eda

eda.py

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()