├── .gitattributes ├── .gitignore ├── 00-HelloSparkSQL ├── HelloSparkSQL.py ├── data │ └── sample.csv ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 01-StreamingWC ├── StreamingWC.py ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 02-FileStreamDemo ├── FileStreamDemo.py ├── SampleData │ ├── Invoice-set1.json │ ├── Invoice-set1.parquet │ ├── Invoice-set2.json │ ├── Invoice-set2.parquet │ ├── Invoice-set3.json │ └── Invoice-set3.parquet ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 03-KafkaStreamDemo ├── KafkaStreamDemo.py ├── datagen │ ├── data │ │ ├── Invoice.json │ │ ├── address.json │ │ └── products.json │ ├── pos-simulator-2.0.0.jar │ ├── run-datagen.cmd │ └── samples.json ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-topic.cmd │ └── 04-start-producer.cmd ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 04-KafkaSinkDemo ├── KafkaSinkDemo.py ├── data │ └── samples.json ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-input-topic.cmd │ ├── 04-create-output-topic.cmd │ ├── 05-start-producer.cmd │ └── 06-start-consumer.cmd ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 05-MultiQueryDemo ├── MultiQueryDemo.py ├── data │ └── samples.json ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-input-topic.cmd │ ├── 04-create-output-topic.cmd │ ├── 05-start-producer.cmd │ └── 06-start-consumer.cmd ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 06-KafkaAvroSinkDemo ├── KafkaAvroSinkDemo.py ├── data │ └── samples.json ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-input-topic.cmd │ ├── 04-create-output-topic.cmd │ ├── 05-start-producer.cmd │ └── 06-start-consumer.cmd ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 07-KafkaAvroSourceDemo ├── KafkaAvroSourceDemo.py ├── kafka-scripts │ ├── 04-create-output-topic.cmd │ └── 06-start-consumer.cmd ├── lib │ ├── __init__.py │ └── logger.py ├── log4j.properties └── schema │ └── invoice-items ├── 08-TumblingWindowDemo ├── TumblingWindowDemo.py ├── data │ └── samples.txt ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-input-topic.cmd │ └── 05-start-producer.cmd ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 09-SlidingWindowDemo ├── SlidingWindowDemo.py ├── data │ └── samples.json ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-input-topic.cmd │ └── 05-start-producer.cmd ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 10-WatermarkDemo ├── WatermarkDemo.py ├── data │ └── samples.txt ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-input-topic.cmd │ └── 05-start-producer.cmd ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 11-StreamTableJoinDemo ├── StreamTableJoinDemo.py ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-input-topic.cmd │ └── 05-start-producer.cmd ├── lib │ ├── __init__.py │ └── logger.py ├── log4j.properties ├── static-data │ └── user.cql └── streaming-data │ └── logins.txt ├── 12-StreamStreamJoinDemo ├── StreamStreamJoinDemo.py ├── data │ └── events.txt ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-impression-topic.cmd │ ├── 04-create-click-topic.cmd │ ├── 05-start-impression-producer.cmd │ └── 06-start-click-producer.cmd ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 13-StreamingWatermarkDemo ├── StreamingWatermarkDemo.py ├── data │ └── events.txt ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-impression-topic.cmd │ ├── 04-create-click-topic.cmd │ ├── 05-start-impression-producer.cmd │ └── 06-start-click-producer.cmd ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── 14-StreamingOuterJoinDemo ├── StreamingOuterJoinDemo.py ├── data │ └── events.txt ├── kafka-scripts │ ├── 01-start-zookeeper.cmd │ ├── 02-start-kafka.cmd │ ├── 03-create-impression-topic.cmd │ ├── 04-create-click-topic.cmd │ ├── 05-start-impression-producer.cmd │ └── 06-start-click-producer.cmd ├── lib │ ├── __init__.py │ └── logger.py └── log4j.properties ├── LICENSE └── README.md /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/.gitattributes -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/.gitignore -------------------------------------------------------------------------------- /00-HelloSparkSQL/HelloSparkSQL.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/00-HelloSparkSQL/HelloSparkSQL.py -------------------------------------------------------------------------------- /00-HelloSparkSQL/data/sample.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/00-HelloSparkSQL/data/sample.csv -------------------------------------------------------------------------------- /00-HelloSparkSQL/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /00-HelloSparkSQL/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/00-HelloSparkSQL/lib/logger.py -------------------------------------------------------------------------------- /00-HelloSparkSQL/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/00-HelloSparkSQL/log4j.properties -------------------------------------------------------------------------------- /01-StreamingWC/StreamingWC.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/01-StreamingWC/StreamingWC.py -------------------------------------------------------------------------------- /01-StreamingWC/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /01-StreamingWC/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/01-StreamingWC/lib/logger.py -------------------------------------------------------------------------------- /01-StreamingWC/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/01-StreamingWC/log4j.properties -------------------------------------------------------------------------------- /02-FileStreamDemo/FileStreamDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/02-FileStreamDemo/FileStreamDemo.py -------------------------------------------------------------------------------- /02-FileStreamDemo/SampleData/Invoice-set1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/02-FileStreamDemo/SampleData/Invoice-set1.json -------------------------------------------------------------------------------- /02-FileStreamDemo/SampleData/Invoice-set1.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/02-FileStreamDemo/SampleData/Invoice-set1.parquet -------------------------------------------------------------------------------- /02-FileStreamDemo/SampleData/Invoice-set2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/02-FileStreamDemo/SampleData/Invoice-set2.json -------------------------------------------------------------------------------- /02-FileStreamDemo/SampleData/Invoice-set2.