Telegram top authors by message per day

jq.sh

jq '
  [ 
    .messages[] | 
    {from, date} | 
    select(.from != null) 
  ] | 
  group_by(.from) | 
  map({ 
    from: .[0].from, 
    count: length, 
    firstDate: (map(.date) | sort | .[0])
  })
' export.json >authors.json
python3 output.py authors.json 

output.py

import json
import csv
from datetime import datetime, timedelta

# Load the JSON output from jq
with open('authors.json', 'r') as file:
    authors = json.load(file)

# Current date
current_date = datetime.now().date()

# Calculate days span and average messages per day
for author in authors:
    first_date = datetime.strptime(author['firstDate'], '%Y-%m-%dT%H:%M:%S').date()
    days_span = (current_date - first_date).days + 1  # Adding 1 to include the first day
    author['avgMessagesPerDay'] = author['count'] / days_span

# Sort authors by avgMessagesPerDay
authors_sorted = sorted(authors, key=lambda x: x['avgMessagesPerDay'], reverse=True)

# Define CSV file name
csv_file_name = 'authors_avg_messages_per_day.csv'

# Define CSV headers
headers = ['from', 'avgMessagesPerDay']

# Write data to CSV
with open(csv_file_name, mode='w', newline='') as file:
    writer = csv.DictWriter(file, fieldnames=headers)

    # Write the header
    writer.writeheader()

    # Write each author's data
    for author in authors_sorted:
        # Ensure to round the avgMessagesPerDay or format it as desired
        author['avgMessagesPerDay'] = round(author['avgMessagesPerDay'], 2)
        writer.writerow({'from': author['from'], 'avgMessagesPerDay': author['avgMessagesPerDay']})

print(f"CSV file '{csv_file_name}' created successfully.")