In [15]:

    

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
names = pd.read_csv("yob1881.txt",names=["Name","Sex","Count"])
total_count = names["Count"].sum()
names['Prop'] = names['Count']/total_count
names.head()


    

    
Out[15]:






  

    

      

      
Name
      
Sex
      
Count
      
Prop
    
  
  

    

      
0
      
Mary
      
F
      
6919
      
0.035906
    
    

      
1
      
Anna
      
F
      
2698
      
0.014001
    
    

      
2
      
Emma
      
F
      
2034
      
0.010555
    
    

      
3
      
Elizabeth
      
F
      
1852
      
0.009611
    
    

      
4
      
Margaret
      
F
      
1658
      
0.008604
    
  

In [18]:

    

val = "names/yob2011.txt"


    

In [22]:

    

val.split("/")[1].split(".")[0].split("yob")[1]


    

    
Out[22]:





'2011'

In [28]:

    

file_data = pd.read_csv("yob1881.txt",names=["Name","Sex","Count"])


    

In [35]:

    

file_data["Name"].count()


    

    
Out[35]:





1935

In [38]:

    

res = names.append(file_data)


    

In [39]:

    

res.count()


    

    
Out[39]:





Count    3870
Name     3870
Prop     1935
Sex      3870
dtype: int64

In [40]:

    

res = pd.DataFrame()


    

In [41]:

    

res


    

    
Out[41]:

In [ ]: