Question

我或多或少是一名Python新手，致力于此evolutionary Mona Lisa实验的音频模拟。

以下代码旨在：

将给定的.wav文件读入NumPy数组。
检测波形中的“过零点”，即当数组元素改变符号时。将数组拆分为这些点上波形“块”的嵌套列表。
将正面与负面块分开，然后将这些块重新组合并将它们重新组合成NumPy阵列，将正面与负面交替。我不能使用random.shuffle（），因为列表中有超过2000个元素。
比较混洗阵列的'适应性' 与原始样本，定义为差异的平方在混洗阵列和原始样本之间。

最终，我将添加复制，变异和选择，但目前我的健身功能存在问题。拆分，混洗和重组数组的尺寸与原始输入的尺寸不同，导致以下错误：

$ ValueError: operands could not be broadcast together with shapes (1273382) (1138213)

每次运行程序时，第二个数组的尺寸都不同，但总是在1138000-1145000左右。我在拆分，改组和重组步骤中似乎丢失了一些块，我怀疑我在步骤3中某处错误地使用了列表解析，但我无法弄清楚在哪里或为什么。出了什么问题？

# Import scipy audio tools, numpy, and randomization tools
import scipy
from scipy.io import wavfile

import numpy

from random import shuffle, randint

# Read a wav file data array, detect zero crossings, split at zero crossings, and return a nested list.
def process_wav(input):

    # Assign the wavefile data array to a variable.
    wavdata = input[1]

    # Detect zero crossings, i.e. changes in sign in the waveform data. The line below returns an array of the indices of elements after which a zero crossing occurs.
    zerocrossings = numpy.where(numpy.diff(numpy.sign(wavdata)))[0]
    # Increment each element in the array by one. Otherwise, the indices are off.
    zerocrossings = numpy.add(numpy.ones(zerocrossings.size, zerocrossings.dtype), zerocrossings)

    wavdatalist = wavdata.tolist()
    zerocrossingslist = zerocrossings.tolist()

    # Split the list at zero crossings. The function below splits a list at the given indices.      
    def partition(alist, indices):
        return [alist[i:j] for i, j in zip([0]+indices, indices+[None])]

    return partition(wavdatalist, zerocrossingslist)


# Accept a list as input, separate into positive and negative chunks, shuffle, and return a shuffled nested list
def shuffle_wav(list):

    # Separate waveform chunks into positive and negative lists.
    positivechunks = []
    negativechunks = []

    for chunk in list:
        if chunk[0] < 0:
            negativechunks.append(chunk)
        elif chunk[0] > 0:
            positivechunks.append(chunk)
        elif chunk[0] == 0:
            positivechunks.append(chunk)

    # Shuffle the chunks and append them to a list, alternating positive with negative.
    shuffledchunks = []
    while len(positivechunks) >= 0 and len(negativechunks) > 0:
        currentpositivechunk = positivechunks.pop(randint(0, len(positivechunks)-1))
        shuffledchunks.append(currentpositivechunk)
        currentnegativechunk = negativechunks.pop(randint(0, len(negativechunks)-1))
        shuffledchunks.append(currentnegativechunk)

    return [chunk for sublist in shuffledchunks for chunk in sublist]

def get_fitness(array, target):
    return numpy.square(numpy.subtract(target, array))

# Read a sample wav file. The wavfile function returns a tuple of the file's sample rate and data as a numpy array, to be passed to the process_wav() function.
input = scipy.io.wavfile.read('sample.wav')     

wavchunks = process_wav(input)  
shuffledlist = shuffle_wav(wavchunks)   
output = numpy.array(shuffledlist, dtype='int16')
print get_fitness(output, input[1])

scipy.io.wavfile.write('output.wav', 44100, output)

编辑：这是完整的追溯：

Traceback (most recent call last):
  File "evowav.py", line 64, in <module>
    print get_fitness(output, input[1])
  File "evowav.py", line 56, in get_fitness
    return numpy.square(numpy.subtract(target, array))
ValueError: operands could not be broadcast together with shapes (1273382) (1136678)`

Answer 1

首先，让我们清理一些代码。

不要将list和input等python内置函数用作变量名来覆盖它们。 Python并没有严格阻止它，但它会在以后引起意外。
无需明确调用z = numpy.add(x, y)之类的内容。 z = x + y更加pythonic，完全相同。（假设x和y是numpy数组。）同样，没有必要创建一个新的数组，只是为了在numpy数组中的每个项目添加1。如果您需要副本，只需致电x += 1或x = x + 1。
不要在定义之上添加有关函数功能的注释，而是将其放在下面。这不仅仅是一种样式约定，因为python的内置帮助和文档工具只能利用这些“docstrings”，如果它们是第一个注释（或多行字符串，因为更常见，因此三重引号）低于函数定义。

正如@talonmies所说，你的问题来自于你假设你有相同数量的正面和负面的块。有几种方法，但一个简单的方法就是使用itertools.izip_longest。

现在，作为一个例子......

import random
import itertools
import numpy
import scipy.io.wavfile

def main():
    """Read a wav file and shuffle the negative and positive pieces."""
    # Use unpacking to your advantage, and avoid using "input" as a var name
    samplerate, data = scipy.io.wavfile.read('sample.wav')     

    # Note, my sample.wav is stereo, so I'm going to just work with one channel
    # If yours is mono, you'd want to just pass "data" directly in
    left, right = data.T

    wavchunks = process_wav(left)  
    output = shuffle_wav(wavchunks).astype(numpy.int16)
    print get_fitness(output, samplerate)

    scipy.io.wavfile.write('output.wav', 44100, output)

def process_wav(wavdata):
    """Read a wav file data array, detect zero crossings, 
    split at zero crossings, and return a list of numpy arrays"""

    # I prefer nonzero to where, but either works in this case...
    zerocrossings, = numpy.diff(numpy.sign(wavdata)).nonzero()
    zerocrossings += 1
    indicies = [0] + zerocrossings.tolist() + [None]

    # The key is that we don't need to convert everything to a list.
    # Just pass back a list of views into the array. This uses less memory.
    return [wavdata[i:j] for i, j in zip(indicies[:-1], indicies[1:])]

def shuffle_wav(partitions):
    """Accept a list as input, separate into positive and negative chunks, 
    shuffle, and return a shuffled nested list."""

    # Instead of iterating through each item, just use indexing 
    poschunks = partitions[::2]
    negchunks = partitions[1::2]
    if poschunks[0][0] < 0:
        # Reverse the variable names if the first chunk wasn't positive.
        negchunks, poschunks = poschunks, negchunks

    # Instead of popping a random index off, just shuffle the lists...
    random.shuffle(poschunks)
    random.shuffle(negchunks)

    # To avoid the error you were getting, use izip_longest
    chunks = itertools.izip_longest(poschunks, negchunks, fillvalue=[])

    return numpy.hstack(item for sublist in chunks for item in sublist)


def get_fitness(array, target):
    """Compares sum of square differences between the two arrays."""
    # I'm going to assume that you wanted a single sum returned here...
    # Your original code returned an array.
    return ((array - target)**2).sum()

main()

'shuffled'NumPy数组上的尺寸不匹配

1 个答案: