icodebroker - 686 중 8 번째 페이지 - 컴퓨터 프로그래밍 코드 데이터베이스

[PYTHON/PANDAS] DataFrame 클래스 : mean 메소드를 사용해 각 컬럼의 평균값 구하기

■ DataFrame 클래스의 mean 메소드를 사용해 각 컬럼의 평균값을 구하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame)

"""
                   A         B         C         D
2013-01-01 -0.427331 -0.372399  0.195643 -0.280798
2013-01-02  0.788336 -0.135781 -0.407083 -0.411756
2013-01-03 -1.350004 -1.162144 -0.036725  0.311316
2013-01-04 -1.433128 -0.333235  2.136542  1.440727
2013-01-05 -0.579444 -0.868167  0.041668  0.019251
2013-01-06 -0.576273  1.069613  1.486077 -1.053925
"""

print()

series = dataFrame.mean()

print(series)

"""
A   -0.596307
B   -0.300352
C    0.569354
D    0.004136
dtype: float64
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame)

"""

A B C D

2013-01-01 -0.427331 -0.372399 0.195643 -0.280798

2013-01-02 0.788336 -0.135781 -0.407083 -0.411756

2013-01-03 -1.350004 -1.162144 -0.036725 0.311316

2013-01-04 -1.433128 -0.333235 2.136542 1.440727

2013-01-05 -0.579444 -0.868167 0.041668 0.019251

2013-01-06 -0.576273 1.069613 1.486077 -1.053925

"""

print()

series = dataFrame.mean()

print(series)

"""

A -0.596307

B -0.300352

C 0.569354

D 0.004136

dtype: float64

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] DataFrame 클래스 : reindex 메소드에서 index/columns 인자를 사용해 인덱스/컬럼 재구성하기

■ DataFrame 클래스의 reindex 메소드에서 index/columns 인자를 사용해 인덱스/컬럼을 재구성하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""
                   A         B         C         D
2013-01-01 -0.273991  0.146700 -0.962881  0.531161
2013-01-02 -0.018018  1.398183 -0.601010 -1.012397
2013-01-03 -0.692638  3.078527  0.164985 -0.842357
2013-01-04 -0.492567 -0.533595 -1.081510 -1.283123
2013-01-05  0.003707 -1.165857  1.957604 -0.203697
2013-01-06  0.474054  2.345456  0.426076  0.330338
"""

print()

dataFrame2 = dataFrame1.reindex(index = datetimeIndex[0:4], columns = list(dataFrame1.columns) + ["E"])

print(dataFrame2)

"""
                   A         B         C         D   E
2013-01-01 -0.273991  0.146700 -0.962881  0.531161 NaN
2013-01-02 -0.018018  1.398183 -0.601010 -1.012397 NaN
2013-01-03 -0.692638  3.078527  0.164985 -0.842357 NaN
2013-01-04 -0.492567 -0.533595 -1.081510 -1.283123 NaN
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""

A B C D

2013-01-01 -0.273991 0.146700 -0.962881 0.531161

2013-01-02 -0.018018 1.398183 -0.601010 -1.012397

2013-01-03 -0.692638 3.078527 0.164985 -0.842357

2013-01-04 -0.492567 -0.533595 -1.081510 -1.283123

2013-01-05 0.003707 -1.165857 1.957604 -0.203697

2013-01-06 0.474054 2.345456 0.426076 0.330338

"""

print()

dataFrame2 = dataFrame1.reindex(index = datetimeIndex[0:4], columns = list(dataFrame1.columns) + ["E"])

print(dataFrame2)

"""

A B C D E

2013-01-01 -0.273991 0.146700 -0.962881 0.531161 NaN

2013-01-02 -0.018018 1.398183 -0.601010 -1.012397 NaN

2013-01-03 -0.692638 3.078527 0.164985 -0.842357 NaN

2013-01-04 -0.492567 -0.533595 -1.081510 -1.283123 NaN

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] DataFrame 클래스 : [] 연산자를 사용해 양수 값을 음수 값으로 변경하기

■ DataFrame 클래스에서 [] 연산자를 사용해 양수 값을 음수 값으로 변경하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame)

"""
                   A         B         C         D
2013-01-01 -2.415582 -0.520550 -1.801407  0.689429
2013-01-02  0.945648  1.536237 -1.778640  0.202120
2013-01-03  0.568660  1.233407 -1.016520  0.733999
2013-01-04 -0.290816  1.417348 -0.050532 -0.024839
2013-01-05 -0.611079  0.372267  1.136837 -2.772960
2013-01-06  2.101773 -0.337019  1.035544 -1.979480
"""

print()

dataFrame[dataFrame > 0] = -dataFrame

print(dataFrame)

"""
                   A         B         C         D
2013-01-01 -2.415582 -0.520550 -1.801407 -0.689429
2013-01-02 -0.945648 -1.536237 -1.778640 -0.202120
2013-01-03 -0.568660 -1.233407 -1.016520 -0.733999
2013-01-04 -0.290816 -1.417348 -0.050532 -0.024839
2013-01-05 -0.611079 -0.372267 -1.136837 -2.772960
2013-01-06 -2.101773 -0.337019 -1.035544 -1.979480
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame)

"""

