import numpy as np, pandas as pd
from scipy import sparse
import functools, multiprocessing
from multiprocessing import Pool
num_cores = multiprocessing.cpu_count()
def parallelize_dataframe(df, func, U=None, V=None):
#blockSize = 5000
num_partitions = 5 # int( np.ceil(df.shape[0]*(1.0/blockSize)) )
blocks = np.array_split(df, num_partitions)
pool = Pool(num_cores)
if V is not None and U is not None:
# apply func with multiple arguments to dataframe (i.e. involves multiple columns)
df = pd.concat(pool.map(functools.partial(func, U=U, V=V), blocks))
else:
# apply func with one argument to dataframe (i.e. involves single column)
df = pd.concat(pool.map(func, blocks))
pool.close()
pool.join()
return df
def square(x):
return x**2
def test_func(data):
print("Process working on: ", data.shape)
data["squareV"] = data["testV"].apply(square)
return data
def vecProd(row, U, V):
return np.sum( np.multiply(U[int(row["obsI"]),:], V[int(row["obsJ"]),:]) )
def mProd_func(data, U, V):
data["predV"] = data.apply( lambda row: vecProd(row, U, V), axis=1 )
return data
def generate_simulated_data():
N, D, nnz, K = [302, 184, 5000, 5]
I = np.random.choice(N, size=nnz, replace=True)
J = np.random.choice(D, size=nnz, replace=True)
vals = np.random.sample(nnz)
sparseY = sparse.csc_matrix((vals, (I, J)), shape=[N, D])
# Generate parameters U and V which could be used to reconstruct the matrix Y
U = np.random.sample(N*K).reshape([N,K])
V = np.random.sample(D*K).reshape([D,K])
return sparseY, U, V
def main():
Y, U, V = generate_simulated_data()
# find row, column indices and obvseved values for sparse matrix Y
(testI, testJ, testV) = sparse.find(Y)
colNames = ["obsI", "obsJ", "testV", "predV", "squareV"]
dtypes = {"obsI":int, "obsJ":int, "testV":float, "predV":float, "squareV": float}
obsValDF = pd.DataFrame(np.zeros((len(testV), len(colNames))), columns=colNames)
obsValDF["obsI"] = testI
obsValDF["obsJ"] = testJ
obsValDF["testV"] = testV
obsValDF = obsValDF.astype(dtype=dtypes)
print("Y.shape: {!s}, #obsVals: {}, obsValDF.shape: {!s}".format(Y.shape, len(testV), obsValDF.shape))
# calculate the square of testVals
obsValDF = parallelize_dataframe(obsValDF, test_func)
# reconstruct prediction of testVals using parameters U and V
obsValDF = parallelize_dataframe(obsValDF, mProd_func, U, V)
print("obsValDF.shape after reconstruction: {!s}".format(obsValDF.shape))
print("First 5 elements of obsValDF:\n", obsValDF.iloc[:5,:])
if __name__ == '__main__':
main()
import time
import ray
ray.init()
# Define the function you want to apply map on, as remote function.
@ray.remote
def f(x):
# Do some work...
time.sleep(1)
return x*x
# Define a helper parmap(f, list) function.
# This function executes a copy of f() on each element in "list".
# Each copy of f() runs in a different process.
# Note f.remote(x) returns a future of its result (i.e.,
# an identifier of the result) rather than the result itself.
def parmap(f, list):
return [f.remote(x) for x in list]
# Call parmap() on a list consisting of first 5 integers.
result_ids = parmap(f, range(1, 6))
# Get the results
results = ray.get(result_ids)
print(results)
A parallel equivalent of the map() built-in function (it supports only
one iterable argument though). It blocks till the result is ready.
This method chops the iterable into a number of chunks which it submits to the
process pool as separate tasks. The (approximate) size of these chunks can be
specified by setting chunksize to a positive integ
例如,如果要映射此函数:
def f(x):
return x**2
要设置范围(10),可以使用内置的map()函数:
map(f, range(10))
或者使用多处理.Pool()对象的方法map():
import multiprocessing
pool = multiprocessing.Pool()
print pool.map(f, range(10))
对于那些寻找与R的mclapply()等价的Python的人,这里是我的实现。这是对以下两个示例的改进:
它可以应用于具有单个或多个参数的映射函数。
这可以通过Ray来实现,该系统允许您轻松地并行化和分发Python代码。
要并行化示例,需要使用
@ray.remote
装饰器定义映射函数,然后使用.remote
调用它。这将确保远程函数的每个实例都将在不同的进程中执行。这将打印:
它将以大约
len(list)/p
(四舍五入到最近的整数)结束,其中p
是您机器上的核心数。假设一台机器有两个内核,我们的示例将在5/2
四舍五入(即大约3
秒)内执行。与multiprocessing模块相比,使用Ray有许多优点。尤其是,同一代码将在一台机器上以及在一组机器上运行。有关Ray的更多优点,请参见this related post。
我觉得你需要的是map method in multiprocessing.Pool():
例如,如果要映射此函数:
要设置范围(10),可以使用内置的map()函数:
或者使用多处理.Pool()对象的方法map():
相关问题 更多 >
编程相关推荐