如果你想仔细考虑边缘条件(只从边缘的可用元素计算平均值)，下面的函数可以解决这个问题。

import numpy as np

def running_mean(x, N):
    out = np.zeros_like(x, dtype=np.float64)
    dim_len = x.shape[0]
    for i in range(dim_len):
        if N%2 == 0:
            a, b = i - (N-1)//2, i + (N-1)//2 + 2
        else:
            a, b = i - (N-1)//2, i + (N-1)//2 + 1

        #cap indices to min and max indices
        a = max(0, a)
        b = min(dim_len, b)
        out[i] = np.mean(x[a:b])
    return out

>>> running_mean(np.array([1,2,3,4]), 2)
array([1.5, 2.5, 3.5, 4. ])

>>> running_mean(np.array([1,2,3,4]), 3)
array([1.5, 2. , 3. , 3.5])

Talib包含一个简单的移动平均工具，以及其他类似的平均工具(即指数移动平均)。下面将该方法与其他一些解决方案进行比较。

%timeit pd.Series(np.arange(100000)).rolling(3).mean()
2.53 ms ± 40.5 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

%timeit talib.SMA(real = np.arange(100000.), timeperiod = 3)
348 µs ± 3.5 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

%timeit moving_average(np.arange(100000))
638 µs ± 45.1 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

需要注意的是，real必须有dtype = float的元素。否则将引发以下错误

例外:实不是双的

for i in range(len(Data)):
    Data[i, 1] = Data[i-lookback:i, 0].sum() / lookback

试试这段代码。我认为这样更简单，也能达到目的。 回望是移动平均线的窗口。

在Data[i-lookback:i, 0].sum()中，我放了0来指代数据集的第一列，但如果你有多个列，你可以放任何你喜欢的列。

所有的答案似乎都集中在预先计算的列表的情况下。对于实际运行的用例，数字一个接一个地进来，这里有一个简单的类，它提供了对最后N个值求平均的服务:

import numpy as np
class RunningAverage():
    def __init__(self, stack_size):
        self.stack = [0 for _ in range(stack_size)]
        self.ptr = 0
        self.full_cycle = False
    def add(self,value):
        self.stack[self.ptr] = value
        self.ptr += 1
        if self.ptr == len(self.stack):
            self.full_cycle = True
            self.ptr = 0
    def get_avg(self):
        if self.full_cycle:
            return np.mean(self.stack)
        else:
            return np.mean(self.stack[:self.ptr])

用法:

N = 50  # size of the averaging window
run_avg = RunningAverage(N)
for i in range(1000):
    value = <my computation>
    run_avg.add(value)
    if i % 20 ==0: # print once in 20 iters:
        print(f'the average value is {run_avg.get_avg()}')

您也可以编写自己的Python C扩展。

这当然不是最简单的方法，但与使用np相比，这将使您运行得更快，内存效率更高。堆积:作为建筑块的堆积

// moving_average.c
#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION
#include <Python.h>
#include <numpy/arrayobject.h>

static PyObject *moving_average(PyObject *self, PyObject *args) {
    PyObject *input;
    int64_t window_size;
    PyArg_ParseTuple(args, "Ol", &input, &window_size);
    if (PyErr_Occurred()) return NULL;
    if (!PyArray_Check(input) || !PyArray_ISNUMBER((PyArrayObject *)input)) {
        PyErr_SetString(PyExc_TypeError, "First argument must be a numpy array with numeric dtype");
        return NULL;
    }
    
    int64_t input_size = PyObject_Size(input);
    double *input_data;
    if (PyArray_AsCArray(&input, &input_data, (npy_intp[]){ [0] = input_size }, 1, PyArray_DescrFromType(NPY_DOUBLE)) != 0) {
        PyErr_SetString(PyExc_TypeError, "Failed to simulate C array of type double");
        return NULL;
    }
    
    int64_t output_size = input_size - window_size + 1;
    PyObject *output = PyArray_SimpleNew(1, (npy_intp[]){ [0] = output_size }, NPY_DOUBLE);
    double *output_data = PyArray_DATA((PyArrayObject *)output);
    
    double cumsum_before = 0;
    double cumsum_after = 0;
    for (int i = 0; i < window_size; ++i) {
        cumsum_after += input_data[i];
    }
    for (int i = 0; i < output_size - 1; ++i) {
        output_data[i] = (cumsum_after - cumsum_before) / window_size;
        cumsum_after += input_data[i + window_size];
        cumsum_before += input_data[i];
    }
    output_data[output_size - 1] = (cumsum_after - cumsum_before) / window_size;

    return output;
}

static PyMethodDef methods[] = {
    {
        "moving_average", 
        moving_average, 
        METH_VARARGS, 
        "Rolling mean of numpy array with specified window size"
    },
    {NULL, NULL, 0, NULL}
};

static struct PyModuleDef moduledef = {
    PyModuleDef_HEAD_INIT,
    "moving_average",
    "C extension for finding the rolling mean of a numpy array",
    -1,
    methods
};

PyMODINIT_FUNC PyInit_moving_average(void) {
    PyObject *module = PyModule_Create(&moduledef);
    import_array();
    return module;
}

METH_VARARGS specifies that the method only takes positional arguments. PyArg_ParseTuple allows you to parse these positional arguments. By using PyErr_SetString and returning NULL from the method, you can signal that an exception has occurred to the Python interpreter from the C extension. PyArray_AsCArray allows your method to be polymorphic when it comes to input array dtype, alignment, whether the array is C-contiguous (See "Can a numpy 1d array not be contiguous?") etc. without needing to create a copy of the array. If you instead used PyArray_DATA, you'd need to deal with this yourself. PyArray_SimpleNew allows you to create a new numpy array. This is similar to using np.empty. The array will not be initialized, and might contain non-deterministic junk which could surprise you if you forget to overwrite it.

构建C扩展

# setup.py
from setuptools import setup, Extension
import numpy

setup(
  ext_modules=[
    Extension(
      'moving_average',
      ['moving_average.c'],
      include_dirs=[numpy.get_include()]
    )
  ]
)

# python setup.py build_ext --build-lib=.

基准

import numpy as np

# Our compiled C extension:
from moving_average import moving_average as moving_average_c

# Answer by Jaime using npcumsum
def moving_average_cumsum(a, n) :
    ret = np.cumsum(a, dtype=float)
    ret[n:] = ret[n:] - ret[:-n]
    return ret[n - 1:] / n

# Answer by yatu using np.convolve
def moving_average_convolve(a, n):
    return np.convolve(a, np.ones(n), 'valid') / n

a = np.random.rand(1_000_000)
print('window_size = 3')
%timeit moving_average_c(a, 3)
%timeit moving_average_cumsum(a, 3)
%timeit moving_average_convolve(a, 3)

print('\nwindow_size = 100')
%timeit moving_average_c(a, 100)
%timeit moving_average_cumsum(a, 100)
%timeit moving_average_convolve(a, 100)

window_size = 3
958 µs ± 4.68 µs per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
4.52 ms ± 15.4 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
809 µs ± 463 ns per loop (mean ± std. dev. of 7 runs, 1,000 loops each)

window_size = 100
977 µs ± 937 ns per loop (mean ± std. dev. of 7 runs, 1,000 loops each)
6.16 ms ± 19.1 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
14.2 ms ± 12.4 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

如果有人需要一个简单的解决方案，这里有一个

def moving_average(a,n):
    N=len(a)
    return np.array([np.mean(a[i:i+n]) for i in np.arange(0,N-n+1)])

你可以通过在np.arange(0,N-n+1,step)中添加step参数来改变窗口之间的重叠