Created by: SultanovAR
ru_obscenity_classifier it is model that classifies text for obscenity, for russian language
Code is placed in deeppavlov/models/classifiers/ru_obscenity_classifier.py
Config is placed in deeppavlov/configs/classifiers/ru_obscenity_classifier.json
example of working:
python deep.py interact -d configs/classifiers/ru_obscenity_classifier.json
2019-06-13 19:12:23.45 INFO in 'deeppavlov.core.data.utils'['utils'] at line 63: Downloading from http://files.deeppavlov.ai/models/obscenity_classifier/ru_obscenity_dataset.zip?config=ru_obscenity_classifier to /home/azat/.deeppavlov/downloads/ru_obscenity_dataset.zip
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 17.7k/17.7k [00:00<00:00, 32.2MB/s]
2019-06-13 19:12:23.49 INFO in 'deeppavlov.core.data.utils'['utils'] at line 201: Extracting /home/azat/.deeppavlov/downloads/ru_obscenity_dataset.zip archive into /home/azat/.deeppavlov/downloads/obscenity_dataset
[nltk_data] Downloading package punkt to /home/azat/nltk_data...
[nltk_data] Package punkt is already up-to-date!
[nltk_data] Downloading package stopwords to /home/azat/nltk_data...
[nltk_data] Package stopwords is already up-to-date!
[nltk_data] Downloading package perluniprops to
[nltk_data] /home/azat/nltk_data...
[nltk_data] Package perluniprops is already up-to-date!
[nltk_data] Downloading package nonbreaking_prefixes to
[nltk_data] /home/azat/nltk_data...
[nltk_data] Package nonbreaking_prefixes is already up-to-date!
2019-06-13 19:12:24.502 INFO in 'deeppavlov.models.classifiers.ru_obscenity_classifier'['ru_obscenity_classifier'] at line 77: Initializing `RuObscenityClassifier`
text::Ты милый
>> not_obscene
text::Ты сука
>> obscene
text::