Why is my multithreaded parser not multithreading? - python

I have a script that parses xml files using the ElementTree Path Evaluator. It works fine as it is, but it takes a long for it to finish. So I tried to make a multithreaded implementation:
import fnmatch
import operator
import os
import lxml.etree
from nltk import FreqDist
from nltk.corpus import stopwords
from collections import defaultdict
from datetime import datetime
import threading
import Queue
STOPWORDS = stopwords.words('dutch')
STOPWORDS.extend(stopwords.words('english'))
DIR_NAME = 'A_DIRNAME'
PATTERN = '*.A_PATTERN'
def loadData(dir_name, pattern):
nohyphen_files = []
dir_names = []
dir_paths = []
for root, dirnames, filenames in os.walk(dir_name):
dir_names.append(dirnames)
dir_paths.append(root)
for filename in fnmatch.filter(filenames, pattern):
nohyphen_files.append(os.path.join(root, filename))
return nohyphen_files, dir_names, dir_paths
def freq(element_list, descending = True):
agglomerated = defaultdict(int)
for e in element_list:
agglomerated[e] += 1
return sorted(agglomerated.items(), key=operator.itemgetter(1), reverse=descending)
def lexDiv(amount_words):
return 1.0*len(set(amount_words))/len(amount_words)
def anotherFreq(list_types, list_words):
fd = FreqDist(list_types)
print 'top 10 most frequent types:'
for t, freq in fd.items()[:10]:
print t, freq
print '\ntop 10 most frequent words:'
agglomerated = defaultdict(int)
for w in list_words:
if not w.lower() in STOPWORDS:
agglomerated[w] += 1
sorted_dict = sorted(agglomerated.items(), key=operator.itemgetter(1),reverse=True)
print sorted_dict[:10]
def extractor(f):
print "check file: {}".format(f)
try:
# doc = lxml.etree.ElementTree(lxml.etree.XML(f))
doc = lxml.etree.ElementTree(file=f)
except lxml.etree.XMLSyntaxError, e:
print e
return
doc_evaluator = lxml.etree.XPathEvaluator(doc)
entities = doc_evaluator('//entity/*/externalRef/#reference')
places_dbpedia = doc_evaluator('//entity[contains(#type, "Schema:Place")]/*/externalRef/#reference')
non_people_dbpedia = set(doc_evaluator('//entity[not(contains(#type, "Schema:Person"))]'))
people = doc_evaluator('//entity[contains(#type, "Schema:Person")]/*/externalRef/#reference')
words = doc.xpath('text/wf[re:match(text(), "[A-Za-z-]")]/text()',\
namespaces={"re": "http://exslt.org/regular-expressions"})
unique_words = set(words)
other_tokens = doc.xpath('text/wf[re:match(text(), "[^A-Za-z-]")]/text()',\
namespaces={"re": "http://exslt.org/regular-expressions"})
amount_of_sentences = doc_evaluator('text/wf/#sent')[-1]
types = doc_evaluator('//term/#morphofeat')
longest_sentence = freq(doc.xpath('text/wf[re:match(text(), "[A-Za-z-]")]/#sent',\
namespaces={"re": "http://exslt.org/regular-expressions"}))[0]
top_people = freq([e.split('/')[-1] for e in people])[:10]
top_entities = freq([e.split('/')[-1] for e in entities])[:10]
top_places = freq([e.split('/')[-1] for e in places_dbpedia])[:10]
def worker():
while 1:
job_number = q.get()
extractor(job_number)
q.task_done() #this thread is complete, move on
if __name__ =='__main__':
startTime = datetime.now()
files, dirs, path = loadData(DIR_NAME, PATTERN)
startTime = datetime.now()
q = Queue.Queue()# job queue
for f in files:
q.put(f)
for i in range(20): #make 20 workerthreads ready
worker_thread = threading.Thread(target=worker)
worker_thread.daemon = True
worker_thread.start()
q.join()
print datetime.now() - startTime
This does something, but when timing it, it isn't faster than the normal version. I think it has something to do with opening and reading files making the threader not multithreaded. If I use a function that instead of parsing the xml file just sleeps for a couple of second and prints something, it does work and it is a lot faster. What do I have to account for to have a multithreaded XML parser?

