PranjalDureja0002

patient_df = pd.DataFrame(columns = ['Diagnosis_data'])
patient_df['Diagnosis_data'] = pd.concat([patient_data["ClmDiagnosisCode_1"],patient_data["ClmDiagnosisCode_2"],patient_data["ClmDiagnosisCode_3"],patient_data["ClmDiagnosisCode_4"],patient_data["ClmDiagnosisCode_5"],patient_data["ClmDiagnosisCode_6"],patient_data["ClmDiagnosisCode_7"],patient_data["ClmDiagnosisCode_8"],patient_data["ClmDiagnosisCode_9"],patient_data["ClmDiagnosisCode_10"]],axis=0)
patient_df = patient_df.dropna()

plt.figure(figsize=(10, 7))
patient_df['Diagnosis_data'].value_counts().head(30).plot(x=patient_df['Diagnosis_data'] , kind = 'bar' , color = 'blue')
plt.title('Diagnosis Codes vs Count')
plt.xlabel('Diagnosis Codes')
plt.show()

PranjalDureja0002

patient_df = pd.DataFrame(columns = ['Procedure_data'])
patient_df['Procedure_data'] = pd.concat([patient_data["ClmProcedureCode_1"],patient_data["ClmProcedureCode_2"],patient_data["ClmProcedureCode_3"],patient_data["ClmProcedureCode_4"],patient_data["ClmProcedureCode_5"],patient_data["ClmProcedureCode_6"]],axis=0)
patient_df = patient_df.dropna()

plt.figure(figsize=(10, 7))
patient_df['Procedure_data'].value_counts().head(30).plot(x=patient_df['Procedure_data'] , kind = 'bar' , color = 'purple')
plt.title('Procedure Codes vs Count')
plt.xlabel('Procedure Codes')
plt.show()

PranjalDureja0002

train_d_inpatient['whether_admitted'] = 1
train_d_outpatient['whether_admitted'] = 0

PranjalDureja0002

att_physician_count = patient_data['AttendingPhysician'].value_counts().to_dict()
patient_data['attend_physician_count']=patient_data['AttendingPhysician'].map(att_physician_count)

oper_physician_count = patient_data['OperatingPhysician'].value_counts().to_dict()
patient_data['operate_physician_count']=patient_data['OperatingPhysician'].map(oper_physician_count)

ben_count = patient_data['BeneID'].value_counts().to_dict()
patient_data['BeneID_count']=patient_data['BeneID'].map(ben_count)

prov_count = patient_data['Provider'].value_counts().to_dict()

PranjalDureja0002

patient_data['Claim_Start'] = pd.to_datetime(patient_data['ClaimStartDt'] , format = '%Y-%m-%d')
patient_data['Claim_End'] = pd.to_datetime(patient_data['ClaimEndDt'],format = '%Y-%m-%d')

patient_data['DOB'] = pd.to_datetime(patient_data['DOB'] , format = '%Y-%m-%d')
patient_data['DOD'] = pd.to_datetime(patient_data['DOD'],format = '%Y-%m-%d')

patient_data['Claim_Days'] = ((patient_data['Claim_End'] - patient_data['Claim_Start']).dt.days) + 1

PranjalDureja0002

patient_data['Admission_Date'] = pd.to_datetime(patient_data['AdmissionDt'] , format = '%Y-%m-%d')
patient_data['Discharge_Date'] = pd.to_datetime(patient_data['DischargeDt'],format = '%Y-%m-%d')
patient_data['hospitalization_days'] = ((patient_data['Discharge_Date'] - patient_data['Admission_Date']).dt.days) + 1

PranjalDureja0002

reimb_amount = patient_data['IPAnnualReimbursementAmt'] + patient_data['OPAnnualReimbursementAmt']
deduct_amount = patient_data['IPAnnualDeductibleAmt'] + patient_data['OPAnnualDeductibleAmt']
patient_data['total_diff_amount'] = reimb_amount - deduct_amount

PranjalDureja0002

diagnosis_codes = patient_data[['ClmDiagnosisCode_1', 'ClmDiagnosisCode_2', 'ClmDiagnosisCode_3',
       'ClmDiagnosisCode_4', 'ClmDiagnosisCode_5', 'ClmDiagnosisCode_6',
       'ClmDiagnosisCode_7', 'ClmDiagnosisCode_8', 'ClmDiagnosisCode_9',
       'ClmDiagnosisCode_10']]

procedure_codes = patient_data[['ClmProcedureCode_1','ClmProcedureCode_2','ClmProcedureCode_3','ClmProcedureCode_4','ClmProcedureCode_5','ClmProcedureCode_6']]

Seven_diag_codes = ['4019','25000','2724','V5869','4011','42731','V5861']  # from EDA    

patient_df = pd.DataFrame(columns = ['procedure'])

PranjalDureja0002

patient_data['is_primary'] = np.where(patient_data['AttendingPhysician'].notnull(),1,0)
patient_data['is_secondary'] = np.where(patient_data['OperatingPhysician'].notnull(),1,0)
patient_data['is_tertiary'] = np.where(patient_data['OtherPhysician'].notnull(),1,0)

PranjalDureja0002

patient_data['PotentialFraud'] = np.where(patient_data['PotentialFraud']=='Yes',1,0)
patient_data['RenalDiseaseIndicator'] = np.where(patient_data['RenalDiseaseIndicator']=='Y',1,0)