কিছু মানদণ্ড সহ এটি করার বিভিন্ন উপায় এখানে রয়েছে। সর্বোত্তম পদ্ধতি হ'ল অন্যান্য লাইব্রেরি থেকে অনুকূলিত কোড ব্যবহার করে সংস্করণ। bottleneck.move_mean
পদ্ধতি সম্ভবত শ্রেষ্ঠ সব প্রায়। scipy.convolve
পদ্ধতির খুব দ্রুত, প্রসার্য এবং চিহ্নগুলি সিন্টেক্সের এবং ধারণার দিক থেকে সহজ, কিন্তু খুব বড় জানালা মানের জন্য ভাল স্কেল নেই। numpy.cumsum
আপনার যদি খাঁটি numpy
পদ্ধতির প্রয়োজন হয় তবে পদ্ধতিটি ভাল ।
দ্রষ্টব্য: এর মধ্যে কয়েকটি (উদাঃ bottleneck.move_mean
) কেন্দ্রিক নয় এবং আপনার ডেটা স্থানান্তর করবে।
import numpy as np
import scipy as sci
import scipy.signal as sig
import pandas as pd
import bottleneck as bn
import time as time
def rollavg_direct(a,n):
'Direct "for" loop'
assert n%2==1
b = a*0.0
for i in range(len(a)) :
b[i]=a[max(i-n//2,0):min(i+n//2+1,len(a))].mean()
return b
def rollavg_comprehension(a,n):
'List comprehension'
assert n%2==1
r,N = int(n/2),len(a)
return np.array([a[max(i-r,0):min(i+r+1,N)].mean() for i in range(N)])
def rollavg_convolve(a,n):
'scipy.convolve'
assert n%2==1
return sci.convolve(a,np.ones(n,dtype='float')/n, 'same')[n//2:-n//2+1]
def rollavg_convolve_edges(a,n):
'scipy.convolve, edge handling'
assert n%2==1
return sci.convolve(a,np.ones(n,dtype='float'), 'same')/sci.convolve(np.ones(len(a)),np.ones(n), 'same')
def rollavg_cumsum(a,n):
'numpy.cumsum'
assert n%2==1
cumsum_vec = np.cumsum(np.insert(a, 0, 0))
return (cumsum_vec[n:] - cumsum_vec[:-n]) / n
def rollavg_cumsum_edges(a,n):
'numpy.cumsum, edge handling'
assert n%2==1
N = len(a)
cumsum_vec = np.cumsum(np.insert(np.pad(a,(n-1,n-1),'constant'), 0, 0))
d = np.hstack((np.arange(n//2+1,n),np.ones(N-n)*n,np.arange(n,n//2,-1)))
return (cumsum_vec[n+n//2:-n//2+1] - cumsum_vec[n//2:-n-n//2]) / d
def rollavg_roll(a,n):
'Numpy array rolling'
assert n%2==1
N = len(a)
rolling_idx = np.mod((N-1)*np.arange(n)[:,None] + np.arange(N), N)
return a[rolling_idx].mean(axis=0)[n-1:]
def rollavg_roll_edges(a,n):
'Numpy array rolling, edge handling'
assert n%2==1
a = np.pad(a,(0,n-1-n//2), 'constant')*np.ones(n)[:,None]
m = a.shape[1]
idx = np.mod((m-1)*np.arange(n)[:,None] + np.arange(m), m)
out = a[np.arange(-n//2,n//2)[:,None], idx]
d = np.hstack((np.arange(1,n),np.ones(m-2*n+1+n//2)*n,np.arange(n,n//2,-1)))
return (out.sum(axis=0)/d)[n//2:]
def rollavg_pandas(a,n):
'Pandas rolling average'
return pd.DataFrame(a).rolling(n, center=True, min_periods=1).mean().to_numpy()
def rollavg_bottlneck(a,n):
'bottleneck.move_mean'
return bn.move_mean(a, window=n, min_count=1)
N = 10**6
a = np.random.rand(N)
functions = [rollavg_direct, rollavg_comprehension, rollavg_convolve,
rollavg_convolve_edges, rollavg_cumsum, rollavg_cumsum_edges,
rollavg_pandas, rollavg_bottlneck, rollavg_roll, rollavg_roll_edges]
print('Small window (n=3)')
%load_ext memory_profiler
for f in functions :
print('\n'+f.__doc__+ ' : ')
%timeit b=f(a,3)
print('\nLarge window (n=1001)')
for f in functions[0:-2] :
print('\n'+f.__doc__+ ' : ')
%timeit b=f(a,1001)
print('\nMemory\n')
print('Small window (n=3)')
N = 10**7
a = np.random.rand(N)
%load_ext memory_profiler
