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?

有点晚了，但我已经做了我自己的小函数，它不环绕端点或垫与零，然后用于查找平均值。进一步的处理是，它还在线性间隔点上对信号进行重新采样。随意定制代码以获得其他特性。

该方法是一个简单的矩阵乘法与规范化高斯核。

def running_mean(y_in, x_in, N_out=101, sigma=1):
    '''
    Returns running mean as a Bell-curve weighted average at evenly spaced
    points. Does NOT wrap signal around, or pad with zeros.
    
    Arguments:
    y_in -- y values, the values to be smoothed and re-sampled
    x_in -- x values for array
    
    Keyword arguments:
    N_out -- NoOf elements in resampled array.
    sigma -- 'Width' of Bell-curve in units of param x .
    '''
    import numpy as np
    N_in = len(y_in)

    # Gaussian kernel
    x_out = np.linspace(np.min(x_in), np.max(x_in), N_out)
    x_in_mesh, x_out_mesh = np.meshgrid(x_in, x_out)
    gauss_kernel = np.exp(-np.square(x_in_mesh - x_out_mesh) / (2 * sigma**2))
    # Normalize kernel, such that the sum is one along axis 1
    normalization = np.tile(np.reshape(np.sum(gauss_kernel, axis=1), (N_out, 1)), (1, N_in))
    gauss_kernel_normalized = gauss_kernel / normalization
    # Perform running average as a linear operation
    y_out = gauss_kernel_normalized @ y_in

    return y_out, x_out

正弦信号加正态分布噪声的一个简单用法:

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)

使用@Aikude的变量，我编写了一行程序。

import numpy as np

mylist = [1, 2, 3, 4, 5, 6, 7]
N = 3

mean = [np.mean(mylist[x:x+N]) for x in range(len(mylist)-N+1)]
print(mean)

>>> [2.0, 3.0, 4.0, 5.0, 6.0]

更新:已经提出了更有效的解决方案，scipy的uniform_filter1d可能是“标准”第三方库中最好的，还有一些更新的或专门的库可用。

你可以用np。卷积得到:

np.convolve(x, np.ones(N)/N, mode='valid')

解释

The running mean is a case of the mathematical operation of convolution. For the running mean, you slide a window along the input and compute the mean of the window's contents. For discrete 1D signals, convolution is the same thing, except instead of the mean you compute an arbitrary linear combination, i.e., multiply each element by a corresponding coefficient and add up the results. Those coefficients, one for each position in the window, are sometimes called the convolution kernel. The arithmetic mean of N values is (x_1 + x_2 + ... + x_N) / N, so the corresponding kernel is (1/N, 1/N, ..., 1/N), and that's exactly what we get by using np.ones(N)/N.

边缘

np的模态参数。Convolve指定如何处理边缘。我在这里选择有效模式，因为我认为这是大多数人期望的运行方式，但您可能有其他优先级。下面是一个图表，说明了模式之间的差异:

import numpy as np
import matplotlib.pyplot as plt
modes = ['full', 'same', 'valid']
for m in modes:
    plt.plot(np.convolve(np.ones(200), np.ones(50)/50, mode=m));
plt.axis([-10, 251, -.1, 1.1]);
plt.legend(modes, loc='lower center');
plt.show()