from multiprocessing import Pool
def function1(var1, var2):
print("function1 executing")
var3 = var1 + var2
return var3
if __name__ == "__main__":
pool = Pool()
pool.apply_async(function1, args=(7, 5))
pool.close()
pool.join()
When I run this I don't get anything in the console. It shows:
In [1]:
In [2]:
I tryed it with several different functions but I don't get anything printed in the console. Sorry for the nooby question :DD
Related
I have a function which is creating a data frame by doing multiprocessing on a df:-
Suppose if I am having 10 rows in my df so the function processor will process all 10 rows separately. what I want is to concatenate all the output of the function processor and make one data frame.
def processor(dff):
"""
reading data from a data frame and doing all sorts of data manipulation
for multiprocessing
"""
return df
def main(infile, mdebug):
global debug
debug = mdebug
try:
lines = sum(1 for line in open(infile))
except Exception as err:
print("Error {} opening file: {}").format(err, infile)
sys.exit(2000)
if debug >= 2:
print(infile)
try:
dff = pd.read_csv(infile)
except Exception as err:
print("Error {}, opening file: {}").format(err, infile)
sys.exit(2000)
df_split = np.array_split(dff, (lines+1))
cores = multiprocessing.cpu_count()
cores = 64
# pool = Pool(cores)
pool = Pool(lines-1)
for n, frame in enumerate(pool.imap(processor, df_split), start=1):
if frame is not None:
frame.to_csv('{}'.format(n))
pool.close()
pool.join()
if __name__ == "__main__":
args = parse_args()
"""
print "Debug is: {}".format(args.debug)
"""
if args.debug >= 1:
print("Running in debug mode: "), args.debug
main(infile=args.infile, mdebug=args.debug)
you can use either the data frame constructor or concat to solve your problem. the appropriate one to use depends on details of your code that you haven't included
here's a more complete example:
import numpy as np
import pandas as pd
# create dummy dataset
dff = pd.DataFrame(np.random.rand(101, 5), columns=list('abcde'))
# process data
with Pool() as pool:
result = pool.map(processor, np.array_split(dff, 7))
# put it all back together in one dataframe
result = np.concat(result)
I started programming in Python about 2 months ago and I've been struggling with this problem in the last 2 weeks.
I know there are many similar threads to this one but I can't really find a solution which suits my case.
I need to have the main process which is the one which interacts with Telegram and another process, buffer, which understands the complex object received from the main and updates it.
I'd like to do this in a simpler and smoother way.
At the moment objects are not being updated due to the use of multi-processing without the join() method.
I tried then to use multi-threading instead but it gives me compatibility problems with Pyrogram a framework which i am using to interact with Telegram.
I wrote again the "complexity" of my project in order to reproduce the same error I am getting and in order to get and give the best help possible from and for everyone.
a.py
class A():
def __init__(self, length = -1, height = -1):
self.length = length
self.height = height
b.py
from a import A
class B(A):
def __init__(self, length = -1, height = -1, width = -1):
super().__init__(length = -1, height = -1)
self.length = length
self.height = height
self.width = width
def setHeight(self, value):
self.height = value
c.py
class C():
def __init__(self, a, x = 0, y = 0):
self.a = a
self.x = x
self.y = y
def func1(self):
if self.x < 7:
self.x = 7
d.py
from c import C
class D(C):
def __init__(self, a, x = 0, y = 0, z = 0):
super().__init__(a, x = 0, y = 0)
self.a = a
self.x = x
self.y = y
self.z = z
def func2(self):
self.func1()
main.py
from b import B
from d import D
from multiprocessing import Process, Manager
from buffer import buffer
if __name__ == "__main__":
manager = Manager()
lizt = manager.list()
buffer = Process(target = buffer, args = (lizt, )) #passing the list as a parameter
buffer.start()
#can't invoke buffer.join() here because I need the below code to keep running while the buffer process takes a few minutes to end an instance passed in the list
#hence I can't wait the join() function to update the objects inside the buffer but i need objects updated in order to pop them out from the list
import datetime as dt
t = dt.datetime.now()
#library of kind of multithreading (pool of 4 processes), uses asyncio lib
#this while was put to reproduce the same error I am getting
while True:
if t + dt.timedelta(seconds = 10) < dt.datetime.now():
lizt.append(D(B(5, 5, 5)))
t = dt.datetime.now()
"""
#This is the code which looks like the one in my project
#main.py
from pyrogram import Client #library of kind of multithreading (pool of 4 processes), uses asyncio lib
from b import B
from d import D
from multiprocessing import Process, Manager
from buffer import buffer
if __name__ == "__main__":
api_id = 1234567
api_hash = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
app = Client("my_account", api_id, api_hash)
manager = Manager()
lizt = manager.list()
buffer = Process(target = buffer, args = (lizt, )) #passing the list as a parameter
buffer.start()
#can't invoke buffer.join() here because I need the below code to run at the same time as the buffer process
#hence I can't wait the join() function to update the objects inside the buffer
#app.on_message()
def my_handler(client, message):
lizt.append(complex_object_conatining_message)
"""
buffer.py
def buffer(buffer):
print("buffer was defined")
while True:
if len(buffer) > 0:
print(buffer[0].x) #prints 0
buffer[0].func2() #this changes the class attribute locally in the class instance but not in here
print(buffer[0].x) #prints 0, but I'd like it to be 7
print(buffer[0].a.height) #prints 5
buffer[0].a.setHeight(10) #and this has the same behaviour
print(buffer[0].a.height) #prints 5 but I'd like it to be 10
buffer.pop(0)
This is the whole code about the problem I am having.
