PranjalDureja0002

colors_list = ['#5bc0de','#d9534f']
plt.title("Potential Fraud distribution")
ax = patient_data['PotentialFraud'].value_counts().plot(kind='bar', figsize=(5,5), width=0.8,color = colors_list)
total = len(patient_data['PotentialFraud'])
for p in ax.patches:
        percentage = '{:.1f}%'.format(100 * p.get_height()/total)        
        x = p.get_x() + p.get_width() - 0.5
        y = p.get_y() + p.get_height()
        ax.annotate(percentage, (x, y))
plt.xlabel('Potential_Fraud')

PranjalDureja0002

How do we know whether the services billed were actually performed? Is the actual patient listed and whether the eligibility is verified? Incorrect reporting of diagnoses or procedures …Or What?

PranjalDureja0002

patient_data_io = pd.merge(train_d_inpatient, train_d_outpatient, left_on = [ col for col in train_d_outpatient.columns if col in train_d_inpatient.columns], \
                    right_on = [ col for col in train_d_outpatient.columns if col in train_d_inpatient.columns], how = 'outer')

patient_data = pd.merge(patient_data_io,train_d_beneficiary,how='inner',on='BeneID' ).\
              merge(label_d_data,how='outer',on='Provider')
                    

PranjalDureja0002

per_miss_values = patient_data.isnull().sum() * 100 / len(patient_data)

PranjalDureja0002

per_miss_values = patient_data.isnull().sum() * 100 / len(patient_data)

PranjalDureja0002

BeneID                               0.000000
ClaimID                              0.000000
ClaimStartDt                         0.000000
ClaimEndDt                           0.000000
Provider                             0.000000
InscClaimAmtReimbursed               0.000000
AttendingPhysician                   0.270149
OperatingPhysician                  79.497538
OtherPhysician                      64.218548
AdmissionDt                         92.749337

PranjalDureja0002

colors_list = ['#5bc0de','#d9534f']
plt.title("Potential Fraud distribution")
ax = patient_data['PotentialFraud'].value_counts().plot(kind='bar', figsize=(5,5), width=0.8,color = colors_list)
total = len(patient_data['PotentialFraud'])
for p in ax.patches:
        percentage = '{:.1f}%'.format(100 * p.get_height()/total)        
        x = p.get_x() + p.get_width() - 0.5
        y = p.get_y() + p.get_height()
        ax.annotate(percentage, (x, y))
plt.xlabel('Potential_Fraud')

PranjalDureja0002

physician_count = outpatients_['AttendingPhysician'].value_counts().to_dict()
outpatients_['physician_count']=outpatients_['AttendingPhysician'].map(physician_count)

physician_count = inpatients_['AttendingPhysician'].value_counts().to_dict()
inpatients_['physician_count']=inpatients_['AttendingPhysician'].map(physician_count)

ax = sns.countplot(y='AttendingPhysician',data=outpatients_,hue='PotentialFraud',order = outpatients_['AttendingPhysician'].value_counts().head(20).index)
d1 = outpatients_['AttendingPhysician'].value_counts().to_dict()
s_s1 = sum(list(d1.values()))
for p in ax.patches:

PranjalDureja0002

plt.figure(figsize=(15, 9))
sns.pointplot(x = outpatients_.physician_count, y = outpatients_.id_Count,hue=outpatients_.PotentialFraud)
plt.suptitle('Physician_attended vs Beneficiaries_count\n')

sns.pointplot(x = inpatients_.physician_count, y = inpatients_.id_Count,hue=inpatients_.PotentialFraud)
plt.suptitle('Physician_attended vs Beneficiaries_count\n')
plt.show()

PranjalDureja0002

inpatient_data['Admission_Date'] = pd.to_datetime(inpatient_data['AdmissionDt'] , format = '%Y-%m-%d')
inpatient_data['Discharge_Date'] = pd.to_datetime(inpatient_data['DischargeDt'],format = '%Y-%m-%d')

inpatient_data['ClaimStart_Date'] = pd.to_datetime(inpatient_data['ClaimStartDt'] , format = '%Y-%m-%d')
inpatient_data['ClaimEnd_Date'] = pd.to_datetime(inpatient_data['ClaimEndDt'],format = '%Y-%m-%d')

inpatient_data['DOB'] = pd.to_datetime(inpatient_data['DOB'] , format = '%Y-%m-%d')
inpatient_data['DOD'] = pd.to_datetime(inpatient_data['DOD'],format = '%Y-%m-%d')
inpatient_data['Age'] = round(((inpatient_data['ClaimStart_Date'] - inpatient_data['DOB']).dt.days + 1)/365.25)