NewscatcherAPI

import spacy
def hello_w():
  ok
  
  

NewscatcherAPI

import spacy
nlp=spacy.load('en_core_web_sm')
matcher = Matcher(nlp.vocab)

NewscatcherAPI

def clean_text(text, all_mentions):
    # If retweet, delete RT and name of the account
    text = re.sub('(RT\s.*):', '', text)
    # Find all links and delete them
    all_links = re.findall('(https:.*?)\s', text + ' ')

    for i in all_links:
        text = text.replace(i, '')

    for i in all_mentions:

NewscatcherAPI

summary = [article['summary'] for article in articles]
sentence = summary[0]

NewscatcherAPI

def is_company_acquisition(headline_doc):
    # check if the acquisition lemma (why lemma?)
    for token in headline_doc:
        if 'acquire' not in [token.lemma_ for token in headline_doc]:
            return False
        # check that at least 2 ORG entities
        elif len([ent.label_ for ent in headline_doc.ents if ent.label_ == 'ORG']) < 2:
            return False
        return True

NewscatcherAPI

 steps:
 # Build the container image
 - name: 'gcr.io/cloud-builders/docker'
   args: ['build', '-t', 'gcr.io/$PROJECT_ID/${_SERVICE_NAME}:${_VERSION}', '-f', './${_DIRECTORY_PROJECT}/Dockerfile', '.', '--build-arg',  'directory=${_DIRECTORY_PROJECT}','--build-arg', 'number_workers=${_NB_WORKERS}']
 # Push the container image to Container Registry
 - name: 'gcr.io/cloud-builders/docker'
   args: ['push', 'gcr.io/$PROJECT_ID/${_SERVICE_NAME}:${_VERSION}']
 # Deploy container image to Cloud Run
 - name: 'gcr.io/google.com/cloudsdktool/cloud-sdk'
   entrypoint: gcloud

NewscatcherAPI

# Use Python36
FROM python:3.6

# Arguments
ARG directory
ARG number_workers # number of threads

WORKDIR /app

# Copy requirements.txt to the docker image and install packages