A B C D

2013-01-01 -2.415582 -0.520550 -1.801407 0.689429

2013-01-02 0.945648 1.536237 -1.778640 0.202120

2013-01-03 0.568660 1.233407 -1.016520 0.733999

2013-01-04 -0.290816 1.417348 -0.050532 -0.024839

2013-01-05 -0.611079 0.372267 1.136837 -2.772960

2013-01-06 2.101773 -0.337019 1.035544 -1.979480

"""

print()

dataFrame[dataFrame > 0] = -dataFrame

print(dataFrame)

"""

A B C D

2013-01-01 -2.415582 -0.520550 -1.801407 -0.689429

2013-01-02 -0.945648 -1.536237 -1.778640 -0.202120

2013-01-03 -0.568660 -1.233407 -1.016520 -0.733999

2013-01-04 -0.290816 -1.417348 -0.050532 -0.024839

2013-01-05 -0.611079 -0.372267 -1.136837 -2.772960

2013-01-06 -2.101773 -0.337019 -1.035544 -1.979480

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install

[PYTHON/PANDAS] DataFrame 클래스 : loc 속성을 사용해 특정 컬럼 데이터 변경하기

■ DataFrame 클래스의 loc 속성을 사용해 특정 컬럼의 데이터를 변경하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame)

"""
                   A         B         C         D
2013-01-01 -1.024513  2.729313  0.866363  0.781470
2013-01-02 -0.594614 -0.238171 -0.041801 -0.337448
2013-01-03 -0.168112 -0.125254  0.037904  0.376932
2013-01-04  0.462503  0.292850 -1.011982  1.821977
2013-01-05 -1.207941 -0.644128 -2.173165 -0.039098
2013-01-06  0.684733  0.323357  1.083395  0.600062
"""

print()

dataFrame.loc[:, "D"] = np.array([5] * len(dataFrame))

print(dataFrame)

"""
                   A         B         C    D
2013-01-01 -1.024513  2.729313  0.866363  5.0
2013-01-02 -0.594614 -0.238171 -0.041801  5.0
2013-01-03 -0.168112 -0.125254  0.037904  5.0
2013-01-04  0.462503  0.292850 -1.011982  5.0
2013-01-05 -1.207941 -0.644128 -2.173165  5.0
2013-01-06  0.684733  0.323357  1.083395  5.0
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame)

"""

A B C D

2013-01-01 -1.024513 2.729313 0.866363 0.781470

2013-01-02 -0.594614 -0.238171 -0.041801 -0.337448

2013-01-03 -0.168112 -0.125254 0.037904 0.376932

2013-01-04 0.462503 0.292850 -1.011982 1.821977

2013-01-05 -1.207941 -0.644128 -2.173165 -0.039098

2013-01-06 0.684733 0.323357 1.083395 0.600062

"""

print()

dataFrame.loc[:, "D"] = np.array([5] * len(dataFrame))

print(dataFrame)

"""

A B C D

2013-01-01 -1.024513 2.729313 0.866363 5.0

2013-01-02 -0.594614 -0.238171 -0.041801 5.0

2013-01-03 -0.168112 -0.125254 0.037904 5.0

2013-01-04 0.462503 0.292850 -1.011982 5.0

2013-01-05 -1.207941 -0.644128 -2.173165 5.0

2013-01-06 0.684733 0.323357 1.083395 5.0

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] DataFrame 클래스 : iat 속성을 사용해 특정 셀 데이터 구하기

■ DataFrame 클래스의 iat 속성을 사용해 특정 셀의 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""
                   A         B         C         D
2013-01-01  0.248786 -0.657086  0.370225 -0.780453
2013-01-02  0.312765 -0.492724  0.654803  1.203754
2013-01-03  0.523139 -2.126527  0.553737  0.041873
2013-01-04  1.316598  0.422930  0.354900 -0.610110
2013-01-05  1.354282 -0.052645  0.497243 -0.943024
2013-01-06 -0.590947  0.494301 -0.692021 -0.128895
"""

print()

cellValue = dataFrame1.iat[1, 1] # numpy.float64

print(cellValue)

"""
-0.49272407509029337
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""

A B C D

2013-01-01 0.248786 -0.657086 0.370225 -0.780453

2013-01-02 0.312765 -0.492724 0.654803 1.203754

2013-01-03 0.523139 -2.126527 0.553737 0.041873

2013-01-04 1.316598 0.422930 0.354900 -0.610110

2013-01-05 1.354282 -0.052645 0.497243 -0.943024

2013-01-06 -0.590947 0.494301 -0.692021 -0.128895

"""

print()

cellValue = dataFrame1.iat[1, 1] # numpy.float64

print(cellValue)

"""

-0.49272407509029337

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] DataFrame 클래스 : iloc 속성을 사용해 컬럼 명시적 슬라이싱하기

■ DataFrame 클래스의 iloc 속성을 사용해 컬럼을 명시적으로 슬라이싱하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""
                   A         B         C         D
2013-01-01 -0.418967 -0.833904 -1.134466  1.835324
2013-01-02 -0.868156  1.606709 -0.455127 -0.484539
2013-01-03 -1.772179 -0.491787  2.472023  0.353378
2013-01-04 -1.455474  0.054363  0.405077 -1.180987
2013-01-05  0.787927 -1.620420  1.945740 -0.311787
2013-01-06 -2.274122  1.185262 -0.923877 -0.539917
"""

print()

dataFrame2 = dataFrame1.iloc[:, 1:3]

print(dataFrame2)

