Funcionalidades de resumen de DataFrames

Jeshua Romero Guadarrama
6 Min para leer
17 May, 2021
- Python
- Pandas

Índice de contenido

python

import pandas as pd

python

file_path = "C:/Users/user/Desktop/adult.data"

col_names = ["age", 
            "workclass",
            "fnlwgt", 
            "education",
            "education-num",
            "marital-status",
            "occupation",
            "relationship",
            "race",
            "sex",
            "capital-gain",
            "capital-loss",
            "hours-per-week",
            "native-country",
            "income"]


df = pd.read_csv(filepath_or_buffer = file_path,
           header = 0,
           names = col_names)
df

	age	workclass	fnlwgt	education	education-num	marital-status	occupation	relationship	race	sex	capital-gain	capital-loss	hours-per-week	native-country	income
0	50	NaN	83311	Bachelors	13	Married-civ-spouse	Exec-managerial	Husband	White	Male	0	0	13	United-States	<=50K
1	38	Private	215646	HS-grad	9	Divorced	Handlers-cleaners	Not-in-family	White	Male	0	0	40	United-States	<=50K
2	53	Private	234721	11th	7	Married-civ-spouse	Handlers-cleaners	Husband	Black	Male	0	0	40	United-States	<=50K
3	28	Private	338409	Bachelors	13	Married-civ-spouse	Prof-specialty	Wife	Black	Female	0	0	40	Cuba	<=50K
4	37	Private	284582	Masters	14	Married-civ-spouse	Exec-managerial	Wife	White	Female	0	0	40	United-States	<=50K
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
32555	27	Private	257302	Assoc-acdm	12	Married-civ-spouse	Tech-support	Wife	White	Female	0	0	38	United-States	<=50K
32556	40	Private	154374	HS-grad	9	Married-civ-spouse	Machine-op-inspct	Husband	White	Male	0	0	40	United-States	>50K
32557	58	Private	151910	HS-grad	9	Widowed	Adm-clerical	Unmarried	White	Female	0	0	40	United-States	<=50K
32558	22	Private	201490	HS-grad	9	Never-married	Adm-clerical	Own-child	White	Male	0	0	20	United-States	<=50K
32559	52	Self-emp-inc	287927	HS-grad	9	Married-civ-spouse	Exec-managerial	Wife	White	Female	15024	0	40	United-States	>50K

32560 rows × 15 columns

df.dtypes

python

df.dtypes

age                int64
workclass         object
fnlwgt             int64
education         object
education-num      int64
marital-status    object
occupation        object
relationship      object
race              object
sex               object
capital-gain       int64
capital-loss       int64
hours-per-week     int64
native-country    object
income            object
dtype: object

df.values

python

df.values

array([[50, nan, 83311, ..., 13, ' United-States', ' <=50K'],
       [38, ' Private', 215646, ..., 40, ' United-States', ' <=50K'],
       [53, ' Private', 234721, ..., 40, ' United-States', ' <=50K'],
       ...,
       [58, ' Private', 151910, ..., 40, ' United-States', ' <=50K'],
       [22, ' Private', 201490, ..., 20, ' United-States', ' <=50K'],
       [52, ' Self-emp-inc', 287927, ..., 40, ' United-States', ' >50K']],
      dtype=object)

df.ndim

python

df.ndim

df.shape

python

df.shape

(32560, 15)

df.size

python

df.size

unique

python

df.apply(lambda x: x.unique())

age               [50, 38, 53, 28, 37, 49, 52, 31, 42, 30, 23, 3...
workclass         [nan,  Private,  Self-emp-not-inc,  State-gov,...
fnlwgt            [83311, 215646, 234721, 338409, 284582, 160187...
education         [ Bachelors,  HS-grad,  11th,  Masters,  9th, ...
education-num     [13, 9, 7, 14, 5, 10, 12, 11, 4, 16, 15, 3, 6,...
marital-status    [ Married-civ-spouse,  Divorced,  Married-spou...
occupation        [ Exec-managerial,  Handlers-cleaners,  Prof-s...
relationship      [ Husband,  Not-in-family,  Wife,  Own-child, ...
race              [ White,  Black,  Asian-Pac-Islander,  Amer-In...
sex                                                [ Male,  Female]
capital-gain      [0, 14084, 5178, 5013, 2407, 14344, 15024, 768...
capital-loss      [0, 2042, 1408, 1902, 1573, 1887, 1719, 1762, ...
hours-per-week    [13, 40, 16, 45, 50, 80, 30, 35, 60, 20, 52, 4...
native-country    [ United-States,  Cuba,  Jamaica,  India,  ?, ...
income                                              [ <=50K,  >50K]
dtype: object

python

df.workclass.unique()

array([nan, ' Private', ' Self-emp-not-inc', ' State-gov', ' Federal-gov',
       ' Local-gov', ' ?', ' Self-emp-inc', ' Without-pay',
       ' Never-worked'], dtype=object)

df.nunique

python

df.nunique(axis=0, dropna=True)

age                  73
workclass             9
fnlwgt            21647
education            16
education-num        16
marital-status        7
occupation           15
relationship          6
race                  5
sex                   2
capital-gain        119
capital-loss         92
hours-per-week       94
native-country       42
income                2
dtype: int64

df.max

python

df.max(axis = 0)

age                              90
fnlwgt                      1484705
education              Some-college
education-num                    16
marital-status              Widowed
occupation         Transport-moving
relationship                   Wife
race                          White
sex                            Male
capital-gain                  99999
capital-loss                   4356
hours-per-week                   99
native-country           Yugoslavia
income                         >50K
dtype: object

df.min

python

df.min(axis=0)

age                                17
fnlwgt                          12285
education                        10th
education-num                       1
marital-status               Divorced
occupation                          ?
relationship                  Husband
race               Amer-Indian-Eskimo
sex                            Female
capital-gain                        0
capital-loss                        0
hours-per-week                      1
native-country                      ?
income                          <=50K
dtype: object

df.duplicated

python

df.duplicated(subset = ["marital-status"])

