We're going to check the quality of the a new data set...

Download the data file from /home/data/kelleher/MotorInsuranceFraudClaimABTFull.csv



In [2]:

    
import os, sys
import numpy as np
import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt



In [3]:

    
df = pd.read_csv('/home/data/kelleher/MotorInsuranceFraudClaimABTFull.csv')
df.head()









    Out[3]:






  
    
      
      ID
      Insurance Type
      Income of Policy Holder
      Marital Status
      Num Claimants
      Injury Type
      Overnight Hospital Stay
      Claim Amount
      Total Claimed
      Num Claims
      Num Soft Tissue
      % Soft Tissue
      Claim Amount Received
      Fraud Flag
    
  
  
    
      0
      1
      CI
      0
      NaN
      2
      Soft Tissue
      No
      1625
      3250
      2
      2.0
      1.0
      0
      1
    
    
      1
      2
      CI
      0
      NaN
      2
      Back
      Yes
      15028
      60112
      1
      0.0
      0.0
      15028
      0
    
    
      2
      3
      CI
      54613
      Married
      1
      Broken Limb
      No
      -99999
      0
      0
      0.0
      0.0
      572
      0
    
    
      3
      4
      CI
      0
      NaN
      3
      Serious
      Yes
      270200
      0
      0
      0.0
      0.0
      270200
      0
    
    
      4
      5
      CI
      0
      NaN
      4
      Soft Tissue
      No
      8869
      0
      0
      0.0
      0.0
      0
      1



In [4]:

    
df.shape









    Out[4]:





(500, 14)



In [ ]:



In [ ]:



In [ ]:



In [ ]:



In [4]:

    
df.describe()









    Out[4]:






  
    
      
      ID
      Income of Policy Holder
      Num Claimants
      Claim Amount
      Total Claimed
      Num Claims
      Num Soft Tissue
      % Soft Tissue
      Claim Amount Received
      Fraud Flag
    
  
  
    
      count
      500.000000
      500.000000
      500.000000
      500.00000
      500.00000
      500.000000
      490.000000
      500.000000
      500.000000
      500.000000
    
    
      mean
      250.500000
      13739.994000
      1.908000
      16373.20400
      9597.18600
      0.798000
      0.234694
      0.172012
      13051.942000
      0.336000
    
    
      std
      144.481833
      20081.535489
      1.012713
      29426.27696
      35655.68622
      2.666724
      0.589635
      0.428015
      30547.194864
      0.472812
    
    
      min
      1.000000
      0.000000
      1.000000
      -99999.00000
      0.00000
      0.000000
      0.000000
      0.000000
      0.000000
      0.000000
    
    
      25%
      125.750000
      0.000000
      1.000000
      3322.25000
      0.00000
      0.000000
      0.000000
      0.000000
      0.000000
      0.000000
    
    
      50%
      250.500000
      0.000000
      2.000000
      5663.00000
      0.00000
      0.000000
      0.000000
      0.000000
      3253.500000
      0.000000
    
    
      75%
      375.250000
      33918.500000
      3.000000
      12245.50000
      11282.75000
      1.000000
      0.000000
      0.000000
      8191.750000
      1.000000
    
    
      max
      500.000000
      71284.000000
      4.000000
      270200.00000
      729792.00000
      56.000000
      5.000000
      2.000000
      295303.000000
      1.000000



In [ ]:



In [ ]:



In [ ]:



In [ ]:



In [ ]:



In [ ]:



In [5]:

    
df.boxplot(column='Claim Amount', by='Injury Type')









    Out[5]:





<matplotlib.axes._subplots.AxesSubplot at 0x3bfb150>

	ID	Insurance Type	Income of Policy Holder	Marital Status	Num Claimants	Injury Type	Overnight Hospital Stay	Claim Amount	Total Claimed	Num Claims	Num Soft Tissue	% Soft Tissue	Claim Amount Received	Fraud Flag
0	1	CI	0	NaN	2	Soft Tissue	No	1625	3250	2	2.0	1.0	0	1
1	2	CI	0	NaN	2	Back	Yes	15028	60112	1	0.0	0.0	15028	0
2	3	CI	54613	Married	1	Broken Limb	No	-99999	0	0	0.0	0.0	572	0
3	4	CI	0	NaN	3	Serious	Yes	270200	0	0	0.0	0.0	270200	0
4	5	CI	0	NaN	4	Soft Tissue	No	8869	0	0	0.0	0.0	0	1

	ID	Income of Policy Holder	Num Claimants	Claim Amount	Total Claimed	Num Claims	Num Soft Tissue	% Soft Tissue	Claim Amount Received	Fraud Flag
count	500.000000	500.000000	500.000000	500.00000	500.00000	500.000000	490.000000	500.000000	500.000000	500.000000
mean	250.500000	13739.994000	1.908000	16373.20400	9597.18600	0.798000	0.234694	0.172012	13051.942000	0.336000
std	144.481833	20081.535489	1.012713	29426.27696	35655.68622	2.666724	0.589635	0.428015	30547.194864	0.472812
min	1.000000	0.000000	1.000000	-99999.00000	0.00000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	125.750000	0.000000	1.000000	3322.25000	0.00000	0.000000	0.000000	0.000000	0.000000	0.000000
50%	250.500000	0.000000	2.000000	5663.00000	0.00000	0.000000	0.000000	0.000000	3253.500000	0.000000
75%	375.250000	33918.500000	3.000000	12245.50000	11282.75000	1.000000	0.000000	0.000000	8191.750000	1.000000
max	500.000000	71284.000000	4.000000	270200.00000	729792.00000	56.000000	5.000000	2.000000	295303.000000	1.000000