10월 2024 - icodebroker

[PYTHON/PANDAS] DataFrame 클래스 : groupby 메소드를 사용해 그룹 데이터 평균 계산하기

■ DataFrame 클래스의 groupby 메소드를 사용해 그룹 데이터 평균을 계산하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

dataFrame1 = pd.DataFrame(
    {
        "v1"  : [1, 3, 5, 7, 8, 3, 5, np.nan, 4, 5, 7, 9],
        "v2"  : [11, 33, 55, 77, 88, 33, 55, np.nan, 44, 55, 77, 99],
        "by1" : ["red", "blue", 1, 2, np.nan, "big", 1, 2, "red", 1, np.nan, 12],
        "by2" : ["wet", "dry", 99, 95, np.nan, "damp", 95, 99, "red", 99, np.nan, np.nan]
    }
)

dataFrameGroupBy1 = dataFrame1.groupby(["by1", "by2"])

dataFrameGroupBy2 = dataFrameGroupBy1[["v1", "v2"]]

dataFrame2 = dataFrameGroupBy2.mean()

print(dataFrame2)

"""
            v1    v2
by1  by2
1    95    5.0  55.0
     99    5.0  55.0
2    95    7.0  77.0
     99    NaN   NaN
big  damp  3.0  33.0
blue dry   3.0  33.0
red  red   4.0  44.0
     wet   1.0  11.0
"""

import pandas as pd

import numpy as np

dataFrame1 = pd.DataFrame(

{

"v1" : [1, 3, 5, 7, 8, 3, 5, np.nan, 4, 5, 7, 9],

"v2" : [11, 33, 55, 77, 88, 33, 55, np.nan, 44, 55, 77, 99],

"by1" : ["red", "blue", 1, 2, np.nan, "big", 1, 2, "red", 1, np.nan, 12],

"by2" : ["wet", "dry", 99, 95, np.nan, "damp", 95, 99, "red", 99, np.nan, np.nan]

}

)

dataFrameGroupBy1 = dataFrame1.groupby(["by1", "by2"])

dataFrameGroupBy2 = dataFrameGroupBy1[["v1", "v2"]]

dataFrame2 = dataFrameGroupBy2.mean()

print(dataFrame2)

"""

v1 v2

by1 by2

1 95 5.0 55.0

99 5.0 55.0

2 95 7.0 77.0

99 NaN NaN

big damp 3.0 33.0

blue dry 3.0 33.0

red red 4.0 44.0

wet 1.0 11.0

"""

▶ 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 : iloc 속성에서 np.r_ 변수를 사용해 임의 영역 데이터 구하기

■ DataFrame 클래스의 iloc 속성에서 np.r_ 변수를 사용해 임의 영역의 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

stringList = list("abcdefg")

count = 30

columnList = stringList + np.arange(len(stringList), count).tolist()

dataFrame1 = pd.DataFrame(np.random.randn(count, count), columns = columnList)

dataFrame2 = dataFrame1.iloc[:, np.r_[:10, 24:30]]

print(dataFrame2)

import pandas as pd

import numpy as np

stringList = list("abcdefg")

count = 30

columnList = stringList + np.arange(len(stringList), count).tolist()

dataFrame1 = pd.DataFrame(np.random.randn(count, count), columns = columnList)

dataFrame2 = dataFrame1.iloc[:, np.r_[:10, 24:30]]

print(dataFrame2)

▶ 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

[PYTHON/PANDAS] DataFrame 클래스 : 생성자에서 columns 인자를 사용해 난수 값을 갖는 DataFrame 객체 만들기

■ DataFrame 클래스의 생성자에서 columns 인자를 사용해 난수 값을 갖는 DataFrame 객체를 만드는 방법을 보여준다. ▶ main.py


import pandas as pd
import numpy  as np

dataFrame = pd.DataFrame(np.random.randn(10, 3), columns = list("abc"))

print(dataFrame)

"""
          a         b         c
0 -1.428998 -0.991100 -0.602438
1  0.552123 -1.917513  0.491549
2  0.641742 -0.086333  0.423445
3 -0.214374 -2.805150  0.296208
4 -0.111616 -0.736000 -1.146009
5  0.545357 -0.012481  0.820069
6 -1.414424  0.487061  0.803664
7  1.705942 -2.167608 -1.233166
8 -0.933875  0.765882  0.180895
9 -2.009916 -0.469145 -0.054593
"""

import pandas as pd

import numpy as np

dataFrame = pd.DataFrame(np.random.randn(10, 3), columns = list("abc"))

print(dataFrame)

"""

a b c

0 -1.428998 -0.991100 -0.602438

1 0.552123 -1.917513 0.491549

2 0.641742 -0.086333 0.423445

3 -0.214374 -2.805150 0.296208

4 -0.111616 -0.736000 -1.146009

5 0.545357 -0.012481 0.820069

6 -1.414424 0.487061 0.803664

7 1.705942 -2.167608 -1.233166

8 -0.933875 0.765882 0.180895

9 -2.009916 -0.469145 -0.054593

"""

▶ 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] DataFrameGroupBy 클래스 : agg 메소드를 사용해 그룹 데이터 평균/합계 집계하기

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


import pandas as pd

dataFrame1 = pd.DataFrame(
    {
        "지역" : ["A", "A", "B", "B", "B", "C"],
        "비용" : [10, 20, 30, 40, 50, 60],
        "수입" : [100, 200, 300, 400, 500, 600]
    }
)

print(dataFrame1)

"""
  지역  비용  수입
0  A    10    100
1  A    20    200
2  B    30    300
3  B    40    400
4  B    50    500
5  C    60    600
"""

print()

dataFrameGroupBy = dataFrame1.groupby("지역")

dataFrame2 = dataFrameGroupBy.agg(
    {
        "비용" : "mean",
        "수입" : ["mean", "sum"]
    }
)

print(dataFrame2)

"""
      비용  수입
      mean  mean   sum
지역
A     15.0  150.0   300
B     40.0  400.0  1200
C     60.0  600.0   600
"""

import pandas as pd

dataFrame1 = pd.DataFrame(

{

"지역" : ["A", "A", "B", "B", "B", "C"],

"비용" : [10, 20, 30, 40, 50, 60],

"수입" : [100, 200, 300, 400, 500, 600]

}

)

print(dataFrame1)

"""

지역 비용 수입

0 A 10 100

1 A 20 200

2 B 30 300

3 B 40 400

4 B 50 500

5 C 60 600

"""

print()

dataFrameGroupBy = dataFrame1.groupby("지역")

dataFrame2 = dataFrameGroupBy.agg(

{

"비용" : "mean",

"수입" : ["mean", "sum"]

}

)

print(dataFrame2)

"""

비용 수입

mean mean sum

지역

A 15.0 150.0 300

B 40.0 400.0 1200

C 60.0 600.0 600

"""

▶ 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 : assign 메소드를 사용해 신규 컬럼 추가하기

■ DataFrame 클래스의 assign 메소드를 사용해 신규 컬럼을 추가하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame1 = pd.DataFrame(
    {
        'a' : [10, 20, 30],
        'b' : [ 1,  2,  3]
    }
)

dataFrame2 = dataFrame1.assign(
    c = dataFrame1["a"] - dataFrame1["b"],
    d = dataFrame1["a"] + dataFrame1["b"]
)

print(dataFrame2)

"""
    a  b   c   d
0  10  1   9  11
1  20  2  18  22
2  30  3  27  33
"""

import pandas as pd

dataFrame1 = pd.DataFrame(

{

'a' : [10, 20, 30],

'b' : [ 1, 2, 3]

}

)

dataFrame2 = dataFrame1.assign(

c = dataFrame1["a"] - dataFrame1["b"],

d = dataFrame1["a"] + dataFrame1["b"]

)

print(dataFrame2)

"""

a b c d

0 10 1 9 11

1 20 2 18 22

2 30 3 27 33

"""

▶ 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 : sample 메소드에서 frac 인자를 사용해 샘플 데이터 구하기

■ DataFrame 클래스의 sample 메소드에서 frac 인자를 사용해 샘플 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1.sample(frac = 0.01)

print(dataFrame2)

"""
     PassengerId  Survived  Pclass                                  Name     Sex   Age  SibSp  Parch      Ticket     Fare Cabin Embarked
113          114         0       3                Jussila, Miss Katriina  female  20.0      1      0        4136   9.8250   NaN        S
489          490         1       3  Coutts, Master Eden Leslie "Neville"    male   9.0      1      1  C.A. 37671  15.9000   NaN        S
425          426         0       3                Wiseman, Mr. Phillippe    male   NaN      0      0  A/4. 34244   7.2500   NaN        S
454          455         0       3                   Peduzzi, Mr. Joseph    male   NaN      0      0    A/5 2817   8.0500   NaN        S
322          323         1       2              Slayter, Miss Hilda Mary  female  30.0      0      0      234818  12.3500   NaN        Q
838          839         1       3                       Chip, Mr. Chang    male  32.0      0      0        1601  56.4958   NaN        S
159          160         0       3             Sage, Master Thomas Henry    male   NaN      8      2    CA. 2343  69.5500   NaN        S
825          826         0       3                       Flynn, Mr. John    male   NaN      0      0      368323   6.9500   NaN        Q
114          115         0       3                  Attalah, Miss Malake  female  17.0      0      0        2627  14.4583   NaN        C
"""

import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1.sample(frac = 0.01)

print(dataFrame2)

"""

PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked

113 114 0 3 Jussila, Miss Katriina female 20.0 1 0 4136 9.8250 NaN S

489 490 1 3 Coutts, Master Eden Leslie "Neville" male 9.0 1 1 C.A. 37671 15.9000 NaN S

425 426 0 3 Wiseman, Mr. Phillippe male NaN 0 0 A/4. 34244 7.2500 NaN S

454 455 0 3 Peduzzi, Mr. Joseph male NaN 0 0 A/5 2817 8.0500 NaN S

322 323 1 2 Slayter, Miss Hilda Mary female 30.0 0 0 234818 12.3500 NaN Q

838 839 1 3 Chip, Mr. Chang male 32.0 0 0 1601 56.4958 NaN S

159 160 0 3 Sage, Master Thomas Henry male NaN 8 2 CA. 2343 69.5500 NaN S

825 826 0 3 Flynn, Mr. John male NaN 0 0 368323 6.9500 NaN Q

114 115 0 3 Attalah, Miss Malake female 17.0 0 0 2627 14.4583 NaN C

"""

▶ 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 : sample 메소드에서 n 인자를 사용해 샘플 데이터 구하기

■ DataFrame 클래스의 sample 메소드에서 n 인자를 사용해 샘플 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1.sample(n = 10)

print(dataFrame2)

"""
     PassengerId  Survived  Pclass                                   Name     Sex   Age  SibSp  Parch    Ticket      Fare Cabin Embarked
360          361         0       3                     Skoog, Mr. Wilhelm    male  40.0      1      4    347088   27.9000   NaN        S
109          110         1       3                     Moran, Miss Bertha  female   NaN      1      0    371110   24.1500   NaN        Q
752          753         0       3       Vande Velde, Mr. Johannes Joseph    male  33.0      0      0    345780    9.5000   NaN        S
537          538         1       1                     LeRoy, Miss Bertha  female  30.0      0      0  PC 17761  106.4250   NaN        C
263          264         0       1                  Harrison, Mr. William    male  40.0      0      0    112059    0.0000   B94        S
858          859         1       3  Baclini, Mrs. Solomon (Latifa Qurban)  female  24.0      0      3      2666   19.2583   NaN        C
597          598         0       3                    Johnson, Mr. Alfred    male  49.0      0      0      LINE    0.0000   NaN        S
454          455         0       3                    Peduzzi, Mr. Joseph    male   NaN      0      0  A/5 2817    8.0500   NaN        S
595          596         0       3            Van Impe, Mr. Jean Baptiste    male  36.0      1      1    345773   24.1500   NaN        S
264          265         0       3                      Henry, Miss Delia  female   NaN      0      0    382649    7.7500   NaN        Q
"""

import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1.sample(n = 10)

print(dataFrame2)

