آموزش عملیات تجمیع داده ها در پایتون (Data Aggregation)

0 دیدگاه

پایتون چندین روش برای انجام عملیات تجمیع داده ها در پایتون (Aggregation) ارائه می دهد. این کار معمولاً با استفاده از کتابخانه های pandas و numpy انجام می شود. برای استفاده از توابع تجمیع، داده ها باید به صورت DataFrame باشند یا به این قالب تبدیل شوند.

اعمال تجمیع روی DataFrame

در این مثال یک DataFrame ایجاد می کنیم و روی آن عملیات تجمیع انجام می دهیم:

import pandas as pd
import numpy as np

df = pd.DataFrame(np.random.randn(10, 4),
      index = pd.date_range('1/1/2000', periods=10),
      columns = ['A', 'B', 'C', 'D'])

print df

r = df.rolling(window=3,min_periods=1)
print r

import pandas as pd

import numpy as np

df = pd.DataFrame(np.random.randn(10, 4),

index = pd.date_range('1/1/2000', periods=10),

columns = ['A', 'B', 'C', 'D'])

print df

r = df.rolling(window=3,min_periods=1)

print r

خروجی آن به شرح زیر است:

                    A           B           C           D
2000-01-01   1.088512   -0.650942   -2.547450   -0.566858
2000-01-02   0.790670   -0.387854   -0.668132    0.267283
2000-01-03  -0.575523   -0.965025    0.060427   -2.179780
2000-01-04   1.669653    1.211759   -0.254695    1.429166
2000-01-05   0.100568   -0.236184    0.491646   -0.466081
2000-01-06   0.155172    0.992975   -1.205134    0.320958
2000-01-07   0.309468   -0.724053   -1.412446    0.627919
2000-01-08   0.099489   -1.028040    0.163206   -1.274331
2000-01-09   1.639500   -0.068443    0.714008   -0.565969
2000-01-10   0.326761    1.479841    0.664282   -1.361169

Rolling [window=3,min_periods=1,center=False,axis=0]

A B C D

2000-01-01 1.088512 -0.650942 -2.547450 -0.566858

2000-01-02 0.790670 -0.387854 -0.668132 0.267283

2000-01-03 -0.575523 -0.965025 0.060427 -2.179780

2000-01-04 1.669653 1.211759 -0.254695 1.429166

2000-01-05 0.100568 -0.236184 0.491646 -0.466081

2000-01-06 0.155172 0.992975 -1.205134 0.320958

2000-01-07 0.309468 -0.724053 -1.412446 0.627919

2000-01-08 0.099489 -1.028040 0.163206 -1.274331

2000-01-09 1.639500 -0.068443 0.714008 -0.565969

2000-01-10 0.326761 1.479841 0.664282 -1.361169

Rolling [window=3,min_periods=1,center=False,axis=0]

ما می توانیم با ارسال یک تابع به کل DataFrame عملیات تجمیع را انجام دهیم یا با استفاده از روش استاندارد get item یک ستون خاص را انتخاب کنیم.

اعمال تجمیع روی کل DataFrame

import pandas as pd
import numpy as np

df = pd.DataFrame(np.random.randn(10, 4),
      index = pd.date_range('1/1/2000', periods=10),
      columns = ['A', 'B', 'C', 'D'])
print df

r = df.rolling(window=3,min_periods=1)
print r.aggregate(np.sum)

import pandas as pd

import numpy as np

df = pd.DataFrame(np.random.randn(10, 4),

index = pd.date_range('1/1/2000', periods=10),

columns = ['A', 'B', 'C', 'D'])

print df

r = df.rolling(window=3,min_periods=1)

print r.aggregate(np.sum)

خروجی آن به شرح زیر است:

                    A           B           C           D
2000-01-01   1.088512   -0.650942   -2.547450   -0.566858
2000-01-02   1.879182   -1.038796   -3.215581   -0.299575
2000-01-03   1.303660   -2.003821   -3.155154   -2.479355
2000-01-04   1.884801   -0.141119   -0.862400   -0.483331
2000-01-05   1.194699    0.010551    0.297378   -1.216695
2000-01-06   1.925393    1.968551   -0.968183    1.284044
2000-01-07   0.565208    0.032738   -2.125934    0.482797
2000-01-08   0.564129   -0.759118   -2.454374   -0.325454
2000-01-09   2.048458   -1.820537   -0.535232   -1.212381
2000-01-10   2.065750    0.383357    1.541496   -3.201469

                    A           B           C           D
2000-01-01   1.088512   -0.650942   -2.547450   -0.566858
2000-01-02   1.879182   -1.038796   -3.215581   -0.299575
2000-01-03   1.303660   -2.003821   -3.155154   -2.479355
2000-01-04   1.884801   -0.141119   -0.862400   -0.483331
2000-01-05   1.194699    0.010551    0.297378   -1.216695
2000-01-06   1.925393    1.968551   -0.968183    1.284044
2000-01-07   0.565208    0.032738   -2.125934    0.482797
2000-01-08   0.564129   -0.759118   -2.454374   -0.325454
2000-01-09   2.048458   -1.820537   -0.535232   -1.212381
2000-01-10   2.065750    0.383357    1.541496   -3.201469

