core.corpus

Corpus

This modul represents the corpus and all related classes.

Useful classes

The following classes can be used via e.g. from core.corpus import Dummy

View Source
"""
# Corpus

This modul represents the corpus and all related classes.

## Useful classes
> The following classes can be used via
> e.g. ``from core.corpus import Dummy``

- `core.corpus.corpus`  
	`StringCorpus`
- `core.corpus.preprocess`  
	`DefaultPreprocessor`, `MinimalPreprocessor`
- `core.corpus.corpora`  
	`ArXiv`, `TwentyNews`, `Dummy`, `ManuscriptCultures`
- `core.corpus.annotators`  
	`Wiktionary`
- `core.corpus.annotated_corpora`  
	`SingleAnnotatedCorpus`, `MultiAnnotatedCorpus`

"""

from core.corpus.preprocess import (
	DefaultPreprocessor,
	MinimalPreprocessor
)

from core.corpus.corpus import (
	StringCorpus
)

from core.corpus.corpora import (
	ArXiv,
	TwentyNews,
	Dummy,
	ManuscriptCultures
)

from core.corpus.annotators import (
	Wiktionary,
	Quotes
)

from core.corpus.annotated_corpora import (
	SingleAnnotatedCorpus,
	MultiAnnotatedCorpus
)