enlp.pipeline.NLPPipeline

class enlp.pipeline.NLPPipeline(model, text)

Pipeline class for combining functions from nlp_tools

Attributes

modelspacy.lang

SpaCy language model

textstr

text string on which to perform processing

poslist

list of Parts-of-Speech tags

tokenslist

list of tokens

Methods

__init__(self, model, text)	__init__ method of nlp_pipeline class
nltk_stem_no(self)	stem text
pos_tag(self)	get part-of-speech tags
rm_punctuation(self, \*\*kwargs)	remove punctuation from text
rm_stopwords(self, \*\*kwargs)	remove stopwords from text
spacy_lemmatize(self)	lemmatise text
tokenise(self)	tokenise text

rm_punctuation(self, **kwargs)

remove punctuation from text

rm_stopwords(self, **kwargs)

remove stopwords from text

Notes

List of stopwords can be obtained from stdtools.get_stopwords()

spacy_lemmatize(self)

lemmatise text

nltk_stem_no(self)

stem text

pos_tag(self)

get part-of-speech tags

tokenise(self)

tokenise text

Examples using enlp.pipeline.NLPPipeline

NLP Pipeline