In [1]:

    

import pandas as pd


    

In [2]:

    

titanic = pd.read_excel("./data/titanic3.xls", "titanic3", index_col=None, na_value=["NA"])


    

In [3]:

    

titanic.head()


    

    
Out[3]:







  

    

      

      
pclass
      
survived
      
name
      
sex
      
age
      
sibsp
      
parch
      
ticket
      
fare
      
cabin
      
embarked
      
boat
      
body
      
home.dest
    
  
  

    

      
0
      
1
      
1
      
Allen, Miss. Elisabeth Walton
      
female
      
29.0000
      
0
      
0
      
24160
      
211.3375
      
B5
      
S
      
2
      
NaN
      
St Louis, MO
    
    

      
1
      
1
      
1
      
Allison, Master. Hudson Trevor
      
male
      
0.9167
      
1
      
2
      
113781
      
151.5500
      
C22 C26
      
S
      
11
      
NaN
      
Montreal, PQ / Chesterville, ON
    
    

      
2
      
1
      
0
      
Allison, Miss. Helen Loraine
      
female
      
2.0000
      
1
      
2
      
113781
      
151.5500
      
C22 C26
      
S
      
NaN
      
NaN
      
Montreal, PQ / Chesterville, ON
    
    

      
3
      
1
      
0
      
Allison, Mr. Hudson Joshua Creighton
      
male
      
30.0000
      
1
      
2
      
113781
      
151.5500
      
C22 C26
      
S
      
NaN
      
135.0
      
Montreal, PQ / Chesterville, ON
    
    

      
4
      
1
      
0
      
Allison, Mrs. Hudson J C (Bessie Waldo Daniels)
      
female
      
25.0000
      
1
      
2
      
113781
      
151.5500
      
C22 C26
      
S
      
NaN
      
NaN
      
Montreal, PQ / Chesterville, ON
    
  

In [4]:

    

titanic.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1309 entries, 0 to 1308
Data columns (total 14 columns):
 #   Column     Non-Null Count  Dtype  
---  ------     --------------  -----  
 0   pclass     1309 non-null   int64  
 1   survived   1309 non-null   int64  
 2   name       1309 non-null   object 
 3   sex        1309 non-null   object 
 4   age        1046 non-null   float64
 5   sibsp      1309 non-null   int64  
 6   parch      1309 non-null   int64  
 7   ticket     1309 non-null   object 
 8   fare       1308 non-null   float64
 9   cabin      295 non-null    object 
 10  embarked   1307 non-null   object 
 11  boat       486 non-null    object 
 12  body       121 non-null    float64
 13  home.dest  745 non-null    object 
dtypes: float64(3), int64(4), object(7)
memory usage: 143.3+ KB

In [ ]:

    

titanic.describe()


    

In [ ]:

    

titanic.shape


    

In [ ]:

    

titanic['name']


    

In [ ]:

    

tit = titanic[['name','age']]


    

In [ ]:

    

tit.head()


    

In [ ]:

    

titanic.loc[5:10,['name','age']]


    

In [ ]:

    

titanic[titanic['age']>20].sort_values('age').head()


    

In [ ]:

    

titanic['fare_2018']=titanic['fare']*26.62


    

In [ ]:

    

titanic[['name','age','fare','fare_2018']].sort_values('fare',ascending=False).head()


    

In [ ]:

    

titanic['age'].isnull().sum()


    

In [ ]:

    

average_age = titanic['age'].mean()
titanic['corrected_age']=titanic['age'].fillna(average_age)
titanic['corrected_age'].isnull().sum()


    

In [ ]:

    

titanic['sex'].value_counts()


    

In [ ]:

    

titanic.groupby('sex')['survived'].sum()


    

In [ ]:

    

# titanic.to_excel('new_titanic_data.xls')


    

In [ ]:

    

titanic.groupby(["sex", "pclass"]).mean()


    

In [ ]:

    

titanic[titanic["age"]<18].groupby(["sex", "pclass"]).mean()


    

In [ ]: