Generate a CSV file showing how many lines of transcription each user has submitted

shax-total-lines-per-user.py

import csv
import json
import sys

csv.field_size_limit(sys.maxsize)

line_count = {}

with open('shakespeares-world-classifications.csv') as f:
    r = csv.DictReader(f)

    for row in r:
        if row['user_name'].startswith('not-logged-in-'):
            continue

        line_count.setdefault(row['user_name'], 0)

        for annotation in json.loads(row['annotations']):
            if annotation.get('task') != 'T2':
                continue
            line_count[row['user_name']] += len(annotation.get('value', []))

with open('shakespeares-world-line-counts-per-user.csv', 'w') as f:
    w = csv.writer(f)
    w.writerow(('username', 'total lines transcribed'))

    for user, count in line_count.items():
        w.writerow((user, count))