"""
                   B         C
2013-01-01 -0.833904 -1.134466
2013-01-02  1.606709 -0.455127
2013-01-03 -0.491787  2.472023
2013-01-04  0.054363  0.405077
2013-01-05 -1.620420  1.945740
2013-01-06  1.185262 -0.923877
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""

A B C D

2013-01-01 -0.418967 -0.833904 -1.134466 1.835324

2013-01-02 -0.868156 1.606709 -0.455127 -0.484539

2013-01-03 -1.772179 -0.491787 2.472023 0.353378

2013-01-04 -1.455474 0.054363 0.405077 -1.180987

2013-01-05 0.787927 -1.620420 1.945740 -0.311787

2013-01-06 -2.274122 1.185262 -0.923877 -0.539917

"""

print()

dataFrame2 = dataFrame1.iloc[:, 1:3]

print(dataFrame2)

"""

B C

2013-01-01 -0.833904 -1.134466

2013-01-02 1.606709 -0.455127

2013-01-03 -0.491787 2.472023

2013-01-04 0.054363 0.405077

2013-01-05 -1.620420 1.945740

2013-01-06 1.185262 -0.923877

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을

[PYTHON/PANDAS] DataFrame 클래스 : iloc 속성을 사용해 행 명시적 슬라이싱하기

■ DataFrame 클래스의 iloc 속성을 사용해 행을 명시적으로 슬라이싱하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""
                   A         B         C         D
2013-01-01  1.319131  1.050159 -0.329930  0.218507
2013-01-02  0.313371 -0.866423  0.648042  0.088910
2013-01-03  0.569949 -0.366839 -0.384350  0.130825
2013-01-04 -0.623062 -0.461133  1.438269 -0.315030
2013-01-05 -0.987991  0.187271 -0.835588  1.024690
2013-01-06  0.554150  1.119017 -0.064934  1.074642
"""

print()

dataFrame2 = dataFrame1.iloc[1:3, :]

print(dataFrame2)

"""
                   A         B         C         D
2013-01-02  0.313371 -0.866423  0.648042  0.088910
2013-01-03  0.569949 -0.366839 -0.384350  0.130825
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""

A B C D

2013-01-01 1.319131 1.050159 -0.329930 0.218507

2013-01-02 0.313371 -0.866423 0.648042 0.088910

2013-01-03 0.569949 -0.366839 -0.384350 0.130825

2013-01-04 -0.623062 -0.461133 1.438269 -0.315030

2013-01-05 -0.987991 0.187271 -0.835588 1.024690

2013-01-06 0.554150 1.119017 -0.064934 1.074642

"""

print()

dataFrame2 = dataFrame1.iloc[1:3, :]

print(dataFrame2)

"""

A B C D

2013-01-02 0.313371 -0.866423 0.648042 0.088910

2013-01-03 0.569949 -0.366839 -0.384350 0.130825

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을

[PYTHON/PANDAS] DataFrame 클래스 : iloc 속성을 사용해 특정 행/컬럼 데이터 구하기

■ DataFrame 클래스의 iloc 속성을 사용해 특정 행/컬럼의 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""
                   A         B         C         D
2013-01-01 -1.076450  0.098831  0.331691 -1.270272
2013-01-02 -0.698761 -0.281936  1.356855  1.439182
2013-01-03 -0.060443 -2.536983  0.474903  0.852891
2013-01-04  0.483600  1.162260 -0.438379 -0.323761
2013-01-05 -1.067515 -0.316740  0.400269  0.318582
2013-01-06 -1.215142  1.216324 -0.214613  0.780061
"""

print()

dataFrame2 = dataFrame1.iloc[[1, 2, 4], [0, 2]]

print(dataFrame2)

"""
                   A         C
2013-01-02 -0.698761  1.356855
2013-01-03 -0.060443  0.474903
2013-01-05 -1.067515  0.400269
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""

A B C D

2013-01-01 -1.076450 0.098831 0.331691 -1.270272

2013-01-02 -0.698761 -0.281936 1.356855 1.439182

2013-01-03 -0.060443 -2.536983 0.474903 0.852891

2013-01-04 0.483600 1.162260 -0.438379 -0.323761

2013-01-05 -1.067515 -0.316740 0.400269 0.318582

2013-01-06 -1.215142 1.216324 -0.214613 0.780061

"""

print()

dataFrame2 = dataFrame1.iloc[[1, 2, 4], [0, 2]]

print(dataFrame2)

"""

A C

2013-01-02 -0.698761 1.356855

2013-01-03 -0.060443 0.474903

2013-01-05 -1.067515 0.400269

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] DataFrame 클래스 : at 속성을 사용해 특정 셀 데이터 구하기

■ DataFrame 클래스의 at 속성을 사용해 특정 셀의 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""
                   A         B         C         D
2013-01-01  1.496475 -0.462460  0.239277 -0.150066
2013-01-02  0.522467 -1.208454 -0.249313  0.337069
2013-01-03 -0.058117  0.351514  2.003000 -1.487527
2013-01-04 -2.049386  0.991963 -1.148437 -0.631090
2013-01-05  0.284946  1.314614 -1.701463  1.685527
2013-01-06 -2.020866  0.165436  1.581737  0.480128
"""

print()

value = dataFrame1.at[datetimeIndex[0], "A"]

print(value)

"""
1.4964751609479943
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""

A B C D

2013-01-01 1.496475 -0.462460 0.239277 -0.150066

2013-01-02 0.522467 -1.208454 -0.249313 0.337069

2013-01-03 -0.058117 0.351514 2.003000 -1.487527

2013-01-04 -2.049386 0.991963 -1.148437 -0.631090

2013-01-05 0.284946 1.314614 -1.701463 1.685527

2013-01-06 -2.020866 0.165436 1.581737 0.480128

"""

print()

value = dataFrame1.at[datetimeIndex[0], "A"]

print(value)

"""

1.4964751609479943

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] DataFrame 클래스 : loc 속성을 사용해 특정 컬럼 데이터 구하기 3

■ DataFrame 클래스의 loc 속성을 사용해 특정 컬럼의 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""
                   A         B         C         D
2013-01-01 -0.453182 -0.861583 -0.254588 -0.361769
2013-01-02  1.215367  0.103539  0.098492  0.149869
2013-01-03  0.821661 -1.125507 -0.242997  0.911715
2013-01-04  0.642376  0.346627 -0.750569 -1.202167
2013-01-05 -1.837095 -0.145270  0.976675  0.339294
2013-01-06 -1.088314  0.103322  0.846974 -1.413636
"""

print()

dataFrame2 = dataFrame1.loc["20130102":"20130104", ["A", "B"]]

print(dataFrame2)

"""
                   A         B
2013-01-02  1.215367  0.103539
2013-01-03  0.821661 -1.125507
2013-01-04  0.642376  0.346627
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""

A B C D

2013-01-01 -0.453182 -0.861583 -0.254588 -0.361769

2013-01-02 1.215367 0.103539 0.098492 0.149869

2013-01-03 0.821661 -1.125507 -0.242997 0.911715

2013-01-04 0.642376 0.346627 -0.750569 -1.202167

2013-01-05 -1.837095 -0.145270 0.976675 0.339294

2013-01-06 -1.088314 0.103322 0.846974 -1.413636

"""

print()

dataFrame2 = dataFrame1.loc["20130102":"20130104", ["A", "B"]]

print(dataFrame2)

"""

A B

2013-01-02 1.215367 0.103539

2013-01-03 0.821661 -1.125507

2013-01-04 0.642376 0.346627

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] DataFrame 클래스 : loc 속성을 사용해 특정 컬럼 데이터 구하기 2

■ DataFrame 클래스의 loc 속성을 사용해 특정 컬럼의 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""
                   A         B         C         D
2013-01-01 -0.012239 -1.219733  0.329373 -0.727080
2013-01-02 -0.174491 -0.052405  0.713403  0.700079
2013-01-03  0.446779 -1.130175 -0.506828 -1.090990
2013-01-04 -0.150186  1.009573  0.664691  1.069907
2013-01-05  2.260466  0.023234 -1.803731  2.082104
2013-01-06 -0.082471 -0.077965  0.253575 -0.043752
"""

print()

dataFrame2 = dataFrame1.loc[:, ["A", "B"]]

print(dataFrame2)

"""
                   A         B
2013-01-01 -0.012239 -1.219733
2013-01-02 -0.174491 -0.052405
2013-01-03  0.446779 -1.130175
2013-01-04 -0.150186  1.009573
2013-01-05  2.260466  0.023234
2013-01-06 -0.082471 -0.077965
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame1 = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame1)

"""

A B C D

2013-01-01 -0.012239 -1.219733 0.329373 -0.727080

2013-01-02 -0.174491 -0.052405 0.713403 0.700079

2013-01-03 0.446779 -1.130175 -0.506828 -1.090990

2013-01-04 -0.150186 1.009573 0.664691 1.069907

2013-01-05 2.260466 0.023234 -1.803731 2.082104

2013-01-06 -0.082471 -0.077965 0.253575 -0.043752

"""

print()

dataFrame2 = dataFrame1.loc[:, ["A", "B"]]

print(dataFrame2)

"""

A B

2013-01-01 -0.012239 -1.219733

2013-01-02 -0.174491 -0.052405

2013-01-03 0.446779 -1.130175

2013-01-04 -0.150186 1.009573

2013-01-05 2.260466 0.023234

2013-01-06 -0.082471 -0.077965

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] DataFrame 클래스 : loc 속성을 사용해 첫번째 데이터 구하기

■ DataFrame 클래스의 loc 속성을 사용해 첫번째 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame)

"""
                   A         B         C         D
2013-01-01  1.158410  0.258659 -0.430055 -2.096008
2013-01-02  0.000879 -0.127080 -0.212951  1.275311
2013-01-03  1.675983 -2.314498 -1.101046 -1.161565
2013-01-04 -0.325405 -2.769847  0.648851  0.535671
2013-01-05 -2.115589 -0.763019  0.626654  0.984163
2013-01-06 -0.830564  1.661675 -0.351440 -0.423769
"""

print()

series = dataFrame.loc[datetimeIndex[0]]

print(series)

"""
A    1.158410
B    0.258659
C   -0.430055
D   -2.096008
Name: 2013-01-01 00:00:00, dtype: float64
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

dataFrame = pd.DataFrame(np.random.randn(6, 4), index = datetimeIndex, columns = list("ABCD"))

print(dataFrame)

"""

A B C D

2013-01-01 1.158410 0.258659 -0.430055 -2.096008

2013-01-02 0.000879 -0.127080 -0.212951 1.275311

2013-01-03 1.675983 -2.314498 -1.101046 -1.161565

2013-01-04 -0.325405 -2.769847 0.648851 0.535671

2013-01-05 -2.115589 -0.763019 0.626654 0.984163

2013-01-06 -0.830564 1.661675 -0.351440 -0.423769

"""

print()

series = dataFrame.loc[datetimeIndex[0]]

print(series)

"""

A 1.158410

B 0.258659

C -0.430055

D -2.096008

Name: 2013-01-01 00:00:00, dtype: float64

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을

[PYTHON/PANDAS] DataFrame 클래스 : sort_index 메소드에서 axis/ascending 인자를 사용해 컬럼 축 기준 컬럼명 정렬하기

■ DataFrame 클래스의 sort_index 메소드에서 axis/ascending 인자를 사용해 컬럼 축 기준 컬럼명을 정렬하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

dataFrame1 = pd.DataFrame(
    {
        "A" : 1.0,
        "B" : pd.Timestamp("20130102"),
        "C" : pd.Series(1, index = list(range(4)), dtype = "float32"),
        "D" : np.array([3] * 4, dtype = "int32"),
        "E" : pd.Categorical(["test", "train", "test", "train"]),
        "F" : "foo"
    }
)

print(dataFrame1)

"""
     A          B    C  D      E    F
0  1.0 2013-01-02  1.0  3   test  foo
1  1.0 2013-01-02  1.0  3  train  foo
2  1.0 2013-01-02  1.0  3   test  foo
3  1.0 2013-01-02  1.0  3  train  foo
"""

print()

dataFrame2 = dataFrame1.sort_index(axis = 1, ascending = False) # axis : 0(행 기준), 1(열 기준)

print(dataFrame2)

"""
     F      E  D    C          B    A
0  foo   test  3  1.0 2013-01-02  1.0
1  foo  train  3  1.0 2013-01-02  1.0
2  foo   test  3  1.0 2013-01-02  1.0
3  foo  train  3  1.0 2013-01-02  1.0
"""

import pandas as pd

import numpy as np

dataFrame1 = pd.DataFrame(

{

"A" : 1.0,

"B" : pd.Timestamp("20130102"),

"C" : pd.Series(1, index = list(range(4)), dtype = "float32"),

"D" : np.array([3] * 4, dtype = "int32"),

"E" : pd.Categorical(["test", "train", "test", "train"]),

"F" : "foo"

}

)

print(dataFrame1)

"""

A B C D E F

0 1.0 2013-01-02 1.0 3 test foo

1 1.0 2013-01-02 1.0 3 train foo

2 1.0 2013-01-02 1.0 3 test foo

3 1.0 2013-01-02 1.0 3 train foo

"""

print()

dataFrame2 = dataFrame1.sort_index(axis = 1, ascending = False) # axis : 0(행 기준), 1(열 기준)

print(dataFrame2)

"""

F E D C B A

0 foo test 3 1.0 2013-01-02 1.0

1 foo train 3 1.0 2013-01-02 1.0

2 foo test 3 1.0 2013-01-02 1.0

3 foo train 3 1.0 2013-01-02 1.0

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※

[PYTHON/PANDAS] DataFrame 클래스 : T 속성을 사용해 데이터 전치하기

■ DataFrame 클래스의 T 속성을 사용해 데이터를 전치하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

dataFrame = pd.DataFrame(
    {
        "A" : 1.0,
        "B" : pd.Timestamp("20130102"),
        "C" : pd.Series(1, index = list(range(4)), dtype = "float32"),
        "D" : np.array([3] * 4, dtype = "int32"),
        "E" : pd.Categorical(["test", "train", "test", "train"]),
        "F" : "foo"
    }
)

print(dataFrame)

"""
     A          B    C  D      E    F
0  1.0 2013-01-02  1.0  3   test  foo
1  1.0 2013-01-02  1.0  3  train  foo
2  1.0 2013-01-02  1.0  3   test  foo
3  1.0 2013-01-02  1.0  3  train  foo
"""

print()

print(dataFrame.T)

"""
                     0                    1                    2                    3
A                  1.0                  1.0                  1.0                  1.0
B  2013-01-02 00:00:00  2013-01-02 00:00:00  2013-01-02 00:00:00  2013-01-02 00:00:00
C                  1.0                  1.0                  1.0                  1.0
D                    3                    3                    3                    3
E                 test                train                 test                train
F                  foo                  foo                  foo                  foo
"""

import pandas as pd

import numpy as np

dataFrame = pd.DataFrame(

{

"A" : 1.0,

"B" : pd.Timestamp("20130102"),

"C" : pd.Series(1, index = list(range(4)), dtype = "float32"),

"D" : np.array([3] * 4, dtype = "int32"),

"E" : pd.Categorical(["test", "train", "test", "train"]),

"F" : "foo"

}

)

print(dataFrame)

"""

A B C D E F

0 1.0 2013-01-02 1.0 3 test foo

1 1.0 2013-01-02 1.0 3 train foo

2 1.0 2013-01-02 1.0 3 test foo

3 1.0 2013-01-02 1.0 3 train foo

"""

print()

print(dataFrame.T)

"""

0 1 2 3

A 1.0 1.0 1.0 1.0

B 2013-01-02 00:00:00 2013-01-02 00:00:00 2013-01-02 00:00:00 2013-01-02 00:00:00

C 1.0 1.0 1.0 1.0

D 3 3 3 3

E test train test train

F foo foo foo foo

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을 실행했다.

