Moving average or running mean

Question

Is there a SciPy function or NumPy function or module for Python that calculates the running mean of a 1D array given a specific window?

Answer 1

For educational purposes, let me add two more Numpy solutions (which are slower than the cumsum solution):

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

Functions used: as_strided, add.reduceat

Answer 2

From reading the other answers I don't think this is what the question asked for, but I got here with the need of keeping a running average of a list of values that was growing in size.

So if you want to keep a list of values that you are acquiring from somewhere (a site, a measuring device, etc.) and the average of the last n values updated, you can use the code bellow, that minimizes the effort of adding new elements:

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)

And you can test it with, for example:

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()

Which gives:

Answer 3

Use Only Python Standard Library (Memory Efficient)

Just give another version of using the standard library deque only. It's quite a surprise to me that most of the answers are using pandas or 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]

Actually I found another implementation in python docs

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

However the implementation seems to me is a bit more complex than it should be. But it must be in the standard python docs for a reason, could someone comment on the implementation of mine and the standard doc?

Answer 4

or module for python that calculates

in my tests at Tradewave.net TA-lib always wins:

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])

results:

[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

Answer 5

I haven't yet checked how fast this is, but you could try:

from collections import deque

cache = deque() # keep track of seen values
n = 10          # window size
A = xrange(100) # some dummy iterable
cum_sum = 0     # initialize cumulative sum

for t, val in enumerate(A, 1):
    cache.append(val)
    cum_sum += val
    if t < n:
        avg = cum_sum / float(t)
    else:                           # if window is saturated,
        cum_sum -= cache.popleft()  # subtract oldest value
        avg = cum_sum / float(n)

Answer 6

Although there are solutions for this question here, please take a look at my solution. It is very simple and working well.

import numpy as np
dataset = np.asarray([1, 2, 3, 4, 5, 6, 7])
ma = list()
window = 3
for t in range(0, len(dataset)):
    if t+window <= len(dataset):
        indices = range(t, t+window)
        ma.append(np.average(np.take(dataset, indices)))
else:
    ma = np.asarray(ma)