1. 결측치(missing_value)

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

titanic = sns.load_dataset("titanic")
titanic.head()

"""
survived	pclass	sex	age	sibsp	parch	fare	embarked	class	who	adult_male	deck	embark_town	alive	alone
0	0	3	male	22.0	1	0	7.2500	S	Third	man	True	NaN	Southampton	no	False
1	1	1	female	38.0	1	0	71.2833	C	First	woman	False	C	Cherbourg	yes	False
2	1	3	female	26.0	0	0	7.9250	S	Third	woman	False	NaN	Southampton	yes	True
3	1	1	female	35.0	1	0	53.1000	S	First	woman	False	C	Southampton	yes	False
4	0	3	male	35.0	0	0	8.0500	S	Third	man	True	NaN	Southampton	no	True

 

결측치 탐색

titanic.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 15 columns):
 #   Column       Non-Null Count  Dtype   
---  ------       --------------  -----   
 0   survived     891 non-null    int64   
 1   pclass       891 non-null    int64   
 2   sex          891 non-null    object  
 3   age          714 non-null    float64 
 4   sibsp        891 non-null    int64   
 5   parch        891 non-null    int64   
 6   fare         891 non-null    float64 
 7   embarked     889 non-null    object  
 8   class        891 non-null    category
 9   who          891 non-null    object  
 10  adult_male   891 non-null    bool    
 11  deck         203 non-null    category
 12  embark_town  889 non-null    object  
 13  alive        891 non-null    object  
 14  alone        891 non-null    bool    
dtypes: bool(2), category(2), float64(2), int64(4), object(5)
memory usage: 80.7+ KB

 

titanic.isnull().sum()

survived         0
pclass           0
sex              0
age            177
sibsp            0
parch            0
fare             0
embarked         2
class            0
who              0
adult_male       0
deck           688
embark_town      2
alive            0
alone            0
dtype: int64

 

import missingno as msno

msno.matrix(titanic, color=(0.2, 0.6, 0.1))
plt.show()

 

msno.bar(titanic, color=(0.1, 0.6, 0.6))
plt.show()

 

결측치 처리

titanic = titanic.dropna(thresh=int(len(titanic)/2), axis=1)
titanic.isnull().sum()

survived         0
pclass           0
sex              0
age            177
sibsp            0
parch            0
fare             0
embarked         2
class            0
who              0
adult_male       0
embark_town      2
alive            0
alone            0
dtype: int64

 

titanic = titanic[titanic.embarked.notnull()]
titanic

"""
survived	pclass	sex	age	sibsp	parch	fare	embarked	class	who	adult_male	embark_town	alive	alone
0	0	3	male	22.0	1	0	7.2500	S	Third	man	True	Southampton	no	False
1	1	1	female	38.0	1	0	71.2833	C	First	woman	False	Cherbourg	yes	False
2	1	3	female	26.0	0	0	7.9250	S	Third	woman	False	Southampton	yes	True
3	1	1	female	35.0	1	0	53.1000	S	First	woman	False	Southampton	yes	False
4	0	3	male	35.0	0	0	8.0500	S	Third	man	True	Southampton	no	True
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
886	0	2	male	27.0	0	0	13.0000	S	Second	man	True	Southampton	no	True
887	1	1	female	19.0	0	0	30.0000	S	First	woman	False	Southampton	yes	True
888	0	3	female	NaN	1	2	23.4500	S	Third	woman	False	Southampton	no	False
889	1	1	male	26.0	0	0	30.0000	C	First	man	True	Cherbourg	yes	True
890	0	3	male	32.0	0	0	7.7500	Q	Third	man	True	Queenstown	no	True

 

titanic = titanic[titanic.embarked.notnull()]
titanic.isnull().sum()

survived         0
pclass           0
sex              0
age            177
sibsp            0
parch            0
fare             0
embarked         0
class            0
who              0
adult_male       0
embark_town      0
alive            0
alone            0
dtype: int64

 

plt.figure(figsize=(8, 8)) 
sns.distplot(titanic['age'])
plt.grid()
plt.show()

 

titanic.age.fillna(value = titanic.age.median(), inplace=True)
titanic.isnull().sum()

survived         0
pclass           0
sex              0
age              0
sibsp            0
parch            0
fare             0
embarked         2
class            0
who              0
adult_male       0
deck           688
embark_town      2
alive            0
alone            0
dtype: int64