In [8]:

    

import pandas as pd
import numpy as np
import matplotlib as plt

df = pd.read_csv("~/Downloads/train.csv")
df.describe()


    

    
Out[8]:






  

    

      

      
PassengerId
      
Survived
      
Pclass
      
Age
      
SibSp
      
Parch
      
Fare
    
  
  

    

      
count
      
891.000000
      
891.000000
      
891.000000
      
714.000000
      
891.000000
      
891.000000
      
891.000000
    
    

      
mean
      
446.000000
      
0.383838
      
2.308642
      
29.699118
      
0.523008
      
0.381594
      
32.204208
    
    

      
std
      
257.353842
      
0.486592
      
0.836071
      
14.526497
      
1.102743
      
0.806057
      
49.693429
    
    

      
min
      
1.000000
      
0.000000
      
1.000000
      
0.420000
      
0.000000
      
0.000000
      
0.000000
    
    

      
25%
      
223.500000
      
0.000000
      
2.000000
      
20.125000
      
0.000000
      
0.000000
      
7.910400
    
    

      
50%
      
446.000000
      
0.000000
      
3.000000
      
28.000000
      
0.000000
      
0.000000
      
14.454200
    
    

      
75%
      
668.500000
      
1.000000
      
3.000000
      
38.000000
      
1.000000
      
0.000000
      
31.000000
    
    

      
max
      
891.000000
      
1.000000
      
3.000000
      
80.000000
      
8.000000
      
6.000000
      
512.329200
    
  

In [13]:

    

df['Age'].median()


    

    
Out[13]:





28.0

In [14]:

    

df['Sex'].unique()


    

    
Out[14]:





array(['male', 'female'], dtype=object)

In [17]:

    

fig = plt.pyplot.figure()
ax = fig.add_subplot(111)
ax.hist(df['Age'], bins=10, range = (df['Age'].min(), df['Age'].max()))
plt.pyplot.title('Age Distribution')
plt.pyplot.xlabel('Age')
plt.pyplot.ylabel('Passenger Count')
plt.pyplot.show()


    

In [ ]:

    

source = "http://www.analyticsvidhya.com/blog/2014/08/baby-steps-python-performing-exploratory-analysis-python/"