
    with pool_sema:
        cnxn = ceODBC.connect(cnxn_string)
        cursor = cnxn.cursor()
        # execute the queries and close the connection. Parallelize?
        df = psql.frame_query(sql, cnxn)
        # close connection
        cnxn.close()


    # to ensure that only one thread can modify global variable
    with responses_lock:
        responses[fname] = df

multiprocessing.Pool易于分发繁重的任务，但它本身有更多的 IO 操作。

于 2013-07-28T22:51:39.987 回答