如何在p中执行多个SQL查询到pandas数据框

Question

嗨，所有的Python熊猫大师。我正在寻找一种方法来与Python并行运行一些SQL，返回几个Pandas数据帧。我有类似于下面的代码，对一个mssqlserver数据库连续运行4个SQL查询。其中两个查询的执行时间比IO（网络）要长得多，所以我认为并行化可以使代码运行快2倍。有没有一种简单的方法可以并行执行查询？在

理想情况下，我希望能够读取项目子目录中的所有*.sql文件，然后启动并行运行的查询，并以易于使用的格式（list？）返回四个数据帧用于进一步的操作（索引、连接、聚合）。在

提前谢谢你， 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()

Answer 1

在N个线程中使用N个连接。然后连接theads和proces结果。在

# 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。在

具有with语句的函数等价：

^{pr2}$

multiprocessing.Pool很容易分发繁重的任务，但它本身有更多的IO操作。在