请注意,您可以从复杂的数据类型数组开始:
In [4]: data = np.zeros(250,dtype='float32, (250000,2)float32')
并将其视为具有同种数据类型的数组:
In [5]: data2 = data.view('float32')
然后,将其转换回复数类型:
In [7]: data3 = data2.view('float32, (250000,2)float32')
更改dtype是一项非常快速的操作;它不会影响底层数据,只会影响NumPy解释数据的方式。因此,更改dtype几乎没有代价。
因此,你可以利用上述技巧,将简单(同质)dtype的数组的相关知识轻易地应用到你的复杂dtype中。
以下代码借鉴了J.F. Sebastian的答案。
import numpy as np
import multiprocessing as mp
import contextlib
import ctypes
import struct
import base64
def decode(arg):
chunk, counter = arg
print len(chunk), counter
for x in chunk:
peak_counter = 0
data_buff = base64.b64decode(x)
buff_size = len(data_buff) / 4
unpack_format = ">%dL" % buff_size
index = 0
for y in struct.unpack(unpack_format, data_buff):
buff1 = struct.pack("I", y)
buff2 = struct.unpack("f", buff1)[0]
with shared_arr.get_lock():
data = tonumpyarray(shared_arr).view(
[('f0', '<f4'), ('f1', '<f4', (250000, 2))])
if (index % 2 == 0):
data[counter][1][peak_counter][0] = float(buff2)
else:
data[counter][1][peak_counter][1] = float(buff2)
peak_counter += 1
index += 1
counter += 1
def pool_init(shared_arr_):
global shared_arr
shared_arr = shared_arr_
def tonumpyarray(mp_arr):
return np.frombuffer(mp_arr.get_obj())
def numpy_array(shared_arr, peaks):
"""Fills the NumPy array 'data' with m/z-intensity values acquired
from b64 decoding and unpacking the binary string read from the
mzXML file, which is stored in the list 'peaks'.
The m/z values are assumed to be ordered without validating this
assumption.
Note: This function uses multi-processing
"""
processors = mp.cpu_count()
with contextlib.closing(mp.Pool(processes=processors,
initializer=pool_init,
initargs=(shared_arr, ))) as pool:
chunk_size = int(len(peaks) / processors)
map_parameters = []
for i in range(processors):
counter = i * chunk_size
chunk = peaks[i*chunk_size : (i + 1)*chunk_size]
map_parameters.append((chunk, counter))
pool.map(decode, map_parameters)
if __name__ == '__main__':
shared_arr = mp.Array(ctypes.c_float, (250000 * 2 * 250) + 250)
peaks = ...
numpy_array(shared_arr, peaks)
如果您可以保证执行分配的各个过程
if (index % 2 == 0):
data[counter][1][peak_counter][0] = float(buff2)
else:
data[counter][1][peak_counter][1] = float(buff2)
不要竞争地更改相同位置的数据,那么我相信你实际上可以放弃使用锁。
with shared_arr.get_lock():
但是我对你的代码理解不够,所以为了安全起见,我包含了锁。
mp
是什么?multiprocessing
模块? - user395760