Threading in Python doesn't work as it does in other languages. It relies on the Global Interpreter Lock that makes sure only one thread is active at one time (running bytecode to be exact).
What you want to do is use the multiprocess library, instead.
You can read more about the GIL and Threading here:
https://docs.python.org/2/glossary.html#term-global-interpreter-lock
https://docs.python.org/2/library/threading.html

Related

Python multicore CSV short program, advice/help needed

I'm a hobby coder started with AHK, then some java and now I try to learn Python. I have searched and found some tips but I have yet not been able to implement it into my own code.
Hopefully someone here can help me, it's a very short program.
I'm using .txt csv database with ";" as a separator.
DATABASE EXAMPLE:
Which color is normally a cat?;Black
How tall was the longest man on earth?;272 cm
Is the earth round?;Yes
The database now consists of 20.000 lines which makes the program "to slow", only using 25% CPU (1 core).
If I can make it use all 4 cores (100%) I guess it would perform the task alot faster. The task is basically to compare the CLIPBOARD with the database and if there is a match, it should give me an answer as a return. Perhaps also I can separate the database into 4 pieces?
The code right now looks like this! Not more then 65 lines and its doing its job (but to slow). Advice on how I can make this process into multi core needed.
import time
import pyperclip as pp
import pandas as pd
import pymsgbox as pmb
from fuzzywuzzy import fuzz
import numpy
ratio_threshold = 90
fall_back_time = 1
db_file_path = 'database.txt'
db_separator = ';'
db_encoding = 'latin-1'
def load_db():
while True:
try:
# Read and create database
db = pd.read_csv(db_file_path, sep=db_separator, encoding=db_encoding)
db = db.drop_duplicates()
return db
except:
print("Error in load_db(). Will sleep for %i seconds..." % fall_back_time)
time.sleep(fall_back_time)
def top_answers(db, question):
db['ratio'] = db['question'].apply(lambda q: fuzz.ratio(q, question))
db_sorted = db.sort_values(by='ratio', ascending=False)
db_sorted = db_sorted[db_sorted['ratio'] >= ratio_threshold]
return db_sorted
def write_txt(top):
result = top.apply(lambda row: "%s" % (row['answer']), axis=1).tolist()
result = '\n'.join(result)
fileHandle = open("svar.txt", "w")
fileHandle.write(result)
fileHandle.close()
pp.copy("")
def main():
try:
db = load_db()
last_db_reload = time.time()
while True:
# Get contents of clipboard
question = pp.paste()
# Rank answer
top = top_answers(db, question)
# If answer was found, show results
if len(top) > 0:
write_txt(top)
time.sleep(fall_back_time)
except:
print("Error in main(). Will sleep for %i seconds..." % fall_back_time)
time.sleep(fall_back_time)
if name == 'main':
main()'
If you could divide the db into four equally large you could process them in parallel like this:
import time
import pyperclip as pp
import pandas as pd
import pymsgbox as pmb
from fuzzywuzzy import fuzz
import numpy
import threading
ratio_threshold = 90
fall_back_time = 1
db_file_path = 'database.txt'
db_separator = ';'
db_encoding = 'latin-1'
def worker(thread_id, question):
thread_id = str(thread_id)
db = pd.read_csv(db_file_path + thread_id, sep=db_separator, encoding=db_encoding)
db = db.drop_duplicates()
db['ratio'] = db['question'].apply(lambda q: fuzz.ratio(q, question))
db_sorted = db.sort_values(by='ratio', ascending=False)
db_sorted = db_sorted[db_sorted['ratio'] >= ratio_threshold]
top = db_sorted
result = top.apply(lambda row: "%s" % (row['answer']), axis=1).tolist()
result = '\n'.join(result)
fileHandle = open("svar" + thread_id + ".txt", "w")
fileHandle.write(result)
fileHandle.close()
pp.copy("")
