Python Forum

Hi, I am getting error in 'TEXTS' that 'too many blank lines, and 'missing white space around operator' and also I am not able to run that program. Please help.

from __future__ import unicode_literals, print_function

import plac
import spacy



TEXTS ='Microsoft was founded by Bill Gates and Paul Allen on April 4 1975 to develop and sell BASIC interpreters for the Altair 8800. Since the 1990, it has increasingly diversified from the operating system market and has made a number of corporate acquisitions. ',


@plac.annotations(model=("Model to load (needs parser and NER)", "positional", None, str))
def main(model='en_core_web_sm'):
    nlp = spacy.load(model)
    print("Loaded model '%s'" % model)
    print("Processing %d texts" % len(TEXTS))

    for text in TEXTS:
        doc = nlp(text)
        relations = extract_currency_relations(doc)
        for r1, r2 in relations:
            print('{:<10}\t{}\t{}'.format(r1.text, r2.ent_type_, r2.text))


def extract_currency_relations(doc):
    # merge entities and noun chunks into one token
    spans = list(doc.ents) + list(doc.noun_chunks)
    for span in spans:
        span.merge()

    relations = []
    for money in filter(lambda w : w.ent_type_ == 'PERSON', doc):
        if money.dep_ in ('attr', 'dobj'):
            subject = [w for w in money.head.lefts if w.dep_ == 'nsubj']
            if subject:
                subject = subject[0]
                relations.append((subject, money))
        elif money.dep_ == 'pobj' and money.head.dep_ == 'prep':
            relations.append((money.head.head, money))
    return relations


if __name__ == '__main__':
    plac.call(main)

For multi line code use python tags, not icode tasks. I'll fix it for you this time.

Those sound like errors you would get from a style checking program, not Python. How exactly are you running the code?

Why is there a comma after the definition of TEXTS?

I am using visual code. Let's say for this example it gives me error:
Loaded model 'en_core_web_sm'
Processing 1 texts

and then it stops and does not gives me anything. Please help

# pip install spacy
# python -m spacy download en_core_web_sm

import spacy

# Load English tokenizer, tagger, parser, NER and word vectors
nlp = spacy.load('en_core_web_sm')

# Process whole documents
text = (u"When Sebastian Thrun started working on self-driving cars at "
        u"Google in 2007, few people outside of the company took him "
        u"seriously. “I can tell you very senior CEOs of major American "
        u"car companies would shake my hand and turn away because I wasn’t "
        u"worth talking to,” said Thrun, now the co-founder and CEO of "
        u"online higher education startup Udacity, in an interview with "
        u"Recode earlier this week.")
doc = nlp(text)

# Find named entities, phrases and concepts
for entity in doc.ents:
    print(entity.text, entity.label_)

# Determine semantic similarities
doc1 = nlp(u"my fries were super gross")
doc2 = nlp(u"such disgusting fries")
similarity = doc1.similarity(doc2)
print(doc1.text, doc2.text, similarity)

I tried to work on this code but it is giving me output only for money and not org and person. Any help would be greatly appreciated. Thanks.

from __future__ import unicode_literals, print_function

import plac
import spacy


TEXTS = [
    'Net income was $9.4 million compared to the prior year of $2.7 million.',
    'Revenue exceeded twelve billion dollars, with a loss of $1b.',
]


@plac.annotations(
   model=("Model to load (needs parser and NER)", "positional", None, str))
def main(model='en_core_web_sm'):
    nlp = spacy.load(model)
    print("Loaded model '%s'" % model)
    print("Processing %d texts" % len(TEXTS))

    for text in TEXTS:
        doc = nlp(text)
        relations = extract_currency_relations(doc)
        for r1, r2 in relations:
            print('{:<10}\t{}\t{}'.format(r1.text, r2.ent_type_, r2.text))


def extract_currency_relations(doc):
    # merge entities and noun chunks into one token
    spans = list(doc.ents) + list(doc.noun_chunks)
    for span in spans:
        span.merge()

    relations = []
    for money in filter(lambda w: w.ent_type_ == 'MONEY', doc):
        if money.dep_ in ('attr', 'dobj'):
            subject = [w for w in money.head.lefts if w.dep_ == 'nsubj']
            if subject:
                subject = subject[0]
                relations.append((subject, money))
        elif money.dep_ == 'pobj' and money.head.dep_ == 'prep':
            relations.append((money.head.head, money))
    return relations

    relations = []
    for person in filter(lambda w: w.ent_type_ == 'PERSON', doc):
        if person.dep_ in ('attr', 'dobj'):
            subject = [w for w in person.head.lefts if w.dep_ == 'nsubj']
            if subject:
                subject = subject[0]
                relations.append((subject, person))
        elif person.dep_ == 'pobj' and person.head.dep_ == 'prep':
            relations.append((person.head.head, person))
    return relations

    relations = []
    for org in filter(lambda w: w.ent_type_ == 'ORG', doc):
        if org.dep_ in ('attr', 'dobj'):
            subject = [w for w in org.head.lefts if w.dep_ == 'nsubj']
            if subject:
                subject = subject[0]
                relations.append((subject, org))
        elif org.dep_ == 'pobj' and org.head.dep_ == 'prep':
            relations.append((org.head.head, org))
    return relations


if __name__ == '__main__':
    plac.call(main)
    main()