A B C D

2000-01-01 1.088512 -0.650942 -2.547450 -0.566858

2000-01-02 1.879182 -1.038796 -3.215581 -0.299575

2000-01-03 1.303660 -2.003821 -3.155154 -2.479355

2000-01-04 1.884801 -0.141119 -0.862400 -0.483331

2000-01-05 1.194699 0.010551 0.297378 -1.216695

2000-01-06 1.925393 1.968551 -0.968183 1.284044

2000-01-07 0.565208 0.032738 -2.125934 0.482797

2000-01-08 0.564129 -0.759118 -2.454374 -0.325454

2000-01-09 2.048458 -1.820537 -0.535232 -1.212381

2000-01-10 2.065750 0.383357 1.541496 -3.201469

A B C D

2000-01-01 1.088512 -0.650942 -2.547450 -0.566858

2000-01-02 1.879182 -1.038796 -3.215581 -0.299575

2000-01-03 1.303660 -2.003821 -3.155154 -2.479355

2000-01-04 1.884801 -0.141119 -0.862400 -0.483331

2000-01-05 1.194699 0.010551 0.297378 -1.216695

2000-01-06 1.925393 1.968551 -0.968183 1.284044

2000-01-07 0.565208 0.032738 -2.125934 0.482797

2000-01-08 0.564129 -0.759118 -2.454374 -0.325454

2000-01-09 2.048458 -1.820537 -0.535232 -1.212381

2000-01-10 2.065750 0.383357 1.541496 -3.201469

اعمال تجمیع روی یک ستون خاص

import pandas as pd
import numpy as np

df = pd.DataFrame(np.random.randn(10, 4),
      index = pd.date_range('1/1/2000', periods=10),
      columns = ['A', 'B', 'C', 'D'])
print df
r = df.rolling(window=3,min_periods=1)
print r['A'].aggregate(np.sum)

import pandas as pd

import numpy as np

df = pd.DataFrame(np.random.randn(10, 4),

index = pd.date_range('1/1/2000', periods=10),

columns = ['A', 'B', 'C', 'D'])

print df

r = df.rolling(window=3,min_periods=1)

print r['A'].aggregate(np.sum)

خروجی آن به شرح زیر است:

                 A           B           C           D
2000-01-01   1.088512   -0.650942   -2.547450   -0.566858
2000-01-02   1.879182   -1.038796   -3.215581   -0.299575
2000-01-03   1.303660   -2.003821   -3.155154   -2.479355
2000-01-04   1.884801   -0.141119   -0.862400   -0.483331
2000-01-05   1.194699    0.010551    0.297378   -1.216695
2000-01-06   1.925393    1.968551   -0.968183    1.284044
2000-01-07   0.565208    0.032738   -2.125934    0.482797
2000-01-08   0.564129   -0.759118   -2.454374   -0.325454
2000-01-09   2.048458   -1.820537   -0.535232   -1.212381
2000-01-10   2.065750    0.383357    1.541496   -3.201469
2000-01-01   1.088512
2000-01-02   1.879182
2000-01-03   1.303660
2000-01-04   1.884801
2000-01-05   1.194699
2000-01-06   1.925393
2000-01-07   0.565208
2000-01-08   0.564129
2000-01-09   2.048458
2000-01-10   2.065750
Freq: D, Name: A, dtype: float64

A B C D

2000-01-01 1.088512 -0.650942 -2.547450 -0.566858

2000-01-02 1.879182 -1.038796 -3.215581 -0.299575

2000-01-03 1.303660 -2.003821 -3.155154 -2.479355

2000-01-04 1.884801 -0.141119 -0.862400 -0.483331

2000-01-05 1.194699 0.010551 0.297378 -1.216695

2000-01-06 1.925393 1.968551 -0.968183 1.284044

2000-01-07 0.565208 0.032738 -2.125934 0.482797

2000-01-08 0.564129 -0.759118 -2.454374 -0.325454

2000-01-09 2.048458 -1.820537 -0.535232 -1.212381

2000-01-10 2.065750 0.383357 1.541496 -3.201469

2000-01-01 1.088512

2000-01-02 1.879182

2000-01-03 1.303660

2000-01-04 1.884801

2000-01-05 1.194699

2000-01-06 1.925393

2000-01-07 0.565208

2000-01-08 0.564129

2000-01-09 2.048458

2000-01-10 2.065750

Freq: D, Name: A, dtype: float64

اعمال تجمیع روی چند ستون انتخابی

import pandas as pd
import numpy as np

df = pd.DataFrame(np.random.randn(10, 4),
      index = pd.date_range('1/1/2000', periods=10),
      columns = ['A', 'B', 'C', 'D'])
print df
r = df.rolling(window=3,min_periods=1)
print r[['A','B']].aggregate(np.sum)

import pandas as pd

import numpy as np

df = pd.DataFrame(np.random.randn(10, 4),

index = pd.date_range('1/1/2000', periods=10),

columns = ['A', 'B', 'C', 'D'])

print df

r = df.rolling(window=3,min_periods=1)

print r[['A','B']].aggregate(np.sum)

خروجی آن به شرح زیر است:

                 A           B           C           D
2000-01-01   1.088512   -0.650942   -2.547450   -0.566858
2000-01-02   1.879182   -1.038796   -3.215581   -0.299575
2000-01-03   1.303660   -2.003821   -3.155154   -2.479355
2000-01-04   1.884801   -0.141119   -0.862400   -0.483331
2000-01-05   1.194699    0.010551    0.297378   -1.216695
2000-01-06   1.925393    1.968551   -0.968183    1.284044
2000-01-07   0.565208    0.032738   -2.125934    0.482797
2000-01-08   0.564129   -0.759118   -2.454374   -0.325454
2000-01-09   2.048458   -1.820537   -0.535232   -1.212381
2000-01-10   2.065750    0.383357    1.541496   -3.201469
                    A           B
2000-01-01   1.088512   -0.650942
2000-01-02   1.879182   -1.038796
2000-01-03   1.303660   -2.003821
2000-01-04   1.884801   -0.141119
2000-01-05   1.194699    0.010551
2000-01-06   1.925393    1.968551
2000-01-07   0.565208    0.032738
2000-01-08   0.564129   -0.759118
2000-01-09   2.048458   -1.820537
2000-01-10   2.065750    0.383357