另一个解决方案是使用标准库和deque:

from collections import deque
import itertools

def moving_average(iterable, n=3):
    # http://en.wikipedia.org/wiki/Moving_average
    it = iter(iterable) 
    # create an iterable object from input argument
    d = deque(itertools.islice(it, n-1))  
    # create deque object by slicing iterable
    d.appendleft(0)
    s = sum(d)
    for elem in it:
        s += elem - d.popleft()
        d.append(elem)
        yield s / n

# example on how to use it
for i in  moving_average([40, 30, 50, 46, 39, 44]):
    print(i)

# 40.0
# 42.0
# 45.0
# 43.0

上述所有的解决方案都很差，因为它们缺乏

由于本机python而不是numpy向量化实现， 数值稳定性，由于numpy使用不当。cumsum或 由于O(len(x) * w)实现为卷积的速度。

鉴于

import numpy
m = 10000
x = numpy.random.rand(m)
w = 1000

注意x_[:w].sum()等于x[:w-1].sum()。因此，对于第一个平均值，numpy.cumsum(…)加上x[w] / w(通过x_[w+1] / w)，并减去0(从x_[0] / w)。结果是x[0:w].mean()

通过cumsum，您将通过添加x[w+1] / w并减去x[0] / w来更新第二个平均值，从而得到x[1:w+1].mean()。

这将一直进行，直到到达x[-w:].mean()。

x_ = numpy.insert(x, 0, 0)
sliding_average = x_[:w].sum() / w + numpy.cumsum(x_[w:] - x_[:-w]) / w

这个解是向量化的，O(m)，可读且数值稳定。

或用于python计算的模块

在我在Tradewave.net的测试中，TA-lib总是赢:

import talib as ta
import numpy as np
import pandas as pd
import scipy
from scipy import signal
import time as t

PAIR = info.primary_pair
PERIOD = 30

def initialize():
    storage.reset()
    storage.elapsed = storage.get('elapsed', [0,0,0,0,0,0])

def cumsum_sma(array, period):
    ret = np.cumsum(array, dtype=float)
    ret[period:] = ret[period:] - ret[:-period]
    return ret[period - 1:] / period

def pandas_sma(array, period):
    return pd.rolling_mean(array, period)

def api_sma(array, period):
    # this method is native to Tradewave and does NOT return an array
    return (data[PAIR].ma(PERIOD))

def talib_sma(array, period):
    return ta.MA(array, period)

def convolve_sma(array, period):
    return np.convolve(array, np.ones((period,))/period, mode='valid')

def fftconvolve_sma(array, period):    
    return scipy.signal.fftconvolve(
        array, np.ones((period,))/period, mode='valid')    

def tick():

    close = data[PAIR].warmup_period('close')

    t1 = t.time()
    sma_api = api_sma(close, PERIOD)
    t2 = t.time()
    sma_cumsum = cumsum_sma(close, PERIOD)
    t3 = t.time()
    sma_pandas = pandas_sma(close, PERIOD)
    t4 = t.time()
    sma_talib = talib_sma(close, PERIOD)
    t5 = t.time()
    sma_convolve = convolve_sma(close, PERIOD)
    t6 = t.time()
    sma_fftconvolve = fftconvolve_sma(close, PERIOD)
    t7 = t.time()

    storage.elapsed[-1] = storage.elapsed[-1] + t2-t1
    storage.elapsed[-2] = storage.elapsed[-2] + t3-t2
    storage.elapsed[-3] = storage.elapsed[-3] + t4-t3
    storage.elapsed[-4] = storage.elapsed[-4] + t5-t4
    storage.elapsed[-5] = storage.elapsed[-5] + t6-t5    
    storage.elapsed[-6] = storage.elapsed[-6] + t7-t6        

    plot('sma_api', sma_api)  
    plot('sma_cumsum', sma_cumsum[-5])
    plot('sma_pandas', sma_pandas[-10])
    plot('sma_talib', sma_talib[-15])
    plot('sma_convolve', sma_convolve[-20])    
    plot('sma_fftconvolve', sma_fftconvolve[-25])

def stop():

    log('ticks....: %s' % info.max_ticks)

    log('api......: %.5f' % storage.elapsed[-1])
    log('cumsum...: %.5f' % storage.elapsed[-2])
    log('pandas...: %.5f' % storage.elapsed[-3])
    log('talib....: %.5f' % storage.elapsed[-4])
    log('convolve.: %.5f' % storage.elapsed[-5])    
    log('fft......: %.5f' % storage.elapsed[-6])