return
def main():
question = pp.paste()
for i in range(1, 4):
t = threading.Thread(target=worker, args=(i, question))
t.start()
t.join()
if name == 'main':
main()
The solution with multiprocessing:
import time
import pyperclip as pp
import pandas as pd
#import pymsgbox as pmb
from fuzzywuzzy import fuzz
import numpy as np
# pathos uses better pickle to tranfer more complicated objects
from pathos.multiprocessing import Pool
from functools import reduce
import sys
import os
from contextlib import closing
ratio_threshold = 70
fall_back_time = 1
db_file_path = 'database.txt'
db_separator = ';'
db_encoding = 'latin-1'
chunked_db = []
NUM_PROCESSES = os.cpu_count()
def load_db():
while True:
try:
# Read and create database
db = pd.read_csv(db_file_path, sep=db_separator, encoding=db_encoding)
db.columns = ['question', 'answer']
#db = db.drop_duplicates() # i drop it for experiment
break
except:
print("Error in load_db(). Will sleep for %i seconds..." % fall_back_time)
time.sleep(fall_back_time)
# split database into equal chunks:
# (if you have a lot of RAM, otherwise you
# need to compute ranges in db, something like
# chunk_size = len(db)//NUM_PROCESSES
# ranges[i] = (i*chunk_size, (i+1)*cjunk_size)
# and pass ranges in original db to processes
chunked_db = np.split(db, [NUM_PROCESSES], axis=0)
return chunked_db
def top_answers_multiprocessed(question, chunked_db):
# on unix, python uses 'fork' mode by default
# so the process has 'copy-on-change' access to all global variables
# i.e. if process will change something in db, it will be copied to it
# with a lot of overhead
# Unfortunately, I'fe heard that on Windows only 'spawn' mode with full
# copy of everything is used
# Process pipeline uses pickle, it's quite slow.
# so on small database you may not have benefit from multiprocessing
# If you are going to transfer big objects in or out, look
# in the direction of multiprocessing.Array
# this solution is not fully efficient,
# as pool is recreated each time
# You can create daemon processes which will monitor
# Queue for incoming questions, but it's harder to implement
def top_answers(idx):
# question is in the scope of parent function,
chunked_db[idx]['ratio'] = chunked_db[idx]['question'].apply(lambda q: fuzz.ratio(q, question))
db_sorted = chunked_db[idx].sort_values(by='ratio', ascending=False)
db_sorted = db_sorted[db_sorted['ratio'] >= ratio_threshold]
return db_sorted
with closing(Pool(processes=NUM_PROCESSES)) as pool:
# chunked_db is a list of databases
# they are in global scope, we send only index beacause
# all the data set is pickled
num_chunks = len(chunked_db)
# apply function top_answers across generator range(num_chunks)
res = pool.imap_unordered(top_answers, range(num_chunks))
res = list(res)
# now res is list of dataframes, let's join it
res_final = reduce(lambda left,right: pd.merge(left,right,on='ratio'), res)
return res_final
def write_txt(top):
result = top.apply(lambda row: "%s" % (row['answer']), axis=1).tolist()
result = '\n'.join(result)
fileHandle = open("svar.txt", "w")
fileHandle.write(result)
fileHandle.close()
pp.copy("")
def mainfunc():
global chunked_db
chunked_db = load_db()
last_db_reload = time.time()
print('db loaded')
last_clip = ""
while True:
# Get contents of clipboard
try:
new_clip = pp.paste()
except:
continue
if (new_clip != last_clip) and (len(new_clip)> 0):
print(new_clip)
last_clip = new_clip
question = new_clip.strip()
else:
continue
# Rank answer
top = top_answers_multiprocessed(question, chunked_db)
# If answer was found, show results
if len(top) > 0:
#write_txt(top)
print(top)
if __name__ == '__main__':
mainfunc()

Python script use while loop to keep updating job scripts and multiprocess the tasks in queue