for f in functions[2:] :
print('\n'+f.__doc__+ ' : ')
%memit b=f(a,3)
print('\nLarge window (n=1001)')
for f in functions[2:-2] :
print('\n'+f.__doc__+ ' : ')
%memit b=f(a,1001)
সময়, ছোট উইন্ডো (n = 3)
Direct "for" loop :
4.14 s ± 23.7 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
List comprehension :
3.96 s ± 27.9 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
scipy.convolve :
1.07 ms ± 26.7 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)
scipy.convolve, edge handling :
4.68 ms ± 9.69 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
numpy.cumsum :
5.31 ms ± 5.11 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
numpy.cumsum, edge handling :
8.52 ms ± 11.1 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Pandas rolling average :
9.85 ms ± 9.63 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
bottleneck.move_mean :
1.3 ms ± 12.2 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Numpy array rolling :
31.3 ms ± 91.9 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Numpy array rolling, edge handling :
61.1 ms ± 55.9 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)
সময়, বড় উইন্ডো (n = 1001)
Direct "for" loop :
4.67 s ± 34 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
List comprehension :
4.46 s ± 14.6 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
scipy.convolve :
103 ms ± 165 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)
scipy.convolve, edge handling :
272 ms ± 1.23 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
numpy.cumsum :
5.19 ms ± 12.4 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
numpy.cumsum, edge handling :
8.7 ms ± 11.5 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
Pandas rolling average :
9.67 ms ± 199 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
bottleneck.move_mean :
1.31 ms ± 15.7 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
স্মৃতি, ছোট উইন্ডো (n = 3)
The memory_profiler extension is already loaded. To reload it, use:
%reload_ext memory_profiler
scipy.convolve :
peak memory: 362.66 MiB, increment: 73.61 MiB
scipy.convolve, edge handling :
peak memory: 510.24 MiB, increment: 221.19 MiB
numpy.cumsum :
peak memory: 441.81 MiB, increment: 152.76 MiB
numpy.cumsum, edge handling :
peak memory: 518.14 MiB, increment: 228.84 MiB
Pandas rolling average :
peak memory: 449.34 MiB, increment: 160.02 MiB
bottleneck.move_mean :
peak memory: 374.17 MiB, increment: 75.54 MiB
Numpy array rolling :
peak memory: 661.29 MiB, increment: 362.65 MiB
Numpy array rolling, edge handling :
peak memory: 1111.25 MiB, increment: 812.61 MiB
স্মৃতি, বড় উইন্ডো (n = 1001)
scipy.convolve :
peak memory: 370.62 MiB, increment: 71.83 MiB
scipy.convolve, edge handling :
peak memory: 521.98 MiB, increment: 223.18 MiB
numpy.cumsum :
peak memory: 451.32 MiB, increment: 152.52 MiB
numpy.cumsum, edge handling :
peak memory: 527.51 MiB, increment: 228.71 MiB
Pandas rolling average :
peak memory: 451.25 MiB, increment: 152.50 MiB
bottleneck.move_mean :
peak memory: 374.64 MiB, increment: 75.85 MiB