automod_stat.py

import requests
import json
from tqdm import tqdm
from concurrent.futures import ThreadPoolExecutor, as_completed

url = "https://api.wikimedia.org/service/lw/inference/v1/models/revertrisk-language-agnostic:predict"
headers = {
    'Content-Type': 'application/json',
}
INTERVAL = 100000
end_rev_id = 85706740
start_rev_id = end_rev_id - INTERVAL + 1
max_threads = 50

high_probability_revisions = []

def fetch_prediction(rev_id):
    payload = {
        "rev_id": rev_id,
        "lang": "zh"
    }
    try:
        response = requests.post(url, headers=headers, data=json.dumps(payload))
        if response.status_code == 200:
            data = response.json()
            true_prob = data['output']['probabilities']['true']
            false_prob = data['output']['probabilities']['false']
            rev_url = f"https://zh.wikipedia.org/w/index.php?oldid={rev_id}"

            result = {
                'rev_id': rev_id,
                'true_prob': true_prob,
                'false_prob': false_prob,
                'url': rev_url,
            }

            # 'very-cautious' => 0.990,
            # 'cautious' => 0.985,
            # 'somewhat-cautious' => 0.980,
            # 'less-cautious' => 0.975

            if true_prob >= 0.99:
                return result
        else:
            return None

    except Exception as e:
        return None

with ThreadPoolExecutor(max_workers=max_threads) as executor:
    futures = {executor.submit(fetch_prediction, rev_id): rev_id for rev_id in range(start_rev_id, end_rev_id + 1)}

    for future in tqdm(as_completed(futures), total=len(futures), desc="Querying revisions", unit="rev_id"):
        result = future.result()
        if result:
            high_probability_revisions.append(result)

if high_probability_revisions:
    print("\nRevisions with true probability >= 0.99:")
    for item in high_probability_revisions:
        print(f"Rev ID: {item['rev_id']}, True Probability: {item['true_prob']}, False Probability: {item['false_prob']}, URL: {item['url']}")
else:
    print("\nNo revisions found with true probability >= 0.99.")