In [1]:

    

import requests
from StringIO import StringIO
from numpy import nan as NA
import pandas as pd
import zipfile
import re
%matplotlib inline
import matplotlib.pyplot as plt
import xlrd
import statsmodels.api as sm
from patsy import dmatrices, dmatrix
import scipy as scipy
import numpy as np


    

In [2]:

    

ls


    

    




datas/
indexplay.ipynb
learningaboutindexing.csv
LICENSE
pa_research_for_stata.csv
pa-research (herrison's conflicted copy 2015-06-17).ipynb
pa-research.ipynb
README.md
requirements.txt
Untitled.ipynb

In [3]:

    

cd datas/


    

    




/home/sam/Dropbox/Documents/pa-research/datas

In [5]:

    

df = pd.read_csv('T201501PDPI+BNFT.CSV')


    

In [6]:

    

df.head()


    

    
Out[6]:






  

    

      

      
SHA
      
PCT
      
PRACTICE
      
BNF CODE
      
BNF NAME
      
ITEMS
      
NIC
      
ACT COST
      
QUANTITY
      
PERIOD
      

    
  
  

    

      
0
      
Q44
      
RXA
      
N81646
      
0102000N0AAABAB
      
Hyoscine Butylbrom_Tab 10mg
      
1
      
1.13
      
1.16
      
21
      
201501
      

    
    

      
1
      
Q44
      
RXA
      
N81646
      
0401010Z0AAAAAA
      
Zopiclone_Tab 7.5mg
      
15
      
3.28
      
4.72
      
57
      
201501
      

    
    

      
2
      
Q44
      
RXA
      
N81646
      
0401020K0AAAHAH
      
Diazepam_Tab 2mg
      
35
      
99.91
      
104.64
      
2662
      
201501
      

    
    

      
3
      
Q44
      
RXA
      
N81646
      
040201060AAALAL
      
Olanzapine_Tab 15mg
      
3
      
1.29
      
1.53
      
21
      
201501
      

    
    

      
4
      
Q44
      
RXA
      
N81646
      
0403010B0AAAHAH
      
Amitriptyline HCl_Tab 25mg
      
16
      
1.52
      
3.20
      
38
      
201501
      

    
  

In [ ]: