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 ?
Related
In my code, I am trying to extract data from csv file to use in the function, but it doesnt output anything, and gives no error. My code works because I tried it with just numpy array as inputs. not sure why it doesnt work with panda.
import numpy as np
import pandas as pd
import os
# change the current directory to the directory where the running script file is
os.chdir(os.path.dirname(os.path.abspath(__file__)))
# finding best fit line for y=mx+b by iteration
def gradient_descent(x,y):
m_iter = b_iter = 1 #starting point
iteration = 10000
n = len(x)
learning_rate = 0.05
last_mse = 10000
#take baby steps to reach global minima
for i in range(iteration):
y_predicted = m_iter*x + b_iter
#mse = 1/n*sum([value**2 for value in (y-y_predicted)]) # cost function to minimize
mse = 1/n*sum((y-y_predicted)**2) # cost function to minimize
if (last_mse - mse)/mse < 0.001:
break
# recall MSE formula is 1/n*sum((yi-y_predicted)^2), where y_predicted = m*x+b
# using partial deriv of MSE formula, d/dm and d/db
dm = -(2/n)*sum(x*(y-y_predicted))
db = -(2/n)*sum((y-y_predicted))
# use current predicted value to get the next value for prediction
# by using learning rate
m_iter = m_iter - learning_rate*dm
b_iter = b_iter - learning_rate*db
print('m is {}, b is {}, cost is {}, iteration {}'.format(m_iter,b_iter,mse,i))
last_mse = mse
#x = np.array([1,2,3,4,5])
#y = np.array([5,7,8,10,13])
#gradient_descent(x,y)
df = pd.read_csv('Linear_Data.csv')
x = df['Area']
y = df['Price']
gradient_descent(x,y)
My code works because I tried it with just numpy array as inputs. not sure why it doesnt work with panda.
Well no, your code also works with pandas dataframes:
df = pd.DataFrame({'Area': [1,2,3,4,5], 'Price': [5,7,8,10,13]})
x = df['Area']
y = df['Price']
gradient_descent(x,y)
Above will give you the same output as with numpy arrays.
Try to check what's in Linear_Data.csv and/or add some print statements in the gradient_descent function just to check your assumptions. I would suggest to first of all add a print statement before the condition with the break statement:
print(last_mse, mse)
if (last_mse - mse)/mse < 0.001:
break
i'm trying to solve tsp with OR-tools for a problem of something like 80,000 nodes, the problem is, I need a huge distance matrix that takes to much memory ,so its infeasible and i don't get a solution.
so:
is there an option to work with partial distance matrix in or-tools?
if not is there a way to improve my code?
is there another external solver that can work for this task in python?
import math
from collections import namedtuple
import random
import time
from collections import namedtuple
from sklearn.metrics.pairwise import euclidean_distances
import numpy as np
import numba
from scipy.spatial import distance_matrix
from sklearn.metrics.pairwise import euclidean_distances
from math import sqrt
Point = namedtuple("Point", ['x', 'y'])
def solve_it(input_data):
# Modify this code to run your optimization algorithm
global POINTS
# parse the input
lines = input_data.split('\n')
nodeCount = int(lines[0])
points = []
for i in range(1, nodeCount+1):
line = lines[i]
parts = line.split()
points.append(Point(float(parts[0]), float(parts[1])))
#2.routing with or tools
def dist_matrix(nodeCount,points):
data=[]
for k in range(len(points)):
data.append([int(points[k].x),int(points[k].y)])
D=euclidean_distances(data, data)
return D
def create_data_model(D):
"""Stores the data for the problem."""
data = {}
data['distance_matrix'] = D # yapf: disable
data['num_vehicles'] = 1
data['depot'] = 0
return data
def print_solution(manager, routing, solution):
index = routing.Start(0)
plan_output = []#Route for vehicle 0:\n'
route_distance = 0
while not routing.IsEnd(index):
plan_output.append(manager.IndexToNode(index))
index = solution.Value(routing.NextVar(index))
return plan_output
def or_main(nodeCount,points):
from ortools.constraint_solver import routing_enums_pb2
from ortools.constraint_solver import pywrapcp
"""Entry point of the program."""
# Instantiate the data problem.
global sol
D=dist_matrix(nodeCount,points)
data = create_data_model(D)
# Create the routing index manager.
manager = pywrapcp.RoutingIndexManager(len(data['distance_matrix']),
data['num_vehicles'], data['depot'])
# Create Routing Model.
routing = pywrapcp.RoutingModel(manager)
def distance_callback(from_index, to_index):
"""Returns the distance between the two nodes."""