"""

PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked

360 361 0 3 Skoog, Mr. Wilhelm male 40.0 1 4 347088 27.9000 NaN S

109 110 1 3 Moran, Miss Bertha female NaN 1 0 371110 24.1500 NaN Q

752 753 0 3 Vande Velde, Mr. Johannes Joseph male 33.0 0 0 345780 9.5000 NaN S

537 538 1 1 LeRoy, Miss Bertha female 30.0 0 0 PC 17761 106.4250 NaN C

263 264 0 1 Harrison, Mr. William male 40.0 0 0 112059 0.0000 B94 S

858 859 1 3 Baclini, Mrs. Solomon (Latifa Qurban) female 24.0 0 3 2666 19.2583 NaN C

597 598 0 3 Johnson, Mr. Alfred male 49.0 0 0 LINE 0.0000 NaN S

454 455 0 3 Peduzzi, Mr. Joseph male NaN 0 0 A/5 2817 8.0500 NaN S

595 596 0 3 Van Impe, Mr. Jean Baptiste male 36.0 1 1 345773 24.1500 NaN S

264 265 0 3 Henry, Miss Delia female NaN 0 0 382649 7.7500 NaN Q

"""

▶ 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] Series 클래스 : drop_duplicates 메소드를 사용해 중복 값 제외한 데이터 구하기 2

■ Series 클래스의 drop_duplicates 메소드를 사용해 중복 값을 제외한 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame[["Sex", "SibSp"]]

series2 = series1.drop_duplicates()

print(series2)

"""
        Sex  SibSp
0      male      1
1    female      1
2    female      0
4      male      0
7      male      3
16     male      4
24   female      3
38   female      2
48     male      2
59     male      5
68   female      4
71   female      5
159    male      8
180  female      8
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame[["Sex", "SibSp"]]

series2 = series1.drop_duplicates()

print(series2)

"""

Sex SibSp

0 male 1

1 female 1

2 female 0

4 male 0

7 male 3

16 male 4

24 female 3

38 female 2

48 male 2

59 male 5

68 female 4

71 female 5

159 male 8

180 female 8

"""

▶ 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] Series 클래스 : drop_duplicates 메소드를 사용해 중복 값 제외한 데이터 구하기 1

■ Series 클래스의 drop_duplicates 메소드를 사용해 중복 값을 제외한 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Sex"]

series2 = series1.drop_duplicates()

print(series2)

"""
0    male
1    female
Name: Sex, dtype: object
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Sex"]

series2 = series1.drop_duplicates()

print(series2)

"""

0 male

1 female

Name: Sex, dtype: object

"""

▶ 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 : drop 메소드를 사용해 특정 컬럼 삭제하기

■ DataFrame 클래스의 drop 메소드를 사용해 특정 컬럼을 삭제하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

print(dataFrame1)

"""
     PassengerId  Survived  Pclass                                               Name     Sex   Age  SibSp  Parch            Ticket     Fare Cabin Embarked
0              1         0       3                            Braund, Mr. Owen Harris    male  22.0      1      0         A/5 21171   7.2500   NaN        S
1              2         1       1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1      0          PC 17599  71.2833   C85        C
2              3         1       3                              Heikkinen, Miss Laina  female  26.0      0      0  STON/O2. 3101282   7.9250   NaN        S
3              4         1       1       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1      0            113803  53.1000  C123        S
4              5         0       3                           Allen, Mr. William Henry    male  35.0      0      0            373450   8.0500   NaN        S
..           ...       ...     ...                                                ...     ...   ...    ...    ...               ...      ...   ...      ...
886          887         0       2                              Montvila, Rev. Juozas    male  27.0      0      0            211536  13.0000   NaN        S
887          888         1       1                        Graham, Miss Margaret Edith  female  19.0      0      0            112053  30.0000   B42        S
888          889         0       3            Johnston, Miss Catherine Helen "Carrie"  female   NaN      1      2        W./C. 6607  23.4500   NaN        S
889          890         1       1                              Behr, Mr. Karl Howell    male  26.0      0      0            111369  30.0000  C148        C
890          891         0       3                                Dooley, Mr. Patrick    male  32.0      0      0            370376   7.7500   NaN        Q

[891 rows x 12 columns]
"""

print()

dataFrame2 = dataFrame1.drop(["Cabin", "Embarked"], axis = 1) # axis : 0(행), 1(컬럼)

print(dataFrame2)

"""
     PassengerId  Survived  Pclass                                               Name     Sex   Age  SibSp  Parch            Ticket     Fare
0              1         0       3                            Braund, Mr. Owen Harris    male  22.0      1      0         A/5 21171   7.2500
1              2         1       1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1      0          PC 17599  71.2833
2              3         1       3                              Heikkinen, Miss Laina  female  26.0      0      0  STON/O2. 3101282   7.9250
3              4         1       1       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1      0            113803  53.1000
4              5         0       3                           Allen, Mr. William Henry    male  35.0      0      0            373450   8.0500
..           ...       ...     ...                                                ...     ...   ...    ...    ...               ...      ...
886          887         0       2                              Montvila, Rev. Juozas    male  27.0      0      0            211536  13.0000
887          888         1       1                        Graham, Miss Margaret Edith  female  19.0      0      0            112053  30.0000
888          889         0       3            Johnston, Miss Catherine Helen "Carrie"  female   NaN      1      2        W./C. 6607  23.4500
889          890         1       1                              Behr, Mr. Karl Howell    male  26.0      0      0            111369  30.0000
890          891         0       3                                Dooley, Mr. Patrick    male  32.0      0      0            370376   7.7500

[891 rows x 10 columns]
"""

import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

print(dataFrame1)

"""

PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked

0 1 0 3 Braund, Mr. Owen Harris male 22.0 1 0 A/5 21171 7.2500 NaN S

1 2 1 1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 0 PC 17599 71.2833 C85 C

2 3 1 3 Heikkinen, Miss Laina female 26.0 0 0 STON/O2. 3101282 7.9250 NaN S

3 4 1 1 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 0 113803 53.1000 C123 S

4 5 0 3 Allen, Mr. William Henry male 35.0 0 0 373450 8.0500 NaN S

.. ... ... ... ... ... ... ... ... ... ... ... ...

886 887 0 2 Montvila, Rev. Juozas male 27.0 0 0 211536 13.0000 NaN S

887 888 1 1 Graham, Miss Margaret Edith female 19.0 0 0 112053 30.0000 B42 S

888 889 0 3 Johnston, Miss Catherine Helen "Carrie" female NaN 1 2 W./C. 6607 23.4500 NaN S

889 890 1 1 Behr, Mr. Karl Howell male 26.0 0 0 111369 30.0000 C148 C

890 891 0 3 Dooley, Mr. Patrick male 32.0 0 0 370376 7.7500 NaN Q

[891 rows x 12 columns]

"""

print()

dataFrame2 = dataFrame1.drop(["Cabin", "Embarked"], axis = 1) # axis : 0(행), 1(컬럼)

print(dataFrame2)

"""

PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare

0 1 0 3 Braund, Mr. Owen Harris male 22.0 1 0 A/5 21171 7.2500

1 2 1 1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 0 PC 17599 71.2833

2 3 1 3 Heikkinen, Miss Laina female 26.0 0 0 STON/O2. 3101282 7.9250

3 4 1 1 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 0 113803 53.1000

4 5 0 3 Allen, Mr. William Henry male 35.0 0 0 373450 8.0500

.. ... ... ... ... ... ... ... ... ... ...

886 887 0 2 Montvila, Rev. Juozas male 27.0 0 0 211536 13.0000

887 888 1 1 Graham, Miss Margaret Edith female 19.0 0 0 112053 30.0000

888 889 0 3 Johnston, Miss Catherine Helen "Carrie" female NaN 1 2 W./C. 6607 23.4500

889 890 1 1 Behr, Mr. Karl Howell male 26.0 0 0 111369 30.0000

890 891 0 3 Dooley, Mr. Patrick male 32.0 0 0 370376 7.7500

[891 rows x 10 columns]

"""

▶ 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 : loc 속성을 사용해 특정 컬럼 데이터 구하기 1

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


import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1.loc[:, "Name":"Age"]

print(dataFrame2)

"""
                                                  Name     Sex   Age
0                              Braund, Mr. Owen Harris    male  22.0
1    Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0
2                                Heikkinen, Miss Laina  female  26.0
3         Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0
4                             Allen, Mr. William Henry    male  35.0
..                                                 ...     ...   ...
886                              Montvila, Rev. Juozas    male  27.0
887                        Graham, Miss Margaret Edith  female  19.0
888            Johnston, Miss Catherine Helen "Carrie"  female   NaN
889                              Behr, Mr. Karl Howell    male  26.0
890                                Dooley, Mr. Patrick    male  32.0

[891 rows x 3 columns]
"""

import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1.loc[:, "Name":"Age"]

print(dataFrame2)

"""

Name Sex Age

0 Braund, Mr. Owen Harris male 22.0

1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0

2 Heikkinen, Miss Laina female 26.0

3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0

4 Allen, Mr. William Henry male 35.0

.. ... ... ...

886 Montvila, Rev. Juozas male 27.0

887 Graham, Miss Margaret Edith female 19.0

888 Johnston, Miss Catherine Helen "Carrie" female NaN

889 Behr, Mr. Karl Howell male 26.0

890 Dooley, Mr. Patrick male 32.0

[891 rows x 3 columns]

"""

▶ 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 특정 조건을 만족하는 데이터 구하기

■ DataFrame 클래스에서 [] 연산자를 사용해 특정 조건을 만족하는 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1[(dataFrame1.Pclass == 2) | (dataFrame1.Pclass == 3)]

print(dataFrame2)

"""
     PassengerId  Survived  Pclass                                     Name     Sex   Age  SibSp  Parch            Ticket     Fare Cabin Embarked
0              1         0       3                  Braund, Mr. Owen Harris    male  22.0      1      0         A/5 21171   7.2500   NaN        S
2              3         1       3                    Heikkinen, Miss Laina  female  26.0      0      0  STON/O2. 3101282   7.9250   NaN        S
4              5         0       3                 Allen, Mr. William Henry    male  35.0      0      0            373450   8.0500   NaN        S
5              6         0       3                         Moran, Mr. James    male   NaN      0      0            330877   8.4583   NaN        Q
7              8         0       3            Palsson, Master Gosta Leonard    male   2.0      3      1            349909  21.0750   NaN        S
..           ...       ...     ...                                      ...     ...   ...    ...    ...               ...      ...   ...      ...
884          885         0       3                   Sutehall, Mr. Henry Jr    male  25.0      0      0   SOTON/OQ 392076   7.0500   NaN        S
885          886         0       3     Rice, Mrs. William (Margaret Norton)  female  39.0      0      5            382652  29.1250   NaN        Q
886          887         0       2                    Montvila, Rev. Juozas    male  27.0      0      0            211536  13.0000   NaN        S
888          889         0       3  Johnston, Miss Catherine Helen "Carrie"  female   NaN      1      2        W./C. 6607  23.4500   NaN        S
890          891         0       3                      Dooley, Mr. Patrick    male  32.0      0      0            370376   7.7500   NaN        Q

[675 rows x 12 columns]
"""

import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1[(dataFrame1.Pclass == 2) | (dataFrame1.Pclass == 3)]

print(dataFrame2)

"""

PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked

0 1 0 3 Braund, Mr. Owen Harris male 22.0 1 0 A/5 21171 7.2500 NaN S

2 3 1 3 Heikkinen, Miss Laina female 26.0 0 0 STON/O2. 3101282 7.9250 NaN S

4 5 0 3 Allen, Mr. William Henry male 35.0 0 0 373450 8.0500 NaN S

5 6 0 3 Moran, Mr. James male NaN 0 0 330877 8.4583 NaN Q

7 8 0 3 Palsson, Master Gosta Leonard male 2.0 3 1 349909 21.0750 NaN S

.. ... ... ... ... ... ... ... ... ... ... ... ...