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/02-FileStreamDemo/SampleData/Invoice-set2.parquet -------------------------------------------------------------------------------- /02-FileStreamDemo/SampleData/Invoice-set3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/02-FileStreamDemo/SampleData/Invoice-set3.json -------------------------------------------------------------------------------- /02-FileStreamDemo/SampleData/Invoice-set3.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/02-FileStreamDemo/SampleData/Invoice-set3.parquet -------------------------------------------------------------------------------- /02-FileStreamDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /02-FileStreamDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/02-FileStreamDemo/lib/logger.py -------------------------------------------------------------------------------- /02-FileStreamDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/02-FileStreamDemo/log4j.properties -------------------------------------------------------------------------------- /03-KafkaStreamDemo/KafkaStreamDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/KafkaStreamDemo.py -------------------------------------------------------------------------------- /03-KafkaStreamDemo/datagen/data/Invoice.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/datagen/data/Invoice.json -------------------------------------------------------------------------------- /03-KafkaStreamDemo/datagen/data/address.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/datagen/data/address.json -------------------------------------------------------------------------------- /03-KafkaStreamDemo/datagen/data/products.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/datagen/data/products.json -------------------------------------------------------------------------------- /03-KafkaStreamDemo/datagen/pos-simulator-2.0.0.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/datagen/pos-simulator-2.0.0.jar -------------------------------------------------------------------------------- /03-KafkaStreamDemo/datagen/run-datagen.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/datagen/run-datagen.cmd -------------------------------------------------------------------------------- /03-KafkaStreamDemo/datagen/samples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/datagen/samples.json -------------------------------------------------------------------------------- /03-KafkaStreamDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /03-KafkaStreamDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /03-KafkaStreamDemo/kafka-scripts/03-create-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/kafka-scripts/03-create-topic.cmd -------------------------------------------------------------------------------- /03-KafkaStreamDemo/kafka-scripts/04-start-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/kafka-scripts/04-start-producer.cmd -------------------------------------------------------------------------------- /03-KafkaStreamDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /03-KafkaStreamDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/lib/logger.py -------------------------------------------------------------------------------- /03-KafkaStreamDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/03-KafkaStreamDemo/log4j.properties -------------------------------------------------------------------------------- /04-KafkaSinkDemo/KafkaSinkDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/04-KafkaSinkDemo/KafkaSinkDemo.py -------------------------------------------------------------------------------- /04-KafkaSinkDemo/data/samples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/04-KafkaSinkDemo/data/samples.json -------------------------------------------------------------------------------- /04-KafkaSinkDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/04-KafkaSinkDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /04-KafkaSinkDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/04-KafkaSinkDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /04-KafkaSinkDemo/kafka-scripts/03-create-input-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/04-KafkaSinkDemo/kafka-scripts/03-create-input-topic.cmd -------------------------------------------------------------------------------- /04-KafkaSinkDemo/kafka-scripts/04-create-output-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/04-KafkaSinkDemo/kafka-scripts/04-create-output-topic.cmd -------------------------------------------------------------------------------- /04-KafkaSinkDemo/kafka-scripts/05-start-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/04-KafkaSinkDemo/kafka-scripts/05-start-producer.cmd -------------------------------------------------------------------------------- /04-KafkaSinkDemo/kafka-scripts/06-start-consumer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/04-KafkaSinkDemo/kafka-scripts/06-start-consumer.cmd -------------------------------------------------------------------------------- /04-KafkaSinkDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /04-KafkaSinkDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/04-KafkaSinkDemo/lib/logger.py -------------------------------------------------------------------------------- /04-KafkaSinkDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/04-KafkaSinkDemo/log4j.properties -------------------------------------------------------------------------------- /05-MultiQueryDemo/MultiQueryDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/05-MultiQueryDemo/MultiQueryDemo.py -------------------------------------------------------------------------------- /05-MultiQueryDemo/data/samples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/05-MultiQueryDemo/data/samples.json -------------------------------------------------------------------------------- /05-MultiQueryDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/05-MultiQueryDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /05-MultiQueryDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/05-MultiQueryDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /05-MultiQueryDemo/kafka-scripts/03-create-input-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/05-MultiQueryDemo/kafka-scripts/03-create-input-topic.cmd -------------------------------------------------------------------------------- /05-MultiQueryDemo/kafka-scripts/04-create-output-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/05-MultiQueryDemo/kafka-scripts/04-create-output-topic.cmd -------------------------------------------------------------------------------- /05-MultiQueryDemo/kafka-scripts/05-start-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/05-MultiQueryDemo/kafka-scripts/05-start-producer.cmd -------------------------------------------------------------------------------- /05-MultiQueryDemo/kafka-scripts/06-start-consumer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/05-MultiQueryDemo/kafka-scripts/06-start-consumer.cmd -------------------------------------------------------------------------------- /05-MultiQueryDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /05-MultiQueryDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/05-MultiQueryDemo/lib/logger.py -------------------------------------------------------------------------------- /05-MultiQueryDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/05-MultiQueryDemo/log4j.properties -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/KafkaAvroSinkDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/06-KafkaAvroSinkDemo/KafkaAvroSinkDemo.py -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/data/samples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/06-KafkaAvroSinkDemo/data/samples.json -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/06-KafkaAvroSinkDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/06-KafkaAvroSinkDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/kafka-scripts/03-create-input-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/06-KafkaAvroSinkDemo/kafka-scripts/03-create-input-topic.cmd -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/kafka-scripts/04-create-output-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/06-KafkaAvroSinkDemo/kafka-scripts/04-create-output-topic.cmd -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/kafka-scripts/05-start-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/06-KafkaAvroSinkDemo/kafka-scripts/05-start-producer.cmd -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/kafka-scripts/06-start-consumer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/06-KafkaAvroSinkDemo/kafka-scripts/06-start-consumer.cmd -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/06-KafkaAvroSinkDemo/lib/logger.py -------------------------------------------------------------------------------- /06-KafkaAvroSinkDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/06-KafkaAvroSinkDemo/log4j.properties -------------------------------------------------------------------------------- /07-KafkaAvroSourceDemo/KafkaAvroSourceDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/07-KafkaAvroSourceDemo/KafkaAvroSourceDemo.py -------------------------------------------------------------------------------- /07-KafkaAvroSourceDemo/kafka-scripts/04-create-output-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/07-KafkaAvroSourceDemo/kafka-scripts/04-create-output-topic.cmd -------------------------------------------------------------------------------- /07-KafkaAvroSourceDemo/kafka-scripts/06-start-consumer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/07-KafkaAvroSourceDemo/kafka-scripts/06-start-consumer.cmd -------------------------------------------------------------------------------- /07-KafkaAvroSourceDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /07-KafkaAvroSourceDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/07-KafkaAvroSourceDemo/lib/logger.py -------------------------------------------------------------------------------- /07-KafkaAvroSourceDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/07-KafkaAvroSourceDemo/log4j.properties -------------------------------------------------------------------------------- /07-KafkaAvroSourceDemo/schema/invoice-items: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/07-KafkaAvroSourceDemo/schema/invoice-items -------------------------------------------------------------------------------- /08-TumblingWindowDemo/TumblingWindowDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/08-TumblingWindowDemo/TumblingWindowDemo.py -------------------------------------------------------------------------------- /08-TumblingWindowDemo/data/samples.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/08-TumblingWindowDemo/data/samples.txt -------------------------------------------------------------------------------- /08-TumblingWindowDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/08-TumblingWindowDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /08-TumblingWindowDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/08-TumblingWindowDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /08-TumblingWindowDemo/kafka-scripts/03-create-input-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/08-TumblingWindowDemo/kafka-scripts/03-create-input-topic.cmd -------------------------------------------------------------------------------- /08-TumblingWindowDemo/kafka-scripts/05-start-producer.cmd: -------------------------------------------------------------------------------- 1 | %KAFKA_HOME%\bin\windows\kafka-console-producer.bat --broker-list localhost:9092 --topic trades -------------------------------------------------------------------------------- /08-TumblingWindowDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /08-TumblingWindowDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/08-TumblingWindowDemo/lib/logger.py -------------------------------------------------------------------------------- /08-TumblingWindowDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/08-TumblingWindowDemo/log4j.properties -------------------------------------------------------------------------------- /09-SlidingWindowDemo/SlidingWindowDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/09-SlidingWindowDemo/SlidingWindowDemo.py -------------------------------------------------------------------