>>> # the recommended syntax to import pandas
>>> import pandas as PD
>>> import numpy as NP
>>> # prepare some fake data:
>>> # the date-time indices:
>>> t = PD.date_range('1/1/2010', '12/31/2012', freq='D')
>>> # the data:
>>> x = NP.arange(0, t.shape[0])
>>> # combine the data & index into a Pandas 'Series' object
>>> D = PD.Series(x, t)
>>> d_mva = PD.rolling_mean(D, 10)
>>> # d_mva is the same size as the original Series
>>> d_mva.shape
(1096,)
>>> # though obviously the first w values are NaN where w is the window size
>>> d_mva[:3]
2010-01-01 NaN
2010-01-02 NaN
2010-01-03 NaN
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])
# the recommended syntax to import pandas
import pandas as pd
import numpy as np
# prepare some fake data:
# the date-time indices:
t = pd.date_range('1/1/2010', '12/31/2012', freq='D')
# the data:
x = np.arange(0, t.shape[0])
# combine the data & index into a Pandas 'Series' object
D = pd.Series(x, t)
现在，只需在dataframe上调用函数rolling，窗口大小，在下面的例子中是10天。
d_mva10 = D.rolling(10).mean()
# d_mva is the same size as the original Series
# though obviously the first w values are NaN where w is the window size
d_mva10[:11]
2010-01-01 NaN
2010-01-02 NaN
2010-01-03 NaN
2010-01-04 NaN
2010-01-05 NaN
2010-01-06 NaN
2010-01-07 NaN
2010-01-08 NaN
2010-01-09 NaN
2010-01-10 4.5
2010-01-11 5.5
Freq: D, dtype: float64
x = np.random.randint(10, size=20)
def moving_average(arr, n):
return [ (arr[:i+1][::-1][:n]).mean() for i, ele in enumerate(arr) ]
d = 5
moving_average(x, d)
通过将下面的解决方案与使用cumsum of numpy的解决方案进行比较，这个解决方案几乎需要一半的时间。这是因为它不需要遍历整个数组来做cumsum，然后做所有的减法。此外，如果数组很大且数量很大，则cumsum可以为"危险的" (可能的溢出)。当然，这里也存在危险，但至少我们只把重要的数字加在一起。
def moving_average(array_numbers, n):
if n > len(array_numbers):
return []
temp_sum = sum(array_numbers[:n])
averages = [temp_sum / float(n)]
for first_index, item in enumerate(array_numbers[n:]):
temp_sum += item - array_numbers[first_index]
averages.append(temp_sum / float(n))
return averages
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()}')
import numpy as np
M=np.arange(12)
avg=[]
i=0
while i<len(M)-2: #for n point average len(M) - (n-1)
avg.append((M[i]+M[i+1]+M[i+2])/3) #n is denominator
i+=1
print(avg)
