Sample of labels and words_to_watch

cmd.bash

$ bzcat datasets/ptwiki.draft_quality.balanced_3k.with_text.json.bz2 | \
  shuf -n 100 | python demo_ptwiki_w2w.py | sort -k1,1

demo_ptwiki_w2w.py

import sys
from revscoring.dependencies import solve
from revscoring.languages import portuguese
from revscoring.utilities.util import read_observations

for ob in read_observations(sys.stdin):
  w2w = solve(portuguese.words_to_watch.revision.datasources.matches, cache={'datasource.revision.text': ob['text']})
  print("\t".join(str(v) for v in [ob['draft_quality'], ob['rev_id'], w2w]))

OK	54768471	[]
OK	55012978	['famosos']
OK	55178661	[]
OK	55196082	[]
OK	55282660	[]
OK	55550859	[]
OK	55576553	[]
OK	55666870	[]
OK	55757315	[]
OK	55802504	[]
OK	56008223	[]
OK	56013248	[]
OK	56108721	[]
OK	56211646	['grande', 'grande', 'grande', 'grande', 'grande', 'grandes', 'chamado', 'grandes', 'grandes', 'grandes', 'chamadas', 'grande', 'grandes', 'grande', 'grandes', 'grande', 'grande', 'excelente', 'grandes', 'grandes', 'grandes', 'grande', 'grande']
OK	56487572	[]
OK	56523192	[]
OK	56651567	[]
OK	56706063	[]
OK	56978139	[]
OK	57084825	['grande', 'chamada', 'notável']
OK	57499021	[]
OK	57691340	[]
OK	57694130	[]
OK	57820321	[]
spam	54684767	[]
spam	54816520	['líder', 'excepcional']
spam	55027682	[]
spam	55090289	[]
spam	55097737	['renomada']
spam	55222616	[]
spam	55266531	[]
spam	55306785	[]
spam	55402946	['grande', 'grandes']
spam	55485152	['grande']
spam	55488071	[]
spam	55519018	['excelente']
spam	55657011	[]
spam	55683016	[]
spam	55719820	[]
spam	55802329	['grandes']
spam	55848783	[]
spam	55971535	[]
spam	55975367	[]
spam	56050190	['grande', 'grande']
spam	56145273	[]
spam	56163090	[]
spam	56256046	[]
spam	56402952	[]
spam	56672628	['Grandes', 'grandes']
spam	56703167	[]
spam	56774615	['grandes', 'grande']
spam	56882778	[]
spam	56955013	['renomadas', 'grandes', 'grande', 'grande']
spam	56974397	['Grande']
spam	57055228	[]
spam	57121144	[]
spam	57154747	[]
spam	57232360	[]
spam	57368799	['grandes']
spam	57424870	[]
spam	57655865	[]
unsuitable	54629893	[]
unsuitable	54700598	[]
unsuitable	54779607	[]
unsuitable	54798297	['observou']
unsuitable	54862152	[]
unsuitable	54868664	[]
unsuitable	55076031	[]
unsuitable	55262319	['Grande', 'Grande', 'grandes', 'grande']
unsuitable	55276068	[]
unsuitable	55324488	[]
unsuitable	55357743	[]
unsuitable	55484487	['Sem dúvida', 'acusado']
unsuitable	55495451	[]
unsuitable	55557638	['chamado']
unsuitable	55611020	['grande', 'grande']
unsuitable	55623181	[]
unsuitable	55623615	['famosas']
unsuitable	55667005	['grande']
unsuitable	55729751	['chamadas', 'chamadas']
unsuitable	56009675	[]
unsuitable	56029192	[]
unsuitable	56231570	['extraordinário', 'brilhante', 'grandes', 'afirmou', 'grande', 'grande', 'negou', 'admitiu', 'notáveis']
unsuitable	56235390	[]
unsuitable	56280467	[]
unsuitable	56317266	['grande', 'grande']
unsuitable	56458848	['famosos', 'suposto', 'revelou']
unsuitable	56467880	['chamada']
unsuitable	56470678	[]
unsuitable	56555184	['chamado']
unsuitable	56599209	[]
unsuitable	56604149	[]
unsuitable	56749658	[]
unsuitable	56817872	[]
unsuitable	57512165	['chamado', 'grande']
unsuitable	57591556	['líder', 'grande']
unsuitable	57651752	['grandes', 'encontrou', 'grandes']
unsuitable	57706330	[]
unsuitable	57777723	['famoso']
unsuitable	57818581	[]