884 885 0 3 Sutehall, Mr. Henry Jr male 25.0 0 0 SOTON/OQ 392076 7.0500 NaN S

885 886 0 3 Rice, Mrs. William (Margaret Norton) female 39.0 0 5 382652 29.1250 NaN Q

886 887 0 2 Montvila, Rev. Juozas male 27.0 0 0 211536 13.0000 NaN S

888 889 0 3 Johnston, Miss Catherine Helen "Carrie" female NaN 1 2 W./C. 6607 23.4500 NaN S

890 891 0 3 Dooley, Mr. Patrick male 32.0 0 0 370376 7.7500 NaN Q

[675 rows x 12 columns]

"""

▶ 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 : query 메소드를 사용해 특정 조건을 만족하는 데이터 구하기 1

■ DataFrame 클래스의 query 메소드를 사용해 특정 조건을 만족하는 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1.query("Sex == 'male' & Age > 30")

print(dataFrame2)

"""
     PassengerId  Survived  Pclass                                  Name   Sex   Age  SibSp  Parch    Ticket     Fare        Cabin Embarked
4              5         0       3              Allen, Mr. William Henry  male  35.0      0      0    373450   8.0500          NaN        S
6              7         0       1               McCarthy, Mr. Timothy J  male  54.0      0      0     17463  51.8625          E46        S
13            14         0       3           Andersson, Mr. Anders Johan  male  39.0      1      5    347082  31.2750          NaN        S
20            21         0       2                  Fynney, Mr. Joseph J  male  35.0      0      0    239865  26.0000          NaN        S
21            22         1       2                 Beesley, Mr. Lawrence  male  34.0      0      0    248698  13.0000          D56        S
..           ...       ...     ...                                   ...   ...   ...    ...    ...       ...      ...          ...      ...
867          868         0       1  Roebling, Mr. Washington Augustus II  male  31.0      0      0  PC 17590  50.4958          A24        S
872          873         0       1              Carlsson, Mr. Frans Olof  male  33.0      0      0       695   5.0000  B51 B53 B55        S
873          874         0       3           Vander Cruyssen, Mr. Victor  male  47.0      0      0    345765   9.0000          NaN        S
881          882         0       3                    Markun, Mr. Johann  male  33.0      0      0    349257   7.8958          NaN        S
890          891         0       3                   Dooley, Mr. Patrick  male  32.0      0      0    370376   7.7500          NaN        Q

[202 rows x 12 columns]
"""

import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1.query("Sex == 'male' & Age > 30")

print(dataFrame2)

"""

PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked

4 5 0 3 Allen, Mr. William Henry male 35.0 0 0 373450 8.0500 NaN S

6 7 0 1 McCarthy, Mr. Timothy J male 54.0 0 0 17463 51.8625 E46 S

13 14 0 3 Andersson, Mr. Anders Johan male 39.0 1 5 347082 31.2750 NaN S

20 21 0 2 Fynney, Mr. Joseph J male 35.0 0 0 239865 26.0000 NaN S

21 22 1 2 Beesley, Mr. Lawrence male 34.0 0 0 248698 13.0000 D56 S

.. ... ... ... ... ... ... ... ... ... ... ... ...

867 868 0 1 Roebling, Mr. Washington Augustus II male 31.0 0 0 PC 17590 50.4958 A24 S

872 873 0 1 Carlsson, Mr. Frans Olof male 33.0 0 0 695 5.0000 B51 B53 B55 S

873 874 0 3 Vander Cruyssen, Mr. Victor male 47.0 0 0 345765 9.0000 NaN S

881 882 0 3 Markun, Mr. Johann male 33.0 0 0 349257 7.8958 NaN S

890 891 0 3 Dooley, Mr. Patrick male 32.0 0 0 370376 7.7500 NaN Q

[202 rows x 12 columns]

"""

▶ 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] Series 클래스 : idxmax 메소드를 사용해 최개 값을 갖는 인덱스 및 항목 구하기

■ Series 클래스의 idxmax 메소드를 사용해 최개 값을 갖는 인덱스 및 항목을 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

series = pd.Series(
    [10, 20, 30, 20, 15],
    index = ['a', 'b', 'c', 'd', 'e']
)

print(series)

"""
a    10
b    20
c    30
d    20
e    15
dtype: int64
"""

# 최대값의 인덱스를 찾는다.
maximumValueIndex = series.idxmax()

print(maximumValueIndex)

"""
c
"""

# 최대 값을 조회한다.
print(series[maximumValueIndex])

"""
30
"""

import pandas as pd

series = pd.Series(

[10, 20, 30, 20, 15],

index = ['a', 'b', 'c', 'd', 'e']

)

print(series)

"""

a 10

b 20

c 30

d 20

e 15

dtype: int64

"""

# 최대값의 인덱스를 찾는다.

maximumValueIndex = series.idxmax()

print(maximumValueIndex)

"""

# 최대 값을 조회한다.

print(series[maximumValueIndex])

"""

▶ 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 : str 속성을 사용해 특정 컬럼 문자열 값 변경하기

■ DataFrame 클래스의 str 속성을 사용해 특정 컬럼의 문자열 값을 변경하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

dataFrame["Sex_short"] = dataFrame["Sex"      ].str.replace("female", "F")
dataFrame["Sex_short"] = dataFrame["Sex_short"].str.replace("male"  , "M")

print(dataFrame)