I am trying to write a python script scanning a folder and collect updated SQL script, and then automatically pull data for the SQL script. In the code, a while loop is scanning new SQL file, and send to data pull function. I am having trouble to understand how to make a dynamic queue with while loop, but also have multiprocess to run the tasks in the queue.
The following code has a problem that the while loop iteration will work on a long job before it moves to next iteration and collects other jobs to fill the vacant processor.
Update:
Thanks to #pbacterio for catching the bug, and now the error message is gone. After changing the code, the python code can take all the job scripts during one iteration, and distribute the scripts to four processors. However, it will get hang by a long job to go to next iteration, scanning and submitting the newly added job scripts. Any idea how to reconstruct the code?
I finally figured out the solution see answer below. It turned out what I was looking for is
the_queue = Queue()
the_pool = Pool(4, worker_main,(the_queue,))
For those stumble on the similar idea, following is the whole architecture of this automation script converting a shared drive to a 'server for SQL pulling' or any other job queue 'server'.
a. The python script auto_data_pull.py as shown in the answer. You need to add your own job function.
b. A 'batch script' with following:
start C:\Anaconda2\python.exe C:\Users\bin\auto_data_pull.py
c. Add a task triggered by start computer, run the 'batch script'
That's all. It works.
Python Code:
from glob import glob
import os, time
import sys
import CSV
import re
import subprocess
import pandas as PD
import pypyodbc
from multiprocessing import Process, Queue, current_process, freeze_support
#
# Function run by worker processes
#
def worker(input, output):
for func, args in iter(input.get, 'STOP'):
result = compute(func, args)
output.put(result)
#
# Function used to compute result
#
def compute(func, args):
result = func(args)
return '%s says that %s%s = %s' % \
(current_process().name, func.__name__, args, result)
def query_sql(sql_file): #test func
#jsl file processing and SQL querying, data table will be saved to csv.
fo_name = os.path.splitext(sql_file)[0] + '.csv'
fo = open(fo_name, 'w')
print sql_file
fo.write("sql_file {0} is done\n".format(sql_file))
return "Query is done for \n".format(sql_file)
def check_files(path):
"""
arguments -- root path to monitor
returns -- dictionary of {file: timestamp, ...}
"""
sql_query_dirs = glob(path + "/*/IDABox/")
files_dict = {}
for sql_query_dir in sql_query_dirs:
for root, dirs, filenames in os.walk(sql_query_dir):
[files_dict.update({(root + filename): os.path.getmtime(root + filename)}) for
filename in filenames if filename.endswith('.jsl')]
return files_dict
##### working in single thread
def single_thread():
path = "Y:/"
before = check_files(path)
sql_queue = []
while True:
time.sleep(3)
after = check_files(path)
added = [f for f in after if not f in before]
deleted = [f for f in before if not f in after]
overlapped = list(set(list(after)) & set(list(before)))
updated = [f for f in overlapped if before[f] < after[f]]
before = after
sql_queue = added + updated
# print sql_queue
for sql_file in sql_queue:
try:
query_sql(sql_file)
except:
pass
##### not working in queue
def multiple_thread():
NUMBER_OF_PROCESSES = 4
path = "Y:/"
sql_queue = []
before = check_files(path) # get the current dictionary of sql_files
task_queue = Queue()
done_queue = Queue()
while True: #while loop to check the changes of the files