[PYTHON/PANDAS] DataFrame 클래스 : to_numpy 메소드를 사용해 ndarray 객체 구하기

■ DataFrame 클래스의 to_numpy 메소드를 사용해 ndarray 객체를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

dataFrame = pd.DataFrame(
    {
        "A" : 1.0,
        "B" : pd.Timestamp("20130102"),
        "C" : pd.Series(1, index = list(range(4)), dtype = "float32"),
        "D" : np.array([3] * 4, dtype = "int32"),
        "E" : pd.Categorical(["test", "train", "test", "train"]),
        "F" : "foo"
    }
)

print(dataFrame)

"""
     A          B    C  D      E    F
0  1.0 2013-01-02  1.0  3   test  foo
1  1.0 2013-01-02  1.0  3  train  foo
2  1.0 2013-01-02  1.0  3   test  foo
3  1.0 2013-01-02  1.0  3  train  foo
"""

ndarray1 = dataFrame.to_numpy()

print(ndarray1)

"""
[[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo']
 [1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']
 [1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo']
 [1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']]
"""

import pandas as pd

import numpy as np

dataFrame = pd.DataFrame(

{

"A" : 1.0,

"B" : pd.Timestamp("20130102"),

"C" : pd.Series(1, index = list(range(4)), dtype = "float32"),

"D" : np.array([3] * 4, dtype = "int32"),

"E" : pd.Categorical(["test", "train", "test", "train"]),

"F" : "foo"

}

)

print(dataFrame)

"""

A B C D E F

0 1.0 2013-01-02 1.0 3 test foo

1 1.0 2013-01-02 1.0 3 train foo

2 1.0 2013-01-02 1.0 3 test foo

3 1.0 2013-01-02 1.0 3 train foo

"""

ndarray1 = dataFrame.to_numpy()

print(ndarray1)

"""

[[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo']

[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']

[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo']

[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']]

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을

[PYTHON/PANDAS] DataFrame 클래스 : 생성자를 사용해 다양한 데이터 타입의 컬럼을 갖는 DataFrame 객체 만들기

■ DataFrame 클래스의 생성자를 사용해 다양한 데이터 타입의 컬럼을 갖는 DataFrame 객체를 만드는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

dataFrame = pd.DataFrame(
    {
        "A" : 1.0,
        "B" : pd.Timestamp("20130102"),
        "C" : pd.Series(1, index = list(range(4)), dtype = "float32"),
        "D" : np.array([3] * 4, dtype = "int32"),
        "E" : pd.Categorical(["test", "train", "test", "train"]),
        "F" : "foo"
    }
)

print(dataFrame)

"""
     A          B    C  D      E    F
0  1.0 2013-01-02  1.0  3   test  foo
1  1.0 2013-01-02  1.0  3  train  foo
2  1.0 2013-01-02  1.0  3   test  foo
3  1.0 2013-01-02  1.0  3  train  foo
"""

import pandas as pd

import numpy as np

dataFrame = pd.DataFrame(

{

"A" : 1.0,

"B" : pd.Timestamp("20130102"),

"C" : pd.Series(1, index = list(range(4)), dtype = "float32"),

"D" : np.array([3] * 4, dtype = "int32"),

"E" : pd.Categorical(["test", "train", "test", "train"]),

"F" : "foo"

}

)

print(dataFrame)

"""

A B C D E F

0 1.0 2013-01-02 1.0 3 test foo

1 1.0 2013-01-02 1.0 3 train foo

2 1.0 2013-01-02 1.0 3 test foo

3 1.0 2013-01-02 1.0 3 train foo

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※

[PYTHON/PANDAS] Categorical 클래스 : 생성자를 사용해 Categorical 객체 만들기

■ Categorical 클래스의 생성자를 사용해 Categorical 객체를 만드는 방법을 보여준다. ▶ main.py


import pandas as pd

categorical = pd.Categorical(["test", "train", "test", "train"])

print(categorical)

"""
['test', 'train', 'test', 'train']
Categories (2, object): ['test', 'train']
"""

import pandas as pd

categorical = pd.Categorical(["test", "train", "test", "train"])

print(categorical)

"""

['test', 'train', 'test', 'train']

Categories (2, object): ['test', 'train']

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을 실행했다.