Literally every suggestion is welcome, hopefully constructive, thank you in advance!
At last I had to change the way to solve this problem, which was using asyncio like the framework was doing as well.
This solution offers everything I was looking for:
-complex objects update
-avoiding the problems of multiprocessing (in particular with join())
It is also:
-lightweight: before I had 2 python processes 1) about 40K 2) about 75K
This actual process is about 30K (and it's also faster and cleaner)
Here's the solution, I hope it will be useful for someone else like it was for me:
The part of the classes is skipped because this solution updates complex objects absolutely fine
main.py
from pyrogram import Client
import asyncio
import time
def cancel_tasks():
#get all task in current loop
tasks = asyncio.Task.all_tasks()
for t in tasks:
t.cancel()
try:
buffer = []
firstWorker(buffer) #this one is the old buffer.py file and function
#the missing loop and loop method are explained in the next piece of code
except KeyboardInterrupt:
print("")
finally:
print("Closing Loop")
cancel_tasks()
firstWorker.py
import asyncio
def firstWorker(buffer):
print("First Worker Executed")
api_id = 1234567
api_hash = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
app = Client("my_account", api_id, api_hash)
#app.on_message()
async def my_handler(client, message):
print("Message Arrived")
buffer.append(complex_object_conatining_message)
await asyncio.sleep(1)
app.run(secondWorker(buffer)) #here is the trick: I changed the
#method run() of the Client class
#inside the Pyrogram framework
#since it was a loop itself.
#In this way I added another task
#to the existing loop in orther to
#let run both of them together.
my secondWorker.py
import asyncio
async def secondWorker(buffer):
while True:
if len(buffer) > 0:
print(buffer.pop(0))
await asyncio.sleep(1)
The resources to understand the asyncio used in this code can be found here:
Asyncio simple tutorial
Python Asyncio Official Documentation
This tutorial about how to fix classical Asyncio errors
I need to run some clustering algorithms in parallel in Jupyter notebook. The clustering function I want to parallel works when doing multithreading or when run individually. However, it returns
raise Py4JError("{0} does not exist in the JVM".format(name))
when I try multiprocessing. I don't have much experience with multiprocessing, what could I be doing wrong?
Code for clustering:
def clustering(ID, df):
pandas_df = df.select("row", "features", "type") \
.where(df.type == ID).toPandas()
print("process " + str(ID) + ": preparing data for clustering")
feature_series = pandas_df["features"].apply(lambda x: x.toArray())
objs = [pandas_df, pd.DataFrame(feature_series.tolist())]
t_df = pd.concat(objs, axis=1)
print("process " + str(ID) + ": initiating clustering")
c= #clustering algo here
print("process " + str(ID) + " DONE!")
return
Code for multiprocessing:
import multiprocessing as mp
k = 4
if __name__ == '__main__':
pl = []
for i in range(0,k):
print("sending process:", i)
process = mp.Process(target=clustering, args=(i, df))
jobs.append(process)
process.start()
for process in pl:
print("waiting for join from process")
process.join()
Error was caused by the subprocesses not being able to access the same memory(in which the pyspark dataframe resided).
Solved by partitioning the dataset first by putting the access to the pyspark dataframe in another function like so:
pandas_df = df.select("row", "features", "type") \
.where(df.type == ID).toPandas()
And then running the clustering on the separated Pandas dataframes.
I need to share numpy array between Processes, to store in it some results. Im not quite sure if what I have done so far is correct. This is my simplified code.
from multiprocessing import Process, Lock, Array
import numpy as np
def worker(shared,lock):
numpy_arr = np.frombuffer(shared.get_obj())
# do some work ...
with lock:
for i in range(10):
numpy_arr[0] += 1
numpy_arr += 1
return
if __name__ == '__main__':
jobs = []
lock = Lock()
shared_array = Array('d', 1000000)
for process in range(4):
p = Process(target=worker, args=(shared_array,lock))
jobs.append(p)
p.start()
for process in jobs:
process.join()
m = np.frombuffer(shared_array.get_obj())
np.save('data', m)
print (m[:5])
From this code i obtain expected results, but again, Im not sure if this is the correct way. And finally, what is the diffrence between multiprocessing.Array and multiprocessing.sharedctypes.Array ?
I'm using the tf.Print op in a Jupyter notebook. It works as required, but will only print the output to the console, without printing in the notebook. Is there any way to get around this?
An example would be the following (in a notebook):
import tensorflow as tf
a = tf.constant(1.0)
a = tf.Print(a, [a], 'hi')
sess = tf.Session()
a.eval(session=sess)
That code will print 'hi[1]' in the console, but nothing in the notebook.
