Model that identifies bots from humans among developer identities.
Example:
from sklearn.preprocessing import LabelEncoder
from sourced.ml.models import BotDetection
from xgboost import XGBClassifier
bot_detection = BotDetection.load("94806d1f-1995-4c72-89c9-07681fa9d97d")
xgb_cls = XGBClassifier()
xgb_cls._Booster = bot_detection_model.booster
xgb_cls._le = LabelEncoder().fit([False, True])
print('model configuration: ', xgb_cls)
print('BPE model vocabulary size: ', len(bot_detection.bpe_model.vocab()))| ID | 94806d1f-1995-4c72-89c9-07681fa9d97d |
| Uploaded | 2019-10-14 14:39:02 |
| Version | 1.0.0 |
| File | https://storage.googleapis.com/models.cdn.sourced.tech/models%2Fbot-detection%2F94806d1f-1995-4c72-89c9-07681fa9d97d.asdf |
| Size | 100.0 kB |
| BPE vocabulary size | 200 |
| Number of distinct features | 252 |
| Number of trained samples | 135941 |
| Proportion of humans against bots | 3 |
| weighted precision | 0.92 |
| weighted recall | 0.91 |
| License | O |