结果:

[2015-01-31 23:00:00] ticks....: 744
[2015-01-31 23:00:00] api......: 0.16445
[2015-01-31 23:00:00] cumsum...: 0.03189
[2015-01-31 23:00:00] pandas...: 0.03677
[2015-01-31 23:00:00] talib....: 0.00700  # <<< Winner!
[2015-01-31 23:00:00] convolve.: 0.04871
[2015-01-31 23:00:00] fft......: 0.22306

仅使用Python标准库(内存高效)

只提供标准库deque的另一个版本。令我惊讶的是，大多数答案都使用pandas或numpy。

def moving_average(iterable, n=3):
    d = deque(maxlen=n)
    for i in iterable:
        d.append(i)
        if len(d) == n:
            yield sum(d)/n

r = moving_average([40, 30, 50, 46, 39, 44])
assert list(r) == [40.0, 42.0, 45.0, 43.0]

实际上，我在python文档中找到了另一个实现

def moving_average(iterable, n=3):
    # moving_average([40, 30, 50, 46, 39, 44]) --> 40.0 42.0 45.0 43.0
    # http://en.wikipedia.org/wiki/Moving_average
    it = iter(iterable)
    d = deque(itertools.islice(it, n-1))
    d.appendleft(0)
    s = sum(d)
    for elem in it:
        s += elem - d.popleft()
        d.append(elem)
        yield s / n

然而，在我看来，实现似乎比它应该的要复杂一些。但它肯定在标准python文档中是有原因的，有人能评论一下我的实现和标准文档吗?

如果你必须为非常小的数组(少于200个元素)重复这样做，我发现只用线性代数就能得到最快的结果。 最慢的部分是建立你的乘法矩阵y，你只需要做一次，但之后可能会更快。

import numpy as np
import random 

N = 100      # window size
size =200     # array length

x = np.random.random(size)
y = np.eye(size, dtype=float)

# prepare matrix
for i in range(size):
  y[i,i:i+N] = 1./N
  
# calculate running mean
z = np.inner(x,y.T)[N-1:]

上面有很多关于计算运行平均值的答案。我的回答增加了两个额外的特征:

忽略nan值 计算N个相邻值的平均值，不包括兴趣值本身

这第二个特征对于确定哪些值与总体趋势有一定的差异特别有用。

我使用numpy。cumsum，因为这是最省时的方法(参见上面Alleo的回答)。

N=10 # number of points to test on each side of point of interest, best if even
padded_x = np.insert(np.insert( np.insert(x, len(x), np.empty(int(N/2))*np.nan), 0, np.empty(int(N/2))*np.nan ),0,0)
n_nan = np.cumsum(np.isnan(padded_x))
cumsum = np.nancumsum(padded_x) 
window_sum = cumsum[N+1:] - cumsum[:-(N+1)] - x # subtract value of interest from sum of all values within window
window_n_nan = n_nan[N+1:] - n_nan[:-(N+1)] - np.isnan(x)
window_n_values = (N - window_n_nan)
movavg = (window_sum) / (window_n_values)

这段代码只适用于偶数n。它可以通过改变np来调整奇数。插入padded_x和n_nan。

输出示例(黑色为raw，蓝色为movavg):

这段代码可以很容易地修改，以删除从小于cutoff = 3的非nan值计算的所有移动平均值。

window_n_values = (N - window_n_nan).astype(float) # dtype must be float to set some values to nan
cutoff = 3
window_n_values[window_n_values<cutoff] = np.nan
movavg = (window_sum) / (window_n_values)