Create csv file with 4 columns for process mining

[thomaskissas33]

Hello
I try little to work with python and process mining. so i try to create a file from a text with 4 columns case id , name, process and time but my problem is that my code put it on same column on csv - excel file wich i dont want it. I want to put them on 4 different columns and same the titles.

import re
import pandas as pd

# Sample text paragraph (replace with your actual text)
text_paragraph = """
Character: Maria
Case1 - 2023-11-01 09:00 AM: Started the process
Character: George
Case2 - 2023-11-01 10:30 AM: Joined the project
Character: Maria
Case1 - 2023-11-01 11:45 AM: Continued working
Character: George
Case2 - 2023-11-01 12:15 PM: Left for a meeting
"""

# Initialize variables to store event data
event_data = {
    'Case ID': [],
    'Character': [],
    'Process': [],
    'Time': []
}

# Use regular expressions to extract character, case ID, process, and time information
event_pattern = r"(Character: (.+)|Case(\d+) - (\d{4}-\d{2}-\d{2} \d{2}:\d{2} [APM]{2}): (.+))"
matches = re.findall(event_pattern, text_paragraph)

current_character = None

for match in matches:
    character, case_id, timestamp, process = match[1], match[2], match[3], match[4]

    if character:
        current_character = character
    else:
        event_data['Character'].append(current_character)
        event_data['Case ID'].append(case_id)
        event_data['Time'].append(timestamp)
        event_data['Process'].append(process)

# Create a DataFrame from the event data
df = pd.DataFrame(event_data)

# Save the DataFrame as a CSV file
df.to_csv('process_mining_data_4_columns.csv', index=False)