[PYTHON/PANDAS] DataFrame 클래스 : 생성자에서 index/columns 인자를 사용해 DataFrame 객체 만들기

■ DataFrame 클래스의 생성자에서 index/columns 인자를 사용해 DataFrame 객체를 만드는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

datetimeIndex = pd.date_range("20130101", periods = 6)

ndarray1 = np.random.randn(6, 4) # 6행 4열 배열

dataFrame = pd.DataFrame(ndarray1, index = datetimeIndex, columns = list("ABCD"))

print(dataFrame)

"""
                   A         B         C         D
2013-01-01  0.379704  0.640741 -2.602984 -1.576275
2013-01-02 -1.400774  1.519939  0.563043 -0.498297
2013-01-03  1.190896  0.389969 -1.515588  0.745648
2013-01-04  0.175308 -0.416092 -0.360387  0.647819
2013-01-05 -0.187323  0.036568  0.392615 -1.870158
2013-01-06  1.161280 -1.250679  0.877178  1.321106
"""

import pandas as pd

import numpy as np

datetimeIndex = pd.date_range("20130101", periods = 6)

ndarray1 = np.random.randn(6, 4) # 6행 4열 배열

dataFrame = pd.DataFrame(ndarray1, index = datetimeIndex, columns = list("ABCD"))

print(dataFrame)

"""

A B C D

2013-01-01 0.379704 0.640741 -2.602984 -1.576275

2013-01-02 -1.400774 1.519939 0.563043 -0.498297

2013-01-03 1.190896 0.389969 -1.515588 0.745648

2013-01-04 0.175308 -0.416092 -0.360387 0.647819

2013-01-05 -0.187323 0.036568 0.392615 -1.870158

2013-01-06 1.161280 -1.250679 0.877178 1.321106

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] date_range 함수 : periods 인자를 사용해 DatetimeIndex 객체 만들기

■ date_range 함수의 periods 인자를 사용해 DatetimeIndex 객체를 만드는 방법을 보여준다. ▶ main.py


import pandas as pd

datetimeIndex = pd.date_range("20130101", periods = 6)

print(datetimeIndex)

"""
DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
               '2013-01-05', '2013-01-06'],
              dtype='datetime64[ns]', freq='D')
"""

import pandas as pd

datetimeIndex = pd.date_range("20130101", periods = 6)

print(datetimeIndex)

"""

DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',

'2013-01-05', '2013-01-06'],

dtype='datetime64[ns]', freq='D')

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을

[PYTHON/PANDAS] Series 클래스 : 생성자를 사용해 Series 객체 만들기

■ Series 클래스의 생성자를 사용해 Series 객체를 만드는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

series = pd.Series([1, 3, 5, np.nan, 6, 8])

print(series)

"""
0    1.0
1    3.0
2    5.0
3    NaN
4    6.0
5    8.0
dtype: float64
"""

import pandas as pd

import numpy as np

series = pd.Series([1, 3, 5, np.nan, 6, 8])

print(series)

"""

0 1.0

1 3.0

2 5.0

3 NaN

4 6.0

5 8.0

dtype: float64

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을 실행했다.

[PYTHON/PANDAS] DataFrame 클래스 : to_stata 메소드를 사용해 STATA 데이타 파일 생성하기

■ DataFrame 클래스의 to_stata 메소드를 사용해 STATA 데이타 파일을 생성하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_stata("data1.dta")

dataFrame.to_stata("tips2.dta")

import pandas as pd

dataFrame = pd.read_stata("data1.dta")

dataFrame.to_stata("tips2.dta")

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] read_stata 함수 : STATA 데이터 파일 로드하기

■ read_stata 함수를 사용해 STATA 데이터 파일을 로드하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_stata("data.dta")

import pandas as pd

dataFrame = pd.read_stata("data.dta")

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을 실행했다.

[PYTHON/PANDAS] DataFrameGroupBy 클래스 : transform 메소드를 사용해 그룹별 데이터 집계하기 2

■ DataFrameGroupBy 클래스의 transform 메소드를 사용해 그룹별 데이터를 집계하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

dataFrame1 = pd.DataFrame({"key" : ["A", "B", "C", "D"], "value" : np.random.randn(4)})
dataFrame2 = pd.DataFrame({"key" : ["B", "D", "D", "E"], "value" : np.random.randn(4)})

dataFrame3 = dataFrame1.merge(dataFrame2, on = ["key"], how = "outer")

dataFrameGroupBy = dataFrame3.groupby("key")

series1 = dataFrameGroupBy.transform("mean" )["value_x"]
series2 = dataFrameGroupBy.transform("mean" )["value_y"]
series3 = dataFrameGroupBy.transform("sum"  )["value_x"]
series4 = dataFrameGroupBy.transform("sum"  )["value_y"]
series5 = dataFrameGroupBy.transform("count")["value_x"]
series6 = dataFrameGroupBy.transform("count")["value_y"]

dataFrame3 = pd.DataFrame(
    {
        'mean_x'  : series1,
        'mean_y'  : series2,
        'sum_x'   : series3,
        'sum_y'   : series4,
        'count_x' : series5,
        'count_y' : series6
    }
)

print(dataFrame3)

"""
     mean_x    mean_y     sum_x     sum_y  count_x  count_y
0  1.054826       NaN  1.054826  0.000000        1        0
1  0.780643  0.105718  0.780643  0.105718        1        1
2 -0.780831       NaN -0.780831  0.000000        1        0
3 -0.709413 -1.636002 -1.418825 -3.272004        2        2
4 -0.709413 -1.636002 -1.418825 -3.272004        2        2
5       NaN  1.348015  0.000000  1.348015        0        1
"""

import pandas as pd

import numpy as np

dataFrame1 = pd.DataFrame({"key" : ["A", "B", "C", "D"], "value" : np.random.randn(4)})

dataFrame2 = pd.DataFrame({"key" : ["B", "D", "D", "E"], "value" : np.random.randn(4)})

dataFrame3 = dataFrame1.merge(dataFrame2, on = ["key"], how = "outer")

dataFrameGroupBy = dataFrame3.groupby("key")

series1 = dataFrameGroupBy.transform("mean" )["value_x"]

series2 = dataFrameGroupBy.transform("mean" )["value_y"]

series3 = dataFrameGroupBy.transform("sum" )["value_x"]

series4 = dataFrameGroupBy.transform("sum" )["value_y"]

series5 = dataFrameGroupBy.transform("count")["value_x"]

series6 = dataFrameGroupBy.transform("count")["value_y"]

dataFrame3 = pd.DataFrame(

{

'mean_x' : series1,

'mean_y' : series2,

'sum_x' : series3,

'sum_y' : series4,

'count_x' : series5,

'count_y' : series6

}

)

print(dataFrame3)