"""
     PassengerId  Survived  Pclass                                               Name     Sex   Age  SibSp  Parch            Ticket     Fare Cabin Embarked Sex_short
0              1         0       3                            Braund, Mr. Owen Harris    male  22.0      1      0         A/5 21171   7.2500   NaN        S         M
1              2         1       1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1      0          PC 17599  71.2833   C85        C         F
2              3         1       3                              Heikkinen, Miss Laina  female  26.0      0      0  STON/O2. 3101282   7.9250   NaN        S         F
3              4         1       1       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1      0            113803  53.1000  C123        S         F
4              5         0       3                           Allen, Mr. William Henry    male  35.0      0      0            373450   8.0500   NaN        S         M
..           ...       ...     ...                                                ...     ...   ...    ...    ...               ...      ...   ...      ...       ...
886          887         0       2                              Montvila, Rev. Juozas    male  27.0      0      0            211536  13.0000   NaN        S         M
887          888         1       1                        Graham, Miss Margaret Edith  female  19.0      0      0            112053  30.0000   B42        S         F
888          889         0       3            Johnston, Miss Catherine Helen "Carrie"  female   NaN      1      2        W./C. 6607  23.4500   NaN        S         F
889          890         1       1                              Behr, Mr. Karl Howell    male  26.0      0      0            111369  30.0000  C148        C         M
890          891         0       3                                Dooley, Mr. Patrick    male  32.0      0      0            370376   7.7500   NaN        Q         M

[891 rows x 13 columns]
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

dataFrame["Sex_short"] = dataFrame["Sex" ].str.replace("female", "F")

dataFrame["Sex_short"] = dataFrame["Sex_short"].str.replace("male" , "M")

print(dataFrame)

"""

PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked Sex_short

0 1 0 3 Braund, Mr. Owen Harris male 22.0 1 0 A/5 21171 7.2500 NaN S M

1 2 1 1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 0 PC 17599 71.2833 C85 C F

2 3 1 3 Heikkinen, Miss Laina female 26.0 0 0 STON/O2. 3101282 7.9250 NaN S F

3 4 1 1 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 0 113803 53.1000 C123 S F

4 5 0 3 Allen, Mr. William Henry male 35.0 0 0 373450 8.0500 NaN S M

.. ... ... ... ... ... ... ... ... ... ... ... ... ...

886 887 0 2 Montvila, Rev. Juozas male 27.0 0 0 211536 13.0000 NaN S M

887 888 1 1 Graham, Miss Margaret Edith female 19.0 0 0 112053 30.0000 B42 S F

888 889 0 3 Johnston, Miss Catherine Helen "Carrie" female NaN 1 2 W./C. 6607 23.4500 NaN S F

889 890 1 1 Behr, Mr. Karl Howell male 26.0 0 0 111369 30.0000 C148 C M

890 891 0 3 Dooley, Mr. Patrick male 32.0 0 0 370376 7.7500 NaN Q M

[891 rows x 13 columns]

"""

▶ 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] Series 클래스 : replace 메소드를 사용해 컬럼 문자열 값 변경하기

■ Series 클래스의 replace 메소드를 사용해 컬럼의 문자열 값을 변경하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series = dataFrame["Sex"]

dataFrame["Sex_short"] = series.replace({"male" : "M", "female" : "F"})

print(dataFrame)

"""
     PassengerId  Survived  Pclass                                               Name     Sex   Age  SibSp  Parch            Ticket     Fare Cabin Embarked Sex_short
0              1         0       3                            Braund, Mr. Owen Harris    male  22.0      1      0         A/5 21171   7.2500   NaN        S         M
1              2         1       1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1      0          PC 17599  71.2833   C85        C         F
2              3         1       3                              Heikkinen, Miss Laina  female  26.0      0      0  STON/O2. 3101282   7.9250   NaN        S         F
3              4         1       1       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1      0            113803  53.1000  C123        S         F
4              5         0       3                           Allen, Mr. William Henry    male  35.0      0      0            373450   8.0500   NaN        S         M
..           ...       ...     ...                                                ...     ...   ...    ...    ...               ...      ...   ...      ...       ...
886          887         0       2                              Montvila, Rev. Juozas    male  27.0      0      0            211536  13.0000   NaN        S         M
887          888         1       1                        Graham, Miss Margaret Edith  female  19.0      0      0            112053  30.0000   B42        S         F
888          889         0       3            Johnston, Miss Catherine Helen "Carrie"  female   NaN      1      2        W./C. 6607  23.4500   NaN        S         F
889          890         1       1                              Behr, Mr. Karl Howell    male  26.0      0      0            111369  30.0000  C148        C         M
890          891         0       3                                Dooley, Mr. Patrick    male  32.0      0      0            370376   7.7500   NaN        Q         M

[891 rows x 13 columns]
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series = dataFrame["Sex"]

dataFrame["Sex_short"] = series.replace({"male" : "M", "female" : "F"})

print(dataFrame)

"""

PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked Sex_short

0 1 0 3 Braund, Mr. Owen Harris male 22.0 1 0 A/5 21171 7.2500 NaN S M

1 2 1 1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 0 PC 17599 71.2833 C85 C F

2 3 1 3 Heikkinen, Miss Laina female 26.0 0 0 STON/O2. 3101282 7.9250 NaN S F

3 4 1 1 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 0 113803 53.1000 C123 S F

4 5 0 3 Allen, Mr. William Henry male 35.0 0 0 373450 8.0500 NaN S M

.. ... ... ... ... ... ... ... ... ... ... ... ... ...

