confluentgist

client.create_stream_as(table_name='creditcardfraud_preprocessed_avro',
                     select_columns=['Time', 'V1', 'V2', 'V3', 'V4', 'V5', 'V6', 'V7', 'V8', 'V9', 'V10', 'V11', 'V12', 'V13', 'V14', 'V15', 'V16', 'V17', 'V18', 'V19', 'V20', 'V21', 'V22', 'V23', 'V24', 'V25', 'V26', 'V27', 'V28', 'Amount', 'Class'],
                     src_table='creditcardfraud_source',
                     conditions='Class IS NOT NULL',
                     kafka_topic='creditcardfraud_preprocessed_avro',
                     value_format='AVRO')

confluentgist

from ksql import KSQLAPI
client = KSQLAPI('http://localhost:8088')

client.create_stream(table_name='creditcardfraud_source',
                     columns_type=['Id bigint', 'Timestamp varchar', 'User varchar', 'Time int', 'V1 double', 'V2 double', 'V3 double', 'V4 double', 'V5 double', 'V6 double', 'V7 double', 'V8 double', 'V9 double', 'V10 double', 'V11 double', 'V12 double', 'V13 double', 'V14 double', 'V15 double', 'V16 double', 'V17 double', 'V18 double', 'V19 double', 'V20 double', 'V21 double', 'V22 double', 'V23 double', 'V24 double', 'V25 double', 'V26 double', 'V27 double', 'V28 double', 'Amount double', 'Class string'],
                     topic='creditcardfraud_source',
                     value_format='DELIMITED')

confluentgist

CREATE STREAM creditcardfraud_preprocessed_avro WITH (VALUE_FORMAT='AVRO', KAFKA_TOPIC='creditcardfraud_preprocessed_avro') AS SELECT Time,  V1 , V2 , V3 , V4 , V5 , V6 , V7 , V8 , V9 , V10 , V11 , V12 , V13 , V14 , V15 , V16 , V17 , V18 , V19 , V20 , V21 , V22 , V23 , V24 , V25 , V26 , V27 , V28 , Amount , Class FROM creditcardfraud_source WHERE Class IS NOT NULL;

confluentgist

SELECT Id, MASK_LEFT(User, 2) FROM creditcardfraud_source;

confluentgist

SELECT Id, IFNULL(Class, -1) FROM creditcardfraud_source;

confluentgist

CREATE STREAM creditcardfraud_per_user WITH (VALUE_FORMAT='AVRO', KAFKA_TOPIC='creditcardfraud_preprocessed_avro') AS SELECT Time,  V1 , V2 , V3 , V4 , V5 , V6 , V7 , V8 , V9 , V10 , V11 , V12 , V13 , V14 , V15 , V16 , V17 , V18 , V19 , V20 , V21 , V22 , V23 , V24 , V25 , V26 , V27 , V28 , Amount , Class FROM creditcardfraud_enahnced c INNER JOIN USERS u on c.userid = u.userid WHERE V1 > 5 AND V2 IS NOT NULL AND u.CITY LIKE 'Premium%';

confluentgist

This is a series of gists documenting testing done with the numeric.mapping option in Kafka Connect.

• Oracle
• MS SQL Server
• Postgres
• MySQL - n/a because of #563

—@rmoff January 9, 2019

confluentgist

events
  .groupByKey()
  .windowedBy(TimeWindows.of(Duration.ofMinutes(2)))
  .count(Materialized.as("count-metric"))

// graph servlet queries "count-metric"

confluentgist

events
  .groupByKey()
  .windowedBy(TimeWindows.of(Duration.ofMinutes(2)))
  .count(Materialized.as("count-metric"))
  .filter( _ < 4 )
  .toStream()
  .foreach( /* Send that email! */)

// graph servlet queries "count-metric"

confluentgist

events
  .groupByKey()
  .windowedBy(
    TimeWindows.of(Duration.ofMinutes(2).withGrace(Duration.ofMinutes(2))
  )
  .count(Materialized.as("count-metric"))
  .suppress(Suppressed.untilWindowClose(BufferConfig.unbounded()))
  .filter( _ < 4 )
  .toStream()
  .foreach( /* Send that email! */)