conda install -c conda-forge spacy

python -m spacy download en # default English model (~50MB)

import spacy
nlp =space.load('en_core_web_sm')

python -m spacy download en_core_web_md # larger English model (~1GB)

doc=nlp(u'Tesla is looking at buying U.S. startup for 6$ million')


for token in doc:
     print(token.text, token.pos)
     print(token.text, token.pos_)
     print(token.text, token.pos_,token.dep_)

nlp.pipeline

nlp.pipe_names

doc2=nlp(u'Tesla is't looking into startups anymore. ')
for token indoc2
     print(token.text, token.pos_,token.dep_

doc2[0].pos_

doc= nlp(u'Apple to build a Hong kong factory for $6 million')

for entity in doc.ents:
   print(entity)
   print(entity.label_)
   print(str(spacy.explain(entity.label_)))
   print('\n')

doc=nlp (u'Autonomous cars shift insurance liability toward manufactures.')

for chunk in doc.noun_chunks:
     print(chunk)

from spacy import displacy

doc=nlp(u'Apple is going to build a U.K. factory for $6 million')

displacy.render(doc,style='dep',jupyter=True,options={'distance':110})

displacy.render(doc,style='ent',jupyter=True,)


displacy.serve(doc,style='dep')

doc = nlp(u"I am a runner running in a race because I love to run since I ran today")

for token in doc:
    print(token.text, '\t',token.pos_,token.lemma,token.lemma_)


def show_lemmas(text):
    for token in text:
        print(f'{token.text:{12} {token.pos_:{5}} {token.lemma_:{10}}')

print(nlp.Defaults.stop_words)
print(len(nlp.Defaults.stop_words)
nlp.vocab['is'].is_stop
nlp.Defaults.stop_words.add('btw')
nlp.vocab['btw'].is_stop=True

from spacy.matcher import PhraseMatcher
matcher=PhraseMatcher(nlp.vocab)