"""

mean_x mean_y sum_x sum_y count_x count_y

0 1.054826 NaN 1.054826 0.000000 1 0

1 0.780643 0.105718 0.780643 0.105718 1 1

2 -0.780831 NaN -0.780831 0.000000 1 0

3 -0.709413 -1.636002 -1.418825 -3.272004 2 2

4 -0.709413 -1.636002 -1.418825 -3.272004 2 2

5 NaN 1.348015 0.000000 1.348015 0 1

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을

[PYTHON/PANDAS] DataFrameGroupBy 클래스 : agg 메소드를 사용해 그룹 데이터 평균/합계/수 집계하기

■ DataFrameGroupBy 클래스의 agg 메소드를 사용해 그룹 데이터의 평균/합계/수를 집계하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

dataFrame1 = pd.DataFrame({"key" : ["A", "B", "C", "D"], "value" : np.random.randn(4)})
dataFrame2 = pd.DataFrame({"key" : ["B", "D", "D", "E"], "value" : np.random.randn(4)})

dataFrame3 = dataFrame1.merge(dataFrame2, on = ["key"], how = "outer")

dataFrameGroupBy = dataFrame3.groupby("key")

dataFrame4 = dataFrameGroupBy.agg(["mean", "sum", "count"])

print(dataFrame4)

"""
      value_x                   value_y
         mean       sum count      mean       sum count
key
A    0.052300  0.052300     1       NaN  0.000000     0
B   -0.128339 -0.128339     1  0.874078  0.874078     1
C    0.868257  0.868257     1       NaN  0.000000     0
D    0.095844  0.191688     2 -0.356354 -0.712709     2
E         NaN  0.000000     0  0.843800  0.843800     1
"""

import pandas as pd

import numpy as np

dataFrame1 = pd.DataFrame({"key" : ["A", "B", "C", "D"], "value" : np.random.randn(4)})

dataFrame2 = pd.DataFrame({"key" : ["B", "D", "D", "E"], "value" : np.random.randn(4)})

dataFrame3 = dataFrame1.merge(dataFrame2, on = ["key"], how = "outer")

dataFrameGroupBy = dataFrame3.groupby("key")

dataFrame4 = dataFrameGroupBy.agg(["mean", "sum", "count"])

print(dataFrame4)

"""

value_x value_y

mean sum count mean sum count

key

A 0.052300 0.052300 1 NaN 0.000000 0

B -0.128339 -0.128339 1 0.874078 0.874078 1

C 0.868257 0.868257 1 NaN 0.000000 0

D 0.095844 0.191688 2 -0.356354 -0.712709 2

E NaN 0.000000 0 0.843800 0.843800 1

"""

▶ requirements.txt


numpy==2.1.2
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.2

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas

[PYTHON/PANDAS] DataFrameGroupBy 클래스 : transform 메소드에서 커스텀 집계 함수 설정하기

■ DataFrameGroupBy 클래스의 transform 메소드에서 커스텀 집계 함수를 설정하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

dataFrame1 = pd.DataFrame({"key" : ["A", "B", "C", "D"], "value" : np.random.randn(4)})
dataFrame2 = pd.DataFrame({"key" : ["B", "D", "D", "E"], "value" : np.random.randn(4)})

dataFrame3 = dataFrame1.merge(dataFrame2, on = ["key"], how = "outer")

dataFrameGroupBy = dataFrame3.groupby("key")

def customFunction(x):
    return x - x.mean()

dataFrame4 = dataFrameGroupBy.transform(customFunction)

print(dataFrame4)

"""
   value_x   value_y
0      0.0       NaN
1      0.0  0.000000
2      0.0       NaN
3      0.0  0.993518
4      0.0 -0.993518
5      NaN  0.000000
"""

import pandas as pd

import numpy as np

dataFrame1 = pd.DataFrame({"key" : ["A", "B", "C", "D"], "value" : np.random.randn(4)})

dataFrame2 = pd.DataFrame({"key" : ["B", "D", "D", "E"], "value" : np.random.randn(4)})

dataFrame3 = dataFrame1.merge(dataFrame2, on = ["key"], how = "outer")

dataFrameGroupBy = dataFrame3.groupby("key")

def customFunction(x):

return x - x.mean()

dataFrame4 = dataFrameGroupBy.transform(customFunction)

print(dataFrame4)

"""

value_x value_y

0 0.0 NaN

1 0.0 0.000000

2 0.0 NaN

3 0.0 0.993518

4 0.0 -0.993518

5 NaN 0.000000

"""

▶ requirements.txt


numpy==2.1.3
pandas==2.2.3
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

numpy==2.1.3

pandas==2.2.3

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install pandas 명령을