Update Feb 3, 2017
I've wrapped this into memory_util package. Example usage
# install memory util
import urllib.request
response = urllib.request.urlopen("https://raw.githubusercontent.com/yaroslavvb/memory_util/master/memory_util.py")
open("memory_util.py", "wb").write(response.read())
import memory_util
sess = tf.Session()
a = tf.random_uniform((1000,))
b = tf.random_uniform((1000,))
c = a + b
with memory_util.capture_stderr() as stderr:
sess.run(c.op)
print(stderr.getvalue())
** Old stuff**
You could reuse FD redirector from IPython core. (idea from Mark Sandler)
import os
import sys
STDOUT = 1
STDERR = 2
class FDRedirector(object):
""" Class to redirect output (stdout or stderr) at the OS level using
file descriptors.
"""
def __init__(self, fd=STDOUT):
""" fd is the file descriptor of the outpout you want to capture.
It can be STDOUT or STERR.
"""
self.fd = fd
self.started = False
self.piper = None
self.pipew = None
def start(self):
""" Setup the redirection.
"""
if not self.started:
self.oldhandle = os.dup(self.fd)
self.piper, self.pipew = os.pipe()
os.dup2(self.pipew, self.fd)
os.close(self.pipew)
self.started = True
def flush(self):
""" Flush the captured output, similar to the flush method of any
stream.
"""
if self.fd == STDOUT:
sys.stdout.flush()
elif self.fd == STDERR:
sys.stderr.flush()
def stop(self):
""" Unset the redirection and return the captured output.
"""
if self.started:
self.flush()
os.dup2(self.oldhandle, self.fd)
os.close(self.oldhandle)
f = os.fdopen(self.piper, 'r')
output = f.read()
f.close()
self.started = False
return output
else:
return ''
def getvalue(self):
""" Return the output captured since the last getvalue, or the
start of the redirection.
"""
output = self.stop()
self.start()
return output
import tensorflow as tf
x = tf.constant([1,2,3])
a=tf.Print(x, [x])
redirect=FDRedirector(STDERR)
sess = tf.InteractiveSession()
redirect.start();
a.eval();
print "Result"
print redirect.stop()
I ran into the same problem and got around it by using a function like this in my notebooks:
def tf_print(tensor, transform=None):
# Insert a custom python operation into the graph that does nothing but print a tensors value
def print_tensor(x):
# x is typically a numpy array here so you could do anything you want with it,
# but adding a transformation of some kind usually makes the output more digestible
print(x if transform is None else transform(x))
return x
log_op = tf.py_func(print_tensor, [tensor], [tensor.dtype])[0]
with tf.control_dependencies([log_op]):
res = tf.identity(tensor)
# Return the given tensor
return res
# Now define a tensor and use the tf_print function much like the tf.identity function
tensor = tf_print(tf.random_normal([100, 100]), transform=lambda x: [np.min(x), np.max(x)])
# This will print the transformed version of the tensors actual value
# (which was summarized to just the min and max for brevity)
sess = tf.InteractiveSession()
sess.run([tensor])
sess.close()
FYI, using a logger instead of calling "print" in my custom function worked wonders for me as the stdout is often buffered by jupyter and not shown before "Loss is Nan" kind of errors -- which was the whole point in using that function in the first place in my case.
You can check the terminal where you launched the jupyter notebook to see the message.
import tensorflow as tf
tf.InteractiveSession()
a = tf.constant(1)
b = tf.constant(2)
opt = a + b
opt = tf.Print(opt, [opt], message="1 + 2 = ")
opt.eval()
In the terminal, I can see:
2018-01-02 23:38:07.691808: I tensorflow/core/kernels/logging_ops.cc:79] 1 + 2 = [3]
A simple way, tried it in regular python, but not jupyter yet.
os.dup2(sys.stdout.fileno(), 1)
os.dup2(sys.stdout.fileno(), 2)
Explanation is here: In python, how to capture the stdout from a c++ shared library to a variable
The issue that I faced was that one can't run a session inside a Tensorflow Graph, like in the training or in the evaluation.
That's why the options to use sess.run(opt) or opt.eval() were not a solution for me.
The best thing was to use tf.Print() and redirect the logging to an external file.
I did this using a temporal file, which I transferred to a regular file like this:
STDERR=2
import os
import sys
import tempfile
class captured:
def __init__(self, fd=STDERR):
self.fd = fd
self.prevfd = None
def __enter__(self):
t = tempfile.NamedTemporaryFile()
self.prevfd = os.dup(self.fd)
os.dup2(t.fileno(), self.fd)
return t
def __exit__(self, exc_type, exc_value, traceback):
os.dup2(self.prevfd, self.fd)
with captured(fd=STDERR) as tmp:
...
classifier.evaluate(input_fn=input_fn, steps=100)
with open('log.txt', 'w') as f:
print(open(tmp.name).read(), file=f)
And then in my evaluation I do:
a = tf.constant(1)
a = tf.Print(a, [a], message="a: ")