ilyasahsan123

CREATE OR REPLACE VIEW `tulisanmedium.digitalviews.top_10_most_film_by_director` 
OPTIONS(
  description="Top 5 most film by director for digital content purpose. requested by digital team"
)
AS
select 
  count(distinct title) number_of_films
  ,director
  ,string_agg(distinct title order by title limit 5) as films
from  

ilyasahsan123

AWSTemplateFormatVersion: '2010-09-09'
Transform: 'AWS::Serverless-2016-10-31'
Description: An AWS Serverless Specification template describing your function.
Resources:
  dogreat:
    Type: 'AWS::Serverless::Function'
    Properties:
      Handler: lambda_function.lambda_handler
      Runtime: python3.6
      CodeUri: s3://do-great-bucket/source.zip

ilyasahsan123

version: 0.2
env:
  variables:
    INPUT_TEMPLATE: "appspec.yaml"
    S3_BUCKET: "do-great-bucket"
phases:
  install:
    commands:
      - wget https://bootstrap.pypa.io/get-pip.py
      - python get-pip.py

ilyasahsan123

PUT series/_mappings/movie
{
  "properties": {
    "film_to_franchise": {
      "type": "join",
      "eager_global_ordinals": true,
      "relations": {
        "franchise": "film"
      }
    },

ilyasahsan123

PUT series/movie/1?routing=1
{
  "id": "1",
  "film_to_franchise": {
    "name": "franchise"
  },
  "title": "Star Wars"
}
PUT series/movie/1196?routing=1
{

ilyasahsan123

curl -XPOST "http://localhost:8083/connectors" -H 'Content-Type: application/json' -d'
{
  "name": "debezium",
  "config": {
    "connector.class": "io.debezium.connector.mysql.MySqlConnector",
    "database.hostname": "localhost",
    "database.port": "3306",
    "database.user": "root",
    "database.password": "",
    "database.server.id": "184054",

ilyasahsan123

import json
from kafka import KafkaConsumer
from google.cloud import bigquery

if __name__ == "__main__":
    
    # bigwuery configuration
    bigquery_client = bigquery.Client()
    dataset_ref = bigquery_client.dataset('DATASET_NAME')
    table_ref = dataset_ref.table('TABLE_NAME')

ilyasahsan123

import json
from kafka import KafkaConsumer
from google.cloud import bigquery

if __name__ == "__main__":
    
    # bigwuery configuration
    bigquery_client = bigquery.Client()
    dataset_ref = bigquery_client.dataset('DATASET_NAME')
    table_ref = dataset_ref.table('TABLE_NAME')

ilyasahsan123

def detect_text(bucket, filename):
    
    # use cloud vision client for extract information from image which store on cloud storage
    from google.cloud import vision 
    vision_client = vision.ImageAnnotatorClient()
    response = vision_client.text_detection({
        'source': {'image_uri': "gs://{}/{}".format(bucket, filename)}
    })
    
    # get all text from extraction

ilyasahsan123

import json
import apache_beam as beam
import apache_beam.transforms.window as window
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.options.pipeline_options import StandardOptions
from apache_beam.io.gcp.internal.clients import bigquery

if __name__ == "__main__":
    
    # create pipeline