time.sleep(5)
after = check_files(path)
added = [f for f in after if not f in before]
deleted = [f for f in before if not f in after]
overlapped = list(set(list(after)) & set(list(before)))
updated = [f for f in overlapped if before[f] < after[f]]
before = after
sql_queue = added + updated
TASKS = [(query_sql, sql_file) for sql_file in sql_queue]
# Create queues
#submit task
for task in TASKS:
task_queue.put(task)
for i in range(NUMBER_OF_PROCESSES):
p = Process(target=worker, args=(task_queue, done_queue)).start()
# try:
# p = Process(target=worker, args=(task_queue))
# p.start()
# except:
# pass
# Get and print results
print 'Unordered results:'
for i in range(len(TASKS)):
print '\t', done_queue.get()
# Tell child processes to stop
for i in range(NUMBER_OF_PROCESSES):
task_queue.put('STOP')
# single_thread()
if __name__ == '__main__':
# freeze_support()
multiple_thread()
Reference:
monitor file changes with python script: http://timgolden.me.uk/python/win32_how_do_i/watch_directory_for_changes.html
Multiprocessing:
https://docs.python.org/2/library/multiprocessing.html
Where did you define sql_file in multiple_thread() in
multiprocessing.Process(target=query_sql, args=(sql_file)).start()
You have not defined sql_file in the method and moreover you have used that variable in a for loop. The variable's scope is only confined to the for loop.
Try replacing this:
result = func(*args)
by this:
result = func(args)
I have figured this out. Thank your for the response inspired the thought.
Now the script can run a while loop to monitor the folder for new updated/added SQL script, and then distribute the data pulling to multiple threads. The solution comes from the queue.get(), and queue.put(). I assume the queue object takes care of the communication by itself.
This is the final code --
from glob import glob
import os, time
import sys
import pypyodbc
from multiprocessing import Process, Queue, Event, Pool, current_process, freeze_support
def query_sql(sql_file): #test func
#jsl file processing and SQL querying, data table will be saved to csv.
fo_name = os.path.splitext(sql_file)[0] + '.csv'
fo = open(fo_name, 'w')
print sql_file
fo.write("sql_file {0} is done\n".format(sql_file))
return "Query is done for \n".format(sql_file)
def check_files(path):
"""
arguments -- root path to monitor
returns -- dictionary of {file: timestamp, ...}
"""
sql_query_dirs = glob(path + "/*/IDABox/")
files_dict = {}
try:
for sql_query_dir in sql_query_dirs:
for root, dirs, filenames in os.walk(sql_query_dir):
[files_dict.update({(root + filename): os.path.getmtime(root + filename)}) for
filename in filenames if filename.endswith('.jsl')]
except:
pass
return files_dict
def worker_main(queue):
print os.getpid(),"working"
while True:
item = queue.get(True)
query_sql(item)
def main():
the_queue = Queue()
the_pool = Pool(4, worker_main,(the_queue,))
path = "Y:/"
before = check_files(path) # get the current dictionary of sql_files
while True: #while loop to check the changes of the files
time.sleep(5)
sql_queue = []
after = check_files(path)
added = [f for f in after if not f in before]
deleted = [f for f in before if not f in after]
overlapped = list(set(list(after)) & set(list(before)))
updated = [f for f in overlapped if before[f] < after[f]]
before = after
sql_queue = added + updated
if sql_queue:
for jsl_file in sql_queue:
try:
the_queue.put(jsl_file)
except:
print "{0} failed with error {1}. \n".format(jsl_file, str(sys.exc_info()[0]))
pass
else:
pass
if __name__ == "__main__":
main()

