Crime Rate Against Women Ver 2.0

Data from 'Data.gov.in'

File names:

>>crcCAW.CSV : `Number of Crime against women`
>>pacCAW.CSV : 'Number of Person Involved in Crime against Women'

Here In this Notebook we will separate all crimes against women according to category and remove all the rows about Total Crimes. and separate all the crimes in individual dataframe.. Hope we'll succed



In [2]:

    
#Lets now import necessary libraries which will help us
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt



In [3]:

    
crimes = pd.read_csv('crcCAW.csv')



In [5]:

    
crimes.head() #lets give it a look









    Out[5]:






  
    
      
      STATE/UT
      CRIME HEAD
      2001
      2002
      2003
      2004
      2005
      2006
      2007
      2008
      2009
      2010
      2011
      2012
    
  
  
    
      0
          ANDHRA PRADESH
       RAPE
       871
       1002
        946
       1016
        935
       1049
       1070
       1257
       1188
       1362
       1442
       1341
    
    
      1
       ARUNACHAL PRADESH
       RAPE
        33
         38
         31
         42
         35
         37
         48
         42
         59
         47
         42
         46
    
    
      2
                   ASSAM
       RAPE
       817
        970
       1095
       1171
       1238
       1244
       1437
       1438
       1631
       1721
       1700
       1716
    
    
      3
                   BIHAR
       RAPE
       888
       1040
        985
       1390
       1147
       1232
       1555
       1302
        929
        795
        934
        927
    
    
      4
            CHHATTISGARH
       RAPE
       959
        992
        898
        969
        990
        995
        982
        978
        976
       1012
       1053
       1034



In [16]:

    
pd.unique(crimes['CRIME HEAD']) # we got all crimes releated to women in the datframe now we can extract the crimes 
#pd.unique(df.values.ravel())









    Out[16]:





array(['RAPE', 'KIDNAPPING and ABDUCTION', 'DOWRY DEATHS',
       'ASSAULT ON WOMEN WITH INTENT TO OUTRAGE HER MODESTY',
       'INSULT TO THE MODESTY OF WOMEN',
       'CRUELTY BY HUSBAND OR HIS RELATIVES (IPC SECTION 498A)',
       'IMPORTATION OF GIRLS FROM FOREIGN COUNTRY',
       'IMMORAL TRAFFIC (P) ACT', 'DOWRY PROHIBITION ACT',
       'INDECENT REPRESENTATION OF WOMEN (P) ACT',
       'COMMISSION OF SATI PREVENTION ACT', 'TOTAL CRIMES AGAINST WOMEN'], dtype=object)

lets extract all rapes releated crime first

as we did it in previous version

First we will remove all the entries releated to Total of the crimes as we don't want total now



In [28]:

    
#df = df[df.line_race != 0] this is we are going to do to remove the total entries
crimes_ver1 = crimes[crimes['CRIME HEAD']!='TOTAL CRIMES AGAINST WOMEN']



In [29]:

    
crimes_ver2 =  crimes_ver1[crimes_ver1['STATE/UT']!='TOTAL (ALL-INDIA)']



In [31]:

    
crimes_ver3 = crimes_ver2[crimes_ver2['STATE/UT']!='TOTAL (STATES)']



In [34]:

    
crimes_ver4 =  crimes_ver3[crimes_ver3['STATE/UT']!='TOTAL (UTs)']



In [36]:

    
crimes_ver4.to_csv('crimescleaned.csv')

Now we have a cleaned data with no data named Total crimes and total states and total(all india) or total(all ut)



In [46]:

    
name = 'kartik'
import os
DIR_PATH = os.path.abspath
DIR_



In [49]:

    
os.walk(',')









    Out[49]:





<generator object walk at 0x02C6AFD0>



In [ ]:

	STATE/UT	CRIME HEAD	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012
0	ANDHRA PRADESH	RAPE	871	1002	946	1016	935	1049	1070	1257	1188	1362	1442	1341
1	ARUNACHAL PRADESH	RAPE	33	38	31	42	35	37	48	42	59	47	42	46
2	ASSAM	RAPE	817	970	1095	1171	1238	1244	1437	1438	1631	1721	1700	1716
3	BIHAR	RAPE	888	1040	985	1390	1147	1232	1555	1302	929	795	934	927
4	CHHATTISGARH	RAPE	959	992	898	969	990	995	982	978	976	1012	1053	1034