0        False
1        False
2         True
3         True
4         True
         ...  
32555     True
32556     True
32557     True
32558     True
32559     True
Length: 32560, dtype: bool

python

df[df.duplicated(subset = ["age", "marital-status"])]

	age	workclass	fnlwgt	education	education-num	marital-status	occupation	relationship	race	sex	capital-gain	capital-loss	hours-per-week	native-country	income
9	37	Private	280464	Some-college	10	Married-civ-spouse	Exec-managerial	Husband	Black	Male	0	0	80	United-States	>50K
16	32	Private	186824	HS-grad	9	Never-married	Machine-op-inspct	Unmarried	White	Male	0	0	40	United-States	<=50K
19	40	Private	193524	Doctorate	16	Married-civ-spouse	Prof-specialty	Husband	White	Male	0	0	60	United-States	>50K
29	23	Local-gov	190709	Assoc-acdm	12	Never-married	Protective-serv	Not-in-family	White	Male	0	0	52	United-States	<=50K
32	30	Federal-gov	59951	Some-college	10	Married-civ-spouse	Adm-clerical	Own-child	White	Male	0	0	40	United-States	<=50K
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
32555	27	Private	257302	Assoc-acdm	12	Married-civ-spouse	Tech-support	Wife	White	Female	0	0	38	United-States	<=50K
32556	40	Private	154374	HS-grad	9	Married-civ-spouse	Machine-op-inspct	Husband	White	Male	0	0	40	United-States	>50K
32557	58	Private	151910	HS-grad	9	Widowed	Adm-clerical	Unmarried	White	Female	0	0	40	United-States	<=50K
32558	22	Private	201490	HS-grad	9	Never-married	Adm-clerical	Own-child	White	Male	0	0	20	United-States	<=50K
32559	52	Self-emp-inc	287927	HS-grad	9	Married-civ-spouse	Exec-managerial	Wife	White	Female	15024	0	40	United-States	>50K

32164 rows × 15 columns

df.info()

python

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 32560 entries, 0 to 32559
Data columns (total 15 columns):
 #   Column          Non-Null Count  Dtype 
---  ------          --------------  ----- 
 0   age             32560 non-null  int64 
 1   workclass       32559 non-null  object
 2   fnlwgt          32560 non-null  int64 
 3   education       32560 non-null  object
 4   education-num   32560 non-null  int64 
 5   marital-status  32560 non-null  object
 6   occupation      32560 non-null  object
 7   relationship    32560 non-null  object
 8   race            32560 non-null  object
 9   sex             32560 non-null  object
 10  capital-gain    32560 non-null  int64 
 11  capital-loss    32560 non-null  int64 
 12  hours-per-week  32560 non-null  int64 
 13  native-country  32560 non-null  object
 14  income          32560 non-null  object
dtypes: int64(6), object(9)
memory usage: 3.7+ MB

df.describe()

python

df.describe(include = "all")

	age	workclass	fnlwgt	education	education-num	marital-status	occupation	relationship	race	sex	capital-gain	capital-loss	hours-per-week	native-country	income
count	32560.000000	32559	3.256000e+04	32560	32560.000000	32560	32560	32560	32560	32560	32560.000000	32560.000000	32560.000000	32560	32560
unique	NaN	9	NaN	16	NaN	7	15	6	5	2	NaN	NaN	NaN	42	2
top	NaN	Private	NaN	HS-grad	NaN	Married-civ-spouse	Prof-specialty	Husband	White	Male	NaN	NaN	NaN	United-States	<=50K
freq	NaN	22696	NaN	10501	NaN	14976	4140	13193	27815	21789	NaN	NaN	NaN	29169	24719
mean	38.581634	NaN	1.897818e+05	NaN	10.080590	NaN	NaN	NaN	NaN	NaN	1077.615172	87.306511	40.437469	NaN	NaN
std	13.640642	NaN	1.055498e+05	NaN	2.572709	NaN	NaN	NaN	NaN	NaN	7385.402999	402.966116	12.347618	NaN	NaN
min	17.000000	NaN	1.228500e+04	NaN	1.000000	NaN	NaN	NaN	NaN	NaN	0.000000	0.000000	1.000000	NaN	NaN
25%	28.000000	NaN	1.178315e+05	NaN	9.000000	NaN	NaN	NaN	NaN	NaN	0.000000	0.000000	40.000000	NaN	NaN
50%	37.000000	NaN	1.783630e+05	NaN	10.000000	NaN	NaN	NaN	NaN	NaN	0.000000	0.000000	40.000000	NaN	NaN
75%	48.000000	NaN	2.370545e+05	NaN	12.000000	NaN	NaN	NaN	NaN	NaN	0.000000	0.000000	45.000000	NaN	NaN
max	90.000000	NaN	1.484705e+06	NaN	16.000000	NaN	NaN	NaN	NaN	NaN	99999.000000	4356.000000	99.000000	NaN	NaN