PranjalDureja0002
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 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 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 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() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| train_d_inpatient['whether_admitted'] = 1 | |
| train_d_outpatient['whether_admitted'] = 0 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 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() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 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() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| s1 = outpatient_data['InscClaimAmtReimbursed'].value_counts() | |
| s_s1 = sum(s1.tolist()) | |
| s2 = inpatient_data['InscClaimAmtReimbursed'].value_counts() | |
| s_s2 = sum(s2.tolist()) | |
| outpatient_data["amountgrp"]=pd.cut(outpatient_data.InscClaimAmtReimbursed, [0,50,100,200,400,600,800,1000,1500,2000]) | |
| inpatient_data["amountgrp"]=pd.cut(inpatient_data.InscClaimAmtReimbursed, [0,2000,4000,6000,8000,10000,12000,14000,16000]) | |
| plt.style.use('fivethirtyeight') | |
| counts = outpatient_data.groupby(['amountgrp', 'PotentialFraud']).InscClaimAmtReimbursed.count().unstack() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| rcParams['figure.figsize'] = 5,5 | |
| sns.kdeplot(outpatient_data['InscClaimAmtReimbursed'],shade=True,color='green',legend=False) | |
| plt.title('InscClaimAmtReimbursed in Outpatient') | |
| plt.xlabel('InscClaimAmtReimbursed') | |
| plt.show() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| rcParams['figure.figsize'] = 5,5 | |
| sns.kdeplot(inpatient_data['InscClaimAmtReimbursed'],shade=True,color='green',legend=False) | |
| plt.title('InscClaimAmtReimbursed in inpatient') | |
| plt.xlabel('InscClaimAmtReimbursed') | |
| plt.show() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| outpatient_data["age_group"]=pd.cut(outpatient_data.Age, [30,40,50,60,70,80,90,100]) | |
| inpatient_data["age_group"]=pd.cut(inpatient_data.Age, [30,40,50,60,70,80,90,100]) | |
| fraud_count = outpatient_data['PotentialFraud'].value_counts().to_dict() | |
| outpatient_data['fraud_Count']=outpatient_data['PotentialFraud'].map(age_count) | |
| s1 = inpatient_data['Gender'].value_counts() | |
| s_s1 = sum(s1.tolist()) | |
| s2 = outpatient_data['Gender'].value_counts() |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| age_count = inpatient_data['Age'].value_counts().to_dict() | |
| inpatient_data['Age_Count']=inpatient_data['Age'].map(age_count) | |
| sns.violinplot(x='PotentialFraud',y='Age', data=inpatient_data,width=0.5) | |
| plt.xlabel('potential fraud') | |
| plt.ylabel('Age_of_patients') | |
| plt.title('Age_of_patients vs frauds') | |
| sns.violinplot(x='PotentialFraud',y='Gender', data=inpatient_data,width=0.5) | |
| plt.xlabel('potential fraud') |