Python中是否有SciPy函数或NumPy函数或模块来计算给定特定窗口的1D数组的运行平均值?


当前回答

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]

其他回答

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

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:]

上面的一个答案中有一个mab的注释,它有这个方法。瓶颈有move_mean,这是一个简单的移动平均:

import numpy as np
import bottleneck as bn

a = np.arange(10) + np.random.random(10)

mva = bn.move_mean(a, window=2, min_count=1)

Min_count是一个很方便的参数,它可以取数组中该点的移动平均值。如果你不设置min_count,它将等于window,并且直到window points的所有内容都将是nan。

从其他答案来看,我不认为这是问题所要求的,但我需要保持一个不断增长的值列表的运行平均值。

因此,如果你想保持从某个地方(站点,测量设备等)获取的值的列表和最近n个值更新的平均值,你可以使用下面的代码,这将最大限度地减少添加新元素的工作:

class Running_Average(object):
    def __init__(self, buffer_size=10):
        """
        Create a new Running_Average object.

        This object allows the efficient calculation of the average of the last
        `buffer_size` numbers added to it.

        Examples
        --------
        >>> a = Running_Average(2)
        >>> a.add(1)
        >>> a.get()
        1.0
        >>> a.add(1)  # there are two 1 in buffer
        >>> a.get()
        1.0
        >>> a.add(2)  # there's a 1 and a 2 in the buffer
        >>> a.get()
        1.5
        >>> a.add(2)
        >>> a.get()  # now there's only two 2 in the buffer
        2.0
        """
        self._buffer_size = int(buffer_size)  # make sure it's an int
        self.reset()

    def add(self, new):
        """
        Add a new number to the buffer, or replaces the oldest one there.
        """
        new = float(new)  # make sure it's a float
        n = len(self._buffer)
        if n < self.buffer_size:  # still have to had numbers to the buffer.
            self._buffer.append(new)
            if self._average != self._average:  # ~ if isNaN().
                self._average = new  # no previous numbers, so it's new.
            else:
                self._average *= n  # so it's only the sum of numbers.
                self._average += new  # add new number.
                self._average /= (n+1)  # divide by new number of numbers.
        else:  # buffer full, replace oldest value.
            old = self._buffer[self._index]  # the previous oldest number.
            self._buffer[self._index] = new  # replace with new one.
            self._index += 1  # update the index and make sure it's...
            self._index %= self.buffer_size  # ... smaller than buffer_size.
            self._average -= old/self.buffer_size  # remove old one...
            self._average += new/self.buffer_size  # ...and add new one...
            # ... weighted by the number of elements.

    def __call__(self):
        """
        Return the moving average value, for the lazy ones who don't want
        to write .get .
        """
        return self._average

    def get(self):
        """
        Return the moving average value.
        """
        return self()

    def reset(self):
        """
        Reset the moving average.

        If for some reason you don't want to just create a new one.
        """
        self._buffer = []  # could use np.empty(self.buffer_size)...
        self._index = 0  # and use this to keep track of how many numbers.
        self._average = float('nan')  # could use np.NaN .

    def get_buffer_size(self):
        """
        Return current buffer_size.
        """
        return self._buffer_size

    def set_buffer_size(self, buffer_size):
        """
        >>> a = Running_Average(10)
        >>> for i in range(15):
        ...     a.add(i)
        ...
        >>> a()
        9.5
        >>> a._buffer  # should not access this!!
        [10.0, 11.0, 12.0, 13.0, 14.0, 5.0, 6.0, 7.0, 8.0, 9.0]

        Decreasing buffer size:
        >>> a.buffer_size = 6
        >>> a._buffer  # should not access this!!
        [9.0, 10.0, 11.0, 12.0, 13.0, 14.0]
        >>> a.buffer_size = 2
        >>> a._buffer
        [13.0, 14.0]

        Increasing buffer size:
        >>> a.buffer_size = 5
        Warning: no older data available!
        >>> a._buffer
        [13.0, 14.0]

        Keeping buffer size:
        >>> a = Running_Average(10)
        >>> for i in range(15):
        ...     a.add(i)
        ...
        >>> a()
        9.5
        >>> a._buffer  # should not access this!!
        [10.0, 11.0, 12.0, 13.0, 14.0, 5.0, 6.0, 7.0, 8.0, 9.0]
        >>> a.buffer_size = 10  # reorders buffer!
        >>> a._buffer
        [5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 13.0, 14.0]
        """
        buffer_size = int(buffer_size)
        # order the buffer so index is zero again:
        new_buffer = self._buffer[self._index:]
        new_buffer.extend(self._buffer[:self._index])
        self._index = 0
        if self._buffer_size < buffer_size:
            print('Warning: no older data available!')  # should use Warnings!
        else:
            diff = self._buffer_size - buffer_size
            print(diff)
            new_buffer = new_buffer[diff:]
        self._buffer_size = buffer_size
        self._buffer = new_buffer

    buffer_size = property(get_buffer_size, set_buffer_size)

你可以测试它,例如:

def graph_test(N=200):
    import matplotlib.pyplot as plt
    values = list(range(N))
    values_average_calculator = Running_Average(N/2)
    values_averages = []
    for value in values:
        values_average_calculator.add(value)
        values_averages.append(values_average_calculator())
    fig, ax = plt.subplots(1, 1)
    ax.plot(values, label='values')
    ax.plot(values_averages, label='averages')
    ax.grid()
    ax.set_xlim(0, N)
    ax.set_ylim(0, N)
    fig.show()

这使:

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)