Hospital Quality Reports Analysis

# XML Analysis Script for Hospital Quality Reports
import os
import xml.etree.ElementTree as ET
import pandas as pd

# Directory paths
input_dir = "/Users/alikhosravi/Desktop/XLMNEW/xml_2023"
output_dir = "/Users/alikhosravi/Desktop/XLMNEW/Result/2. Structure/XML file structure"

# Initialize data structures
tag_inventory = {}
hospital_data = []

# Process each XML file
for filename in os.listdir(input_dir):
    if filename.endswith(".xml"):
        filepath = os.path.join(input_dir, filename)
        tree = ET.parse(filepath)
        root = tree.getroot()
        
        # Extract hospital information
        hospital = {
            'name': root.find('hospital/name').text,
            'ik_code': root.find('hospital/ik_code').text,
            'location': root.find('hospital/address/city').text
        }
        hospital_data.append(hospital)
        
        # Build tag inventory
        for elem in root.iter():
            tag_path = ' > '.join([e.tag for e in elem.findall('./ancestor-or-self::*')])
            tag_inventory[tag_path] = tag_inventory.get(tag_path, 0) + 1

# Save results
pd.DataFrame(hospital_data).to_excel(os.path.join(output_dir, 'hospital_info.xlsx'))
pd.DataFrame(list(tag_inventory.items()), columns=['Tag_Path', 'Count']).to_csv(
    os.path.join(output_dir, 'tag_inventory.csv'), index=False)

<?xml version="1.0" encoding="UTF-8"?>
<hospital_report>
  <hospital>
    <info>
      <name>Charité - Universitätsmedizin Berlin</name>
      <ik_code>260500499</ik_code>
      <address>
        <street>Charitéplatz 1</street>
        <city>Berlin</city>
        <zip>10117</zip>
      </address>
    </info>
    <services>
      <department name="Cardiology" beds="120"/>
      <department name="Neurology" beds="85"/>
    </services>
    <quality_indicators>
      <indicator name="Patient Satisfaction" value="92.5"/>
      <indicator name="Readmission Rate" value="8.2"/>
    </quality_indicators>
  </hospital>
</hospital_report>