886 887 0 2 Montvila, Rev. Juozas male 27.0 0 0 211536 13.0000 NaN S M

887 888 1 1 Graham, Miss Margaret Edith female 19.0 0 0 112053 30.0000 B42 S F

888 889 0 3 Johnston, Miss Catherine Helen "Carrie" female NaN 1 2 W./C. 6607 23.4500 NaN S F

889 890 1 1 Behr, Mr. Karl Howell male 26.0 0 0 111369 30.0000 C148 C M

890 891 0 3 Dooley, Mr. Patrick male 32.0 0 0 370376 7.7500 NaN Q M

[891 rows x 13 columns]

"""

▶ 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] Series 클래스 : idxmax 메소드를 사용해 최대값을 갖는 인덱스의 특정 컬럼 값 구하기

■ Series 클래스의 idxmax 메소드를 사용해 최대값을 갖는 인덱스의 특정 컬럼 값을 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Name"]

series2 = series1.str.len()

name = dataFrame.loc[series2.idxmax(), "Name"]

print(name)

"""
Penasco y Castellana, Mrs. Victor de Satode (Maria Josefa Perez de Soto y Vallejo)
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Name"]

series2 = series1.str.len()

name = dataFrame.loc[series2.idxmax(), "Name"]

print(name)

"""

Penasco y Castellana, Mrs. Victor de Satode (Maria Josefa Perez de Soto y Vallejo)

"""

▶ 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] Series 클래스 : idxmax 메소드를 사용해 최대값을 갖는 인덱스 구하기

■ Series 클래스의 idxmax 메소드를 사용해 최대값을 갖는 인덱스를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Name"]

series2 = series1.str.len()

index = series2.idxmax()

print(index)
print(series2[index])

"""
307
82
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Name"]

series2 = series1.str.len()

index = series2.idxmax()

print(index)

print(series2[index])

"""

307

"""

▶ 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] Series 클래스 : str 속성을 사용해 컬럼 문자열 값 길이 구하기

■ Series 클래스의 str 속성을 사용해 컬럼 문자열 값의 길이를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series = dataFrame["Name"].str.len()

print(series)

"""
0      23
1      51
2      21
3      44
4      24
       ..
886    21
887    27
888    39
889    21
890    19
Name: Name, Length: 891, dtype: int64
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series = dataFrame["Name"].str.len()

print(series)

"""

0 23

1 51

2 21

3 44

4 24

886 21

887 27

888 39

889 21

890 19

Name: Name, Length: 891, dtype: int64

"""

▶ 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] Series 클래스 : str 속성을 사용해 컬럼 문자열 값에 특정 문자열이 포함된 데이터 구하기

■ Series 클래스의 str 속성을 사용해 컬럼 문자열 값에 특정 문자열이 포함된 데이터를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1[dataFrame1["Name"].str.contains("Countess")]

print(dataFrame2)

"""
     PassengerId  Survived  Pclass                                               Name     Sex   Age  SibSp  Parch  Ticket  Fare Cabin Embarked
759          760         1       1  Rothes, the Countess. of (Lucy Noel Martha Dye...  female  33.0      0      0  110152  86.5   B77        S
"""

import pandas as pd

dataFrame1 = pd.read_csv("titanic.csv")

dataFrame2 = dataFrame1[dataFrame1["Name"].str.contains("Countess")]

print(dataFrame2)

"""

PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked

759 760 1 1 Rothes, the Countess. of (Lucy Noel Martha Dye... female 33.0 0 0 110152 86.5 B77 S

"""

▶ 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] Series 클래스 : str 속성을 사용해 컬럼 문자열 값에 특정 문자열 포함 여부 구하기

■ Series 클래스의 str 속성을 사용해 컬럼 문자열 값에 특정 문자열 포함 여부를 구하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Name"]

series2 = series1.str.contains("Countess")

print(series2)

"""
0      False
1      False
2      False
3      False
4      False
       ...
886    False
887    False
888    False
889    False
890    False
Name: Name, Length: 891, dtype: bool
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Name"]

series2 = series1.str.contains("Countess")

print(series2)

"""

0 False

1 False

2 False

3 False

4 False

...

886 False

887 False

888 False

889 False

890 False

Name: Name, Length: 891, dtype: bool

"""

▶ 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] Series 클래스 : str 속성을 사용해 DataFrame 객체 신규 컬럼 추가하기

■ Series 클래스의 str 속성을 사용해 DataFrame 객체의 신규 컬럼을 추가하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

dataFrame["Surname"] = dataFrame["Name"].str.split(",").str.get(0)

print(dataFrame)

"""
     PassengerId  Survived  Pclass                                               Name     Sex   Age  SibSp  Parch            Ticket     Fare Cabin Embarked    Surname
0              1         0       3                            Braund, Mr. Owen Harris    male  22.0      1      0         A/5 21171   7.2500   NaN        S     Braund
1              2         1       1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1      0          PC 17599  71.2833   C85        C    Cumings
2              3         1       3                              Heikkinen, Miss Laina  female  26.0      0      0  STON/O2. 3101282   7.9250   NaN        S  Heikkinen
3              4         1       1       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1      0            113803  53.1000  C123        S   Futrelle
4              5         0       3                           Allen, Mr. William Henry    male  35.0      0      0            373450   8.0500   NaN        S      Allen
..           ...       ...     ...                                                ...     ...   ...    ...    ...               ...      ...   ...      ...        ...
886          887         0       2                              Montvila, Rev. Juozas    male  27.0      0      0            211536  13.0000   NaN        S   Montvila
887          888         1       1                        Graham, Miss Margaret Edith  female  19.0      0      0            112053  30.0000   B42        S     Graham
888          889         0       3            Johnston, Miss Catherine Helen "Carrie"  female   NaN      1      2        W./C. 6607  23.4500   NaN        S   Johnston
889          890         1       1                              Behr, Mr. Karl Howell    male  26.0      0      0            111369  30.0000  C148        C       Behr
890          891         0       3                                Dooley, Mr. Patrick    male  32.0      0      0            370376   7.7500   NaN        Q     Dooley
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

dataFrame["Surname"] = dataFrame["Name"].str.split(",").str.get(0)

print(dataFrame)

"""

PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked Surname

0 1 0 3 Braund, Mr. Owen Harris male 22.0 1 0 A/5 21171 7.2500 NaN S Braund

1 2 1 1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 0 PC 17599 71.2833 C85 C Cumings

2 3 1 3 Heikkinen, Miss Laina female 26.0 0 0 STON/O2. 3101282 7.9250 NaN S Heikkinen

3 4 1 1 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 0 113803 53.1000 C123 S Futrelle

4 5 0 3 Allen, Mr. William Henry male 35.0 0 0 373450 8.0500 NaN S Allen

.. ... ... ... ... ... ... ... ... ... ... ... ... ...

