In [3]:

    

%matplotlib inline
import matplotlib.pyplot as plt
import pandas as pd


    

In [12]:

    

names = pd.read_csv("../../data/names.txt", header=None)
names.columns = ["name"]
names["length"] = names["name"].apply(lambda name: len(name))

names.head()


    

    
Out[12]:







  

    

      

      
name
      
length
    
  
  

    

      
0
      
barjraj
      
7
    
    

      
1
      
ramdin verma
      
12
    
    

      
2
      
sharat chandran
      
15
    
    

      
3
      
birender mandal
      
15
    
    

      
4
      
amit
      
4
    
  

In [13]:

    

names.describe()


    

    
Out[13]:







  

    

      

      
length
    
  
  

    

      
count
      
30172.000000
    
    

      
mean
      
9.220900
    
    

      
std
      
4.850825
    
    

      
min
      
2.000000
    
    

      
25%
      
6.000000
    
    

      
50%
      
8.000000
    
    

      
75%
      
12.000000
    
    

      
max
      
54.000000
    
  

In [55]:

    

plt.hist(names["length"], bins=[i for i in range(30)], rwidth=0.9, facecolor='green', alpha=0.75)
plt.title("Name Length Distribution")
plt.xlabel("Length")
plt.ylabel("#Names")


    

    
Out[55]:





<matplotlib.text.Text at 0x7f278970ac50>






    

In [ ]: