另一种不使用numpy或pandas找到移动平均线的方法

import itertools
sample = [2, 6, 10, 8, 11, 10]
list(itertools.starmap(
    lambda a,b: b/a, 
    enumerate(itertools.accumulate(sample), 1))
)

将打印[2.0,4.0,6.0,6.5,7.4,7.83333333333333333]

2.0 = (2)/1 4.0 is (2 + 6) / 2 6.0 = (2 + 6 + 10) / 3 .

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

出于教学目的，让我再添加两个Numpy解决方案(比cumsum解决方案慢):

import numpy as np
from numpy.lib.stride_tricks import as_strided

def ra_strides(arr, window):
    ''' Running average using as_strided'''
    n = arr.shape[0] - window + 1
    arr_strided = as_strided(arr, shape=[n, window], strides=2*arr.strides)
    return arr_strided.mean(axis=1)

def ra_add(arr, window):
    ''' Running average using add.reduceat'''
    n = arr.shape[0] - window + 1
    indices = np.array([0, window]*n) + np.repeat(np.arange(n), 2)
    arr = np.append(arr, 0)
    return np.add.reduceat(arr, indices )[::2]/window

使用的函数:as_strided, add.reduceat

高效的解决方案

卷积比直接的方法好得多，但(我猜)它使用FFT，因此相当慢。但是，下面的方法特别适用于计算运行平均值

def running_mean(x, N):
    cumsum = numpy.cumsum(numpy.insert(x, 0, 0)) 
    return (cumsum[N:] - cumsum[:-N]) / float(N)

要检查的代码

In[3]: x = numpy.random.random(100000)
In[4]: N = 1000
In[5]: %timeit result1 = numpy.convolve(x, numpy.ones((N,))/N, mode='valid')
10 loops, best of 3: 41.4 ms per loop
In[6]: %timeit result2 = running_mean(x, N)
1000 loops, best of 3: 1.04 ms per loop

注意numpy。allclose(result1, result2)为True，两个方法等价。 N越大，时间差异越大。

警告:虽然cumsum更快，但会增加浮点错误，这可能导致您的结果无效/不正确/不可接受

这里的评论指出了这个浮点错误问题，但我在回答中让它更明显。

# demonstrate loss of precision with only 100,000 points
np.random.seed(42)
x = np.random.randn(100000)+1e6
y1 = running_mean_convolve(x, 10)
y2 = running_mean_cumsum(x, 10)
assert np.allclose(y1, y2, rtol=1e-12, atol=0)

the more points you accumulate over the greater the floating point error (so 1e5 points is noticable, 1e6 points is more significant, more than 1e6 and you may want to resetting the accumulators) you can cheat by using np.longdouble but your floating point error still will get significant for relatively large number of points (around >1e5 but depends on your data) you can plot the error and see it increasing relatively fast the convolve solution is slower but does not have this floating point loss of precision the uniform_filter1d solution is faster than this cumsum solution AND does not have this floating point loss of precision

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)

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: