Accessing and modifying a global array using python joblib

Question

I am trying to use joblib in python to speed up the processing of some data, but I am having problems trying to determine how to assign the output to the required format. I tried to create, possibly too simplified code that shows the problems I am facing:

from joblib import Parallel, delayed
import numpy as np

def main():
    print "Nested loop array assignment:"
    regular()
    print "Parallel nested loop assignment using a single process:"
    par2(1)
    print "Parallel nested loop assignment using multiple process:"
    par2(2)

def regular():
    # Define variables
    a = [0,1,2,3,4]
    b = [0,1,2,3,4]
    # Set array variable to global and define size and shape
    global ab
    ab = np.zeros((2,np.size(a),np.size(b)))

    # Iterate to populate array
    for i in range(0,np.size(a)):
        for j in range(0,np.size(b)):
            func(i,j,a,b)

    # Show array output
    print ab

def par2(process):
    # Define variables
    a2 = [0,1,2,3,4]
    b2 = [0,1,2,3,4]
    # Set array variable to global and define size and shape
    global ab2
    ab2 = np.zeros((2,np.size(a2),np.size(b2)))

    # Parallel process in order to populate array
    Parallel(n_jobs=process)(delayed(func2)(i,j,a2,b2) for i in xrange(0,np.size(a2)) for j in xrange(0,np.size(b2)))

    # Show array output
    print ab2

def func(i,j,a,b):
    # Populate array
    ab[0,i,j] = a[i]+b[j]
    ab[1,i,j] = a[i]*b[j]

def func2(i,j,a2,b2):
    # Populate array
    ab2[0,i,j] = a2[i]+b2[j]
    ab2[1,i,j] = a2[i]*b2[j]

# Run script
main()

This conclusion is as follows:

Nested loop array assignment:
[[[  0.   1.   2.   3.   4.]
  [  1.   2.   3.   4.   5.]
  [  2.   3.   4.   5.   6.]
  [  3.   4.   5.   6.   7.]
  [  4.   5.   6.   7.   8.]]

 [[  0.   0.   0.   0.   0.]
  [  0.   1.   2.   3.   4.]
  [  0.   2.   4.   6.   8.]
  [  0.   3.   6.   9.  12.]
  [  0.   4.   8.  12.  16.]]]
Parallel nested loop assignment using a single process:
[[[  0.   1.   2.   3.   4.]
  [  1.   2.   3.   4.   5.]
  [  2.   3.   4.   5.   6.]
  [  3.   4.   5.   6.   7.]
  [  4.   5.   6.   7.   8.]]

 [[  0.   0.   0.   0.   0.]
  [  0.   1.   2.   3.   4.]
  [  0.   2.   4.   6.   8.]
  [  0.   3.   6.   9.  12.]
  [  0.   4.   8.  12.  16.]]]
Parallel nested loop assignment using multiple process:
[[[ 0.  0.  0.  0.  0.]
  [ 0.  0.  0.  0.  0.]
  [ 0.  0.  0.  0.  0.]
  [ 0.  0.  0.  0.  0.]
  [ 0.  0.  0.  0.  0.]]

 [[ 0.  0.  0.  0.  0.]
  [ 0.  0.  0.  0.  0.]
  [ 0.  0.  0.  0.  0.]
  [ 0.  0.  0.  0.  0.]
  [ 0.  0.  0.  0.  0.]]]

From the Google search function and StackOverflow, it appears that when using joblib, the global array is not shared between each subprocess. I'm not sure if this is a joblib limitation or if there is a way around this?

script , , (4, x, x), x ( 100 ). , 2 x = 2400.

joblib ( ), , , . python 2.7.3 joblib 0.7.1.

Answer 1

, numpy memmap. memmap - joblib, joblib (0.9.3) . :

from joblib import Parallel, delayed
import numpy as np
import os
import tempfile
import shutil

def main():

    print "Nested loop array assignment:"
    regular()

    print "Parallel nested loop assignment using numpy memmap:"
    par3(4)

def regular():
    # Define variables
    a = [0,1,2,3,4]
    b = [0,1,2,3,4]

    # Set array variable to global and define size and shape
    global ab
    ab = np.zeros((2,np.size(a),np.size(b)))

    # Iterate to populate array
    for i in range(0,np.size(a)):
        for j in range(0,np.size(b)):
            func(i,j,a,b)

    # Show array output
    print ab

def par3(process):

    # Creat a temporary directory and define the array path
    path = tempfile.mkdtemp()
    ab3path = os.path.join(path,'ab3.mmap')

    # Define variables
    a3 = [0,1,2,3,4]
    b3 = [0,1,2,3,4]

    # Create the array using numpy memmap
    ab3 = np.memmap(ab3path, dtype=float, shape=(2,np.size(a3),np.size(b3)), mode='w+')

    # Parallel process in order to populate array
    Parallel(n_jobs=process)(delayed(func3)(i,a3,b3,ab3) for i in xrange(0,np.size(a3)))

    # Show array output
    print ab3

    # Delete the temporary directory and contents
    try:
        shutil.rmtree(path)
    except:
        print "Couldn't delete folder: "+str(path)

def func(i,j,a,b):
    # Populate array
    ab[0,i,j] = a[i]+b[j]
    ab[1,i,j] = a[i]*b[j]

def func3(i,a3,b3,ab3):
    # Populate array
    for j in range(0,np.size(b3)):
        ab3[0,i,j] = a3[i]+b3[j]
        ab3[1,i,j] = a3[i]*b3[j]

# Run script
main()

:

Nested loop array assignment:
[[[  0.   1.   2.   3.   4.]
  [  1.   2.   3.   4.   5.]
  [  2.   3.   4.   5.   6.]
  [  3.   4.   5.   6.   7.]
  [  4.   5.   6.   7.   8.]]

 [[  0.   0.   0.   0.   0.]
  [  0.   1.   2.   3.   4.]
  [  0.   2.   4.   6.   8.]
  [  0.   3.   6.   9.  12.]
  [  0.   4.   8.  12.  16.]]]
Parallel nested loop assignment using numpy memmap:
[[[  0.   1.   2.   3.   4.]
  [  1.   2.   3.   4.   5.]
  [  2.   3.   4.   5.   6.]
  [  3.   4.   5.   6.   7.]
  [  4.   5.   6.   7.   8.]]

 [[  0.   0.   0.   0.   0.]
  [  0.   1.   2.   3.   4.]
  [  0.   2.   4.   6.   8.]
  [  0.   3.   6.   9.  12.]
  [  0.   4.   8.  12.  16.]]]

, :

• , ( ) , , .
• , . a a3 np.arange(0,10000), b b3 - np.arange(0,1000) 12.4s "" 7.7s joblib .
• , j- (. func3). , 10 000 , 10 000 000
  .

Answer 2

joblib ( 0.13.2) DataFrames .

, DataFrames , DataFrame , .

data  = pd.DataFrame(...)
stats = pd.DataFrame(np.nan, index=np.arange(0, size/step), columns=cols, dtype=np.float64)

Parallel(n_jobs=8, prefer='threads')(
            delayed(_threadsafe_func)(data, stats, i, step, other_params)
            for i in range(0, size, step))

_threadsafe_func stats DataFrame :

index = i/step
print('[' + str(i) + '] Running job with index:', str(int(index)), '/', len(data)/step)
chunk = data[i:i + step]
stats.loc[index, 'mean'] = chunk.mean()    # 'mean' is an existing column already filled with np.nan