how can we write the program by using multiprocessing module of Python?

# -*- coding: utf-8 -*-
from __future__ import print_function
import os, codecs, re, string, mysql
import mysql.connector
'''Reading files with txt extension'''
y_ = ""
for root, dirs, files in os.walk("/Users/Documents/source-document/part1"):
for file in files:
if file.endswith(".txt"):
x_ = codecs.open(os.path.join(root,file),"r", "utf-8-sig")
for lines in x_.readlines():
y_ = y_ + lines
#print(tokenized_docs)
'''Tokenizing sentences of the text files'''
from nltk.tokenize import sent_tokenize
raw_docs = sent_tokenize(y_)
tokenized_docs = [sent_tokenize(y_) for sent in raw_docs]
'''Removing stop words'''
stopword_removed_sentences = []
from nltk.corpus import stopwords
stopset = stopwords.words("English")
for i in tokenized_docs[0]:
tokenized_docs = ' '.join([word for word in i.split() if word not in stopset])
stopword_removed_sentences.append(tokenized_docs)
''' Removing punctuation marks'''
regex = re.compile('[%s]' % re.escape(string.punctuation)) #see documentation here: http://docs.python.org/2/library/string.html
nw = []
for review in stopword_removed_sentences:
new_review = ''
for token in review:
new_token = regex.sub(u'', token)
if not new_token == u'':
new_review += new_token
nw.append(new_review)
'''Lowercasing letters after removing puctuation marks.'''
lw = [] #lw stands for lowercase word.
for i in nw:
k = i.lower()
lw.append(k)
'''Removing number with a dummy symbol'''
nr = []
for j in lw:
string = j
regex = r'[^\[\]]+(?=\])'
# let "#" be the dummy symbol
output = re.sub(regex,'#',string)
nr.append(output)
nrfinal = []
for j in nr:
rem = 0
outr = ''
for i in j:
if ord(i)>= 48 and ord(i)<=57:
rem += 1
if rem == 1:
outr = outr+ '#'
else:
rem = 0
outr = outr+i
nrfinal.append(outr)
'''Inserting into database'''
def connect():
for j in nrfinal:
conn = mysql.connector.connect(user = 'root', password = '', unix_socket = "/tmp/mysql.sock", database = 'Thesis' )
cursor = conn.cursor()
cursor.execute("""INSERT INTO splitted_sentences(sentence_id, splitted_sentences) VALUES(%s, %s)""",(cursor.lastrowid,j))
conn.commit()
conn.close()
if __name__ == '__main__':
connect()
I am not getting any error with this code. It is doing well for the text files. The problem is only the execution time as I have a lot of text files (nearly 6Gb) for which the program is taking too much time. On inspection i found that it is CPU-bound. So to solve it, multiprocessing is needed. Please help me to write my code with multiprocessing module so that parallel processing can be done.
Thank you all.
there's an example in the python docs which demonstrates the use of multiprocessing:
from multiprocessing import Pool
def f(x):
return x*x
if __name__ == '__main__':
with Pool(5) as p:
print(p.map(f, [1, 2, 3]))
You can use this to adapt your code. Once you've obtained the text files, you use the map function to execute the rest in parallel. You'd have to define a function encapsulating the code you want to execute on multiple cores.
However, reading files in parallel may decrease the performance. Also, adding content to the database in asynchronously may not work. So you may want to perform these two tasks in the main thread, still

Data not printing correct

When running a data streaming sub-process against a multiprocessing, after printing a single element in the dictionary program freezes,
#!/usr/bin/python
import subprocess,time, timeit
from multiprocessing import Process, Queue
import re, os, pprint, math
from collections import defaultdict
Dict = {}
count = defaultdict(int)
queueVar = Queue()
def __ReadRX__(RX_info):
lines = iter(RX_info.stdout.readline, "")
try:
start = time.clock()
for line in lines:
if re.match(r"^\d+.*$",line):
splitline = line.split()
del splitline[1:4]
identifier = splitline[1]
count[identifier] += 1
end = time.clock()
timing = round((end - start) * 10000, 100)
dlc = splitline[2]
hexbits = splitline[3:]
Dict[identifier] = [dlc, hexbits, count[identifier],int(timing)]
start = end
for identifier,hexbits in Dict.items():
queueVar.put(Dict)
except KeyboardInterrupt:
pass
procRX = subprocess.Popen('receivetest -f=/dev/pcan32'.split(), stdout=subprocess.PIPE)
if __name__ == '__main__':
munchCan = Process(target=__ReadRX__, args=(procRX,))
munchCan.start()
#munchCan.join()
printDict = queueVar.get()
for i in range(len(printDict)):
print printDict
I know if if I print from __ReadRX__ it prints a constant stream however when trying to print from outside of the function I only get a single entry in the dictionary.
add the following at the top:
from time import sleep
then after the print statement add:
sleep(1)
this will make the script wait for 1 second. You can adjust that number as necessary.