886 887 0 2 Montvila, Rev. Juozas male 27.0 0 0 211536 13.0000 NaN S Montvila

887 888 1 1 Graham, Miss Margaret Edith female 19.0 0 0 112053 30.0000 B42 S Graham

888 889 0 3 Johnston, Miss Catherine Helen "Carrie" female NaN 1 2 W./C. 6607 23.4500 NaN S Johnston

889 890 1 1 Behr, Mr. Karl Howell male 26.0 0 0 111369 30.0000 C148 C Behr

890 891 0 3 Dooley, Mr. Patrick male 32.0 0 0 370376 7.7500 NaN Q Dooley

"""

▶ 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] Series 클래스 : str 속성을 사용해 컬럼 문자열 값 분리하기

■ Series 클래스의 str 속성을 사용해 컬럼 문자열 값을 분리하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Name"]

series2 = series1.str.split(",")

"""
0                             [Braund,  Mr. Owen Harris]
1      [Cumings,  Mrs. John Bradley (Florence Briggs ...
2                               [Heikkinen,  Miss Laina]
3        [Futrelle,  Mrs. Jacques Heath (Lily May Peel)]
4                            [Allen,  Mr. William Henry]
                             ...
886                             [Montvila,  Rev. Juozas]
887                       [Graham,  Miss Margaret Edith]
888           [Johnston,  Miss Catherine Helen "Carrie"]
889                             [Behr,  Mr. Karl Howell]
890                               [Dooley,  Mr. Patrick]
Name: Name, Length: 891, dtype: object
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Name"]

series2 = series1.str.split(",")

"""

0 [Braund, Mr. Owen Harris]

1 [Cumings, Mrs. John Bradley (Florence Briggs ...

2 [Heikkinen, Miss Laina]

3 [Futrelle, Mrs. Jacques Heath (Lily May Peel)]

4 [Allen, Mr. William Henry]

...

886 [Montvila, Rev. Juozas]

887 [Graham, Miss Margaret Edith]

888 [Johnston, Miss Catherine Helen "Carrie"]

889 [Behr, Mr. Karl Howell]

890 [Dooley, Mr. Patrick]

Name: Name, Length: 891, dtype: object

"""

▶ 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] Series 클래스 : str 속성을 사용해 컬럼 문자열 값 소문자로 변경하기

■ Series 클래스의 str 속성을 사용해 컬럼 문자열 값을 소문자로 변경하는 방법을 보여준다. ▶ main.py


import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Name"]

series2 = series1.str.lower()

print(series2)

"""
0                                braund, mr. owen harris
1      cumings, mrs. john bradley (florence briggs th...
2                                  heikkinen, miss laina
3           futrelle, mrs. jacques heath (lily may peel)
4                               allen, mr. william henry
                             ...
886                                montvila, rev. juozas
887                          graham, miss margaret edith
888              johnston, miss catherine helen "carrie"
889                                behr, mr. karl howell
890                                  dooley, mr. patrick
Name: Name, Length: 891, dtype: object
"""

import pandas as pd

dataFrame = pd.read_csv("titanic.csv")

series1 = dataFrame["Name"]

series2 = series1.str.lower()

print(series2)

"""

0 braund, mr. owen harris

1 cumings, mrs. john bradley (florence briggs th...

2 heikkinen, miss laina

3 futrelle, mrs. jacques heath (lily may peel)

4 allen, mr. william henry

...

886 montvila, rev. juozas

887 graham, miss margaret edith

888 johnston, miss catherine helen "carrie"

889 behr, mr. karl howell

890 dooley, mr. patrick

Name: Name, Length: 891, dtype: object

"""

▶ 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 : pivot/plot 메소드를 사용해 장소별 일별 LINE 차트 그리기

■ DataFrame 클래스의 pivot/plot 메소드를 사용해 장소별 일별 LINE 차트를 그리는 방법을 보여준다. ▶ main.py


import pandas            as pd
import matplotlib.pyplot as plt

sourceDataFrame = pd.read_csv("air_quality_no2_long.csv", parse_dates = ["date.utc"])

renameDataFrame = sourceDataFrame.rename(columns = {"date.utc" : "datetime"})

pivotDataFrame = renameDataFrame.pivot(index = "datetime", columns = "location", values = "value")

datetimeIndexResampler = pivotDataFrame.resample("D")

targetDataFrame = datetimeIndexResampler.mean()

targetDataFrame.plot(style = "-o", figsize = (10, 5))

plt.show()

import pandas as pd

import matplotlib.pyplot as plt

sourceDataFrame = pd.read_csv("air_quality_no2_long.csv", parse_dates = ["date.utc"])

renameDataFrame = sourceDataFrame.rename(columns = {"date.utc" : "datetime"})

pivotDataFrame = renameDataFrame.pivot(index = "datetime", columns = "location", values = "value")

datetimeIndexResampler = pivotDataFrame.resample("D")

targetDataFrame = datetimeIndexResampler.mean()

targetDataFrame.plot(style = "-o", figsize = (10, 5))

plt.show()

▶ requirements.txt


contourpy==1.3.0
cycler==0.12.1
fonttools==4.54.1
kiwisolver==1.4.7
matplotlib==3.9.2
numpy==2.1.2
packaging==24.1
pandas==2.2.3
pillow==11.0.0
pyparsing==3.2.0
python-dateutil==2.9.0.post0
pytz==2024.2
six==1.16.0
tzdata==2024.2

contourpy==1.3.0

cycler==0.12.1

fonttools==4.54.1

kiwisolver==1.4.7

matplotlib==3.9.2

numpy==2.1.2

packaging==24.1

pandas==2.2.3

pillow==11.0.0

pyparsing==3.2.0

python-dateutil==2.9.0.post0

pytz==2024.2

six==1.16.0

tzdata==2024.2

※ pip install