NesrineSF

living_from_live = "She's living her best life"
living_from_living = "What do you do for a living?"

language = 'en'

#Request to the API
output = client.specific_resource_analysis(
    body={"document": {"text": living_from_live }}, 
    params={'language': language, 'resource': 'disambiguation'
})

NesrineSF

#Concept_ID for object_noun
print (f'\t \033[1mConcept_ID for object when NOUN \033[0m \n') 

#to print TOKEN, POS  and ID (for the concept) in bold at the beginning of the output array:
print (f'\033[1m{"TOKEN":{20}} {"POS":{15}} {"ID":{6}}\033[0m')

#Syncon stands for "Concept" that we refer to with an ID
for token in output.tokens:
    print (f'{object_noun[token.start:token.end]:{20}} {token.pos:{15}} {token.syncon:{6}} ')

NesrineSF

#POS of the first sentence
print (f'\t \033[1mOutput of the first sentence : \033[0m \n') 
#to print TOKEN and POS in bold at the beginning of the output array:
print (f'\033[1m{"TOKEN":{20}} {"POS":{6}}\033[0m')

#to iterate over the tokens and assign a POS to each token for the first sentence
for token in output.tokens:
    print (f'{object_noun[token.start:token.end]:{20}} {token.pos:{6}}')

#POS of the second sentence

NesrineSF

#first sentence
object_noun = "The object of this exercise is to raise money for the charity."
#second sentence
object_verb = "A lot of people will object to the book."
language = 'en'
#Request to the API for the first sentence
output = client.specific_resource_analysis(
    body={"document": {"text": object_noun}}, 
    params={'language': language, 'resource': 'disambiguation'
})

NesrineSF

#first sentence
object_noun = "The object of this exercise is to raise money for the charity."
language = 'en'
#Request to the API
output = client.specific_resource_analysis(
    body={"document": {"text": object_noun}}, 
    params={'language': language, 'resource': 'disambiguation'
})

NesrineSF

object_noun = "The object of this exercise is to raise money for the charity."
object_verb = "A lot of people will object to the book."

NesrineSF

for token in output.tokens:
    print (f'{text[token.start:token.end]:{20}}')
    #we iterate on the tokens array to subdivise the compound words into the atom level
    for atom in token.atoms:
        print (f'\t atom:{text[atom.start:atom.end]:{20}}')

NesrineSF

text = "CNBC has commented on the robot's  lifelike skin and her ability to emulate more than 60 facial expressions." 
language= 'en'

output = client.specific_resource_analysis(
    body={"document": {"text": text}}, 
    params={'language': language, 'resource': 'disambiguation'
})

#to print to tokens within the sentence
print (f'{"TOKEN":{20}} ')

NesrineSF

text = "CNBC has commented on the robot's  lifelike skin and her ability to emulate more than 60 facial expressions."

tokens = text.split()
print('These are the tokens of the sentence', tokens)

NesrineSF

#Output arrays size
print("phrases array size: ", len(output.phrases))