Get revscoring draftquality prediction

POST	`/service/lw/inference/v1/models/{wiki}-draftquality:predict`

Get a score from the Revscoring Draft Quality model (previously hosted on ORES) for a given Wiki revision id.

Examples

curl

Anonymous access

# Get a score from the Revscoring Draft Quality model for the revision 12345 of English Wikipedia.
$ curl https://api.wikimedia.org/service/lw/inference/v1/models/enwiki-draftquality:predict -X POST -d '{"rev_id": 12345}'

Logged in access

# Get a score from the Revscoring Draft Quality model for the revision 12345 of English Wikipedia.
$ curl https://api.wikimedia.org/service/lw/inference/v1/models/enwiki-draftquality:predict -X POST -d '{"rev_id": 12345}' -H "Authorization: Bearer YOUR_ACCESS_TOKEN"

Python

# Python 3
# Get a score from the Revscoring Draft Quality model for the revision 12345 of English Wikipedia.

import json
import requests

use_auth = False
inference_url = 'https://api.wikimedia.org/service/lw/inference/v1/models/enwiki-draftquality:predict'

if use_auth:
  headers: {
      'Authorization': 'Bearer YOUR_ACCESS_TOKEN',
      'User-Agent': 'YOUR_APP_NAME (YOUR_EMAIL_OR_CONTACT_PAGE)'
  }
else:
  headers = {}
data = {"rev_id": 12345 }
response = requests.post(inference_url, headers=headers, data=json.dumps(data))
print(response.json())

URI Parameters

`wiki` required	Wiki code:`enwiki` (English) or `ptwiki` (Portuguese).

POST Parameters

`rev_id` required	Wiki Revision id: integer related to a certain revision id for the Wiki set in the URI parameter.
`extended_output`	Whether or not the response should include the extended output of the model (like the list of features used etc..). Either true or false. Default: false

Responses

200

Success: Revision id found. Returns a Revscoring score object.

Example

{
  "enwiki": {
    "models": {
      "draftquality": {
        "version": "0.2.1"
      }
    },
    "scores": {
      "12345": {
        "draftquality": {
          "score": {
            "prediction": "spam",
            "probability": {
              "OK": 0.2058707138961481,
              "attack": 0.08356921917837876,
              "spam": 0.39768296325893626,
              "vandalism": 0.31287710366653687
            }
          }
        }
      }
    }
  }
}