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)

PranjalDureja0002

ClmProcedureCode_1_count = patient_data['ClmProcedureCode_1'].value_counts().to_dict()
patient_data['ClmProcedureCode_1_count']=patient_data['ClmProcedureCode_1'].map(ClmProcedureCode_1_count)

ClmProcedureCode_2_count = patient_data['ClmProcedureCode_2'].value_counts().to_dict()
patient_data['ClmProcedureCode_2_count']=patient_data['ClmProcedureCode_2'].map(ClmProcedureCode_2_count)

ClmProcedureCode_3_count = patient_data['ClmProcedureCode_3'].value_counts().to_dict()
patient_data['ClmProcedureCode_3_count']=patient_data['ClmProcedureCode_3'].map(ClmProcedureCode_3_count)

ClmDiagnosisCode_1_count = patient_data['ClmDiagnosisCode_1'].value_counts().to_dict()

PranjalDureja0002

col_to_remove = ['Provider','BeneID', 'ClaimID', 'ClaimStartDt','ClaimEndDt','AttendingPhysician',\
                 'OperatingPhysician', 'OtherPhysician','ClmAdmitDiagnosisCode','NoOfMonths_PartACov',\
                 'NoOfMonths_PartBCov','DiagnosisGroupCode','AdmissionDt','DischargeDt']
diagnosis_codes = ['ClmDiagnosisCode_1', 'ClmDiagnosisCode_2', 'ClmDiagnosisCode_3',
       'ClmDiagnosisCode_4', 'ClmDiagnosisCode_5', 'ClmDiagnosisCode_6',
       'ClmDiagnosisCode_7', 'ClmDiagnosisCode_8', 'ClmDiagnosisCode_9',
       'ClmDiagnosisCode_10']

procedure_codes = ['ClmProcedureCode_1','ClmProcedureCode_2','ClmProcedureCode_3','ClmProcedureCode_4','ClmProcedureCode_5','ClmProcedureCode_6']
oth_cols = ['DOB','DOD','Claim_Start','Claim_Start','Admission_Date','Admission_Date','Claim_End','Discharge_Date']

PranjalDureja0002

min_max_scaler = preprocessing.MinMaxScaler()
def scale_fun(X_train,X_test,col):   
    min_max_scaler.fit(X_train[col].values.reshape(-1,1))
    
    X_train_=min_max_scaler.transform(X_train[col].values.reshape(-1,1))
    X_test_=min_max_scaler.transform(X_test[col].values.reshape(-1,1))
    
    return X_train_,X_test_

for col in X_train.columns:

PranjalDureja0002

parameters = {'max_depth':[1, 5, 10, 20, 50],
              'min_samples_split':[5, 10, 100, 500]}

dt = DecisionTreeClassifier()

dt_grid = GridSearchCV(dt, param_grid=parameters, n_jobs=-1, verbose=1,scoring='f1_macro',cv=3,return_train_score=True)
dt_grid.fit(X_train,y_train)

best_depth=dt_grid.best_params_['max_depth']
best_samples=dt_grid.best_params_['min_samples_split']