الذاكرة والإدخال والمعالجة المجزأة المحدودة

from io import StringIO
import pandas as pd

source = StringIO('units\n1\n2\n3\n4\n')
partials = []
for chunk in pd.read_csv(source, usecols=['units'], dtype={'units': 'Int64'}, chunksize=2):
    partials.append((int(chunk['units'].sum()), int(chunk['units'].count())))
total = sum(partial[0] for partial in partials)
count = sum(partial[1] for partial in partials)
assert (total, count) == (10, 4)
print(total / count)

2.5

المتوقع 2.5 لأربع قيم مرصودة؛ ولم يختبر قارئ pandas أو ذاكرته.

partials = [(10, 2), (90, 1)]
combined = sum(total for total, _ in partials) / sum(count for _, count in partials)
mean_of_means = sum(total / count for total, count in partials) / len(partials)
assert round(combined, 2) == 33.33
assert mean_of_means == 47.5
print(f'{combined:.2f} {mean_of_means:.2f}')

33.33 47.50

33.33 المتوسط المجمع المقرب؛ وتزن 47.50 الأجزاء غير المتساوية بالتساوي وتجيب سؤالاً آخر.