# Convert from routing variable Index to distance matrix NodeIndex.
from_node = manager.IndexToNode(from_index)
to_node = manager.IndexToNode(to_index)
return data['distance_matrix'][from_node][to_node]
transit_callback_index = routing.RegisterTransitCallback(distance_callback)
# Define cost of each arc.
routing.SetArcCostEvaluatorOfAllVehicles(transit_callback_index)
# Setting first solution heuristic.
search_parameters = pywrapcp.DefaultRoutingSearchParameters()
search_parameters.local_search_metaheuristic = (
routing_enums_pb2.LocalSearchMetaheuristic.GUIDED_LOCAL_SEARCH)
k = 100
if nodeCount <= 100:
k = 30
elif 100 <= nodeCount <= 1000:
k = 300
elif nodeCount > 1000:
k = 17000
search_parameters.time_limit.seconds =k
search_parameters.log_search = True
# Solve the problem.
solution = routing.SolveWithParameters(search_parameters)
# #print solution on console.
if solution:
sol=print_solution(manager, routing, solution)
return sol
######################################################################
solution=or_main(nodeCount,points)
# calculate the length of the tour
obj = length(points[solution[-1]], points[solution[0]])
for index in range(0, nodeCount-1):
obj += length(points[solution[index]], points[solution[index+1]])
# prepare the solution in the specified output format
output_data = '%.2f' % obj + ' ' + str(0) + '\n'
output_data += ' '.join(map(str, solution))
return output_data
if __name__ == '__main__':
import sys
if len(sys.argv) > 1:
file_location = sys.argv[1].strip()
with open(file_location, 'r') as input_data_file:
input_data = input_data_file.read()
#print(solve_it(input_data))
else:
print('This test requires an input file. Please select one from the data directory. (i.e. python solver.py ./data/tsp_51_1)')
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'm trying to run an Apache Beam job based on Tensorflow Transform on Dataflow but its killed. Someone has experienced that behaviour? This is a simple example with DirectRunner, that runs ok on my local but fails on Dataflow (I change the runner properly):
import os
import csv
import datetime
import numpy as np
import tensorflow as tf
import tensorflow_transform as tft
from apache_beam.io import textio
from apache_beam.io import tfrecordio
from tensorflow_transform.beam import impl as beam_impl
from tensorflow_transform.beam import tft_beam_io
from tensorflow_transform.tf_metadata import dataset_metadata
from tensorflow_transform.tf_metadata import dataset_schema
import apache_beam as beam
NUMERIC_FEATURE_KEYS = ['feature_'+str(i) for i in range(2000)]
def _create_raw_metadata():
column_schemas = {}
for key in NUMERIC_FEATURE_KEYS:
column_schemas[key] = dataset_schema.ColumnSchema(tf.float32, [], dataset_schema.FixedColumnRepresentation())
raw_data_metadata = dataset_metadata.DatasetMetadata(dataset_schema.Schema(column_schemas))
return raw_data_metadata
def preprocessing_fn(inputs):
outputs={}
for key in NUMERIC_FEATURE_KEYS:
outputs[key] = tft.scale_to_0_1(inputs[key])
return outputs
def main():
output_dir = '/tmp/tmp-folder-{}'.format(datetime.datetime.now().strftime('%Y%m%d%H%M%S'))
RUNNER = 'DirectRunner'
with beam.Pipeline(RUNNER) as p:
with beam_impl.Context(temp_dir=output_dir):
raw_data_metadata = _create_raw_metadata()
_ = (raw_data_metadata | 'WriteInputMetadata' >> tft_beam_io.WriteMetadata(os.path.join(output_dir, 'rawdata_metadata'), pipeline=p))
m = numpy_dataset = np.random.rand(100,2000)*100
raw_data = (p
| 'CreateTestDataset' >> beam.Create([dict(zip(NUMERIC_FEATURE_KEYS, m[i,:])) for i in range(m.shape[0])]))
raw_dataset = (raw_data, raw_data_metadata)
transform_fn = (raw_dataset | 'Analyze' >> beam_impl.AnalyzeDataset(preprocessing_fn))
_ = (transform_fn | 'WriteTransformFn' >> tft_beam_io.WriteTransformFn(output_dir))
(transformed_data, transformed_metadata) = ((raw_dataset, transform_fn) | 'Transform' >> beam_impl.TransformDataset())
transformed_data_coder = tft.coders.ExampleProtoCoder(transformed_metadata.schema)
_ = transformed_data | 'WriteTrainData' >> tfrecordio.WriteToTFRecord(os.path.join(output_dir, 'train'), file_name_suffix='.gz', coder=transformed_data_coder)
if __name__ == '__main__':
main()
Also, my production code (not shown) fail with the message: The job graph is too large. Please try again with a smaller job graph, or split your job into two or more smaller jobs.
Any hint?
The restriction on the pipeline description size is documented here:
https://cloud.google.com/dataflow/quotas#limits
There is a way around that, instead of creating stages for each tensor that goes into tft.scale_to_0_1 we could fuse them by first stacking them together, and then passing them into tft.scale_to_0_1 with 'elementwise=True'.
The result will be the same, because the min and max are computed per 'column' instead of across the whole tensor.
This would look something like this:
stacked = tf.stack([inputs[key] for key in NUMERIC_FEATURE_KEYS], axis=1)
scaled_stacked = tft.scale_to_0_1(stacked, elementwise=True)
for key, tensor in zip(NUMERIC_FEATURE_KEYS, tf.unstack(scaled_stacked, axis=1)):
outputs[key] = tensor