Successive multiprocessing

I am filtering huge text files using multiprocessing.py. The code basically opens the text files, works on it, then closes it.
Thing is, I'd like to be able to launch it successively on multiple text files. Hence, I tried to add a loop, but for some reason it doesn't work (while the code works on each file). I believe this is an issue with:
if __name__ == '__main__':
However, I am looking for something else. I tried to create a Launcher and a LauncherCount files like this:
LauncherCount.py:
def setLauncherCount(n):
global LauncherCount
LauncherCount = n
and,
Launcher.py:
import os
import LauncherCount
LauncherCount.setLauncherCount(0)
os.system("OrientedFilterNoLoop.py")
LauncherCount.setLauncherCount(1)
os.system("OrientedFilterNoLoop.py")
...
I import LauncherCount.py, and use LauncherCount.LauncherCount as my loop index.
Of course, this doesn't work too as it edits the variable LauncherCount.LauncherCount locally, so it won't be edited in the imported version of LauncherCount.
Is there any way to edit globally a variable in an imported file? Or, is there any way to do this in any other way? What I need is running a code multiple times, in changing one value, and without using any loop apparently.
Thanks!
Edit: Here is my main code if necessary. Sorry for the bad style ...
import multiprocessing
import config
import time
import LauncherCount
class Filter:
""" Filtering methods """
def __init__(self):
print("launching methods")
# Return the list: [Latitude,Longitude] (elements are floating point numbers)
def LatLong(self,line):
comaCount = []
comaCount.append(line.find(','))
comaCount.append(line.find(',',comaCount[0] + 1))
comaCount.append(line.find(',',comaCount[1] + 1))
Lat = line[comaCount[0] + 1 : comaCount[1]]
Long = line[comaCount[1] + 1 : comaCount[2]]
try:
return [float(Lat) , float(Long)]
except ValueError:
return [0,0]
# Return a boolean:
# - True if the Lat/Long is within the Lat/Long rectangle defined by:
# tupleFilter = (minLat,maxLat,minLong,maxLong)
# - False if not
def LatLongFilter(self,LatLongList , tupleFilter) :
if tupleFilter[0] <= LatLongList[0] <= tupleFilter[1] and
tupleFilter[2] <= LatLongList[1] <= tupleFilter[3]:
return True
else:
return False
def writeLine(self,key,line):
filterDico[key][1].write(line)
def filteringProcess(dico):
myFilter = Filter()
while True:
try:
currentLine = readFile.readline()
except ValueError:
break
if len(currentLine) ==0: # Breaks at the end of the file
break
if len(currentLine) < 35: # Deletes wrong lines (too short)
continue
LatLongList = myFilter.LatLong(currentLine)
for key in dico:
if myFilter.LatLongFilter(LatLongList,dico[key][0]):
myFilter.writeLine(key,currentLine)
###########################################################################
# Main
###########################################################################
# Open read files:
readFile = open(config.readFileList[LauncherCount.LauncherCount][1], 'r')
# Generate writing files:
pathDico = {}
filterDico = config.filterDico
# Create outputs
for key in filterDico:
output_Name = config.readFileList[LauncherCount.LauncherCount][0][:-4]
+ '_' + key +'.log'
pathDico[output_Name] = config.writingFolder + output_Name
filterDico[key] = [filterDico[key],open(pathDico[output_Name],'w')]
p = []
CPUCount = multiprocessing.cpu_count()
CPURange = range(CPUCount)
startingTime = time.localtime()
if __name__ == '__main__':
### Create and start processes:
for i in CPURange:
p.append(multiprocessing.Process(target = filteringProcess ,
args = (filterDico,)))
p[i].start()
### Kill processes:
while True:
if [p[i].is_alive() for i in CPURange] == [False for i in CPURange]:
readFile.close()
for key in config.filterDico:
config.filterDico[key][1].close()
print(key,"is Done!")
endTime = time.localtime()
break
print("Process started at:",startingTime)
print("And ended at:",endTime)
To process groups of files in sequence while working on files within a group in parallel:
#!/usr/bin/env python
from multiprocessing import Pool
def work_on(args):
"""Process a single file."""
i, filename = args
print("working on %s" % (filename,))
return i
def files():
"""Generate input filenames to work on."""
#NOTE: you could read the file list from a file, get it using glob.glob, etc
yield "inputfile1"
yield "inputfile2"
def process_files(pool, filenames):
"""Process filenames using pool of processes.
Wait for results.
"""
for result in pool.imap_unordered(work_on, enumerate(filenames)):
#NOTE: in general the files won't be processed in the original order
print(result)
def main():
p = Pool()
# to do "successive" multiprocessing
for filenames in [files(), ['other', 'bunch', 'of', 'files']]:
process_files(p, filenames)
if __name__=="__main__":
main()
Each process_file() is called in sequence after the previous one has been complete i.e., the files from different calls to process_files() are not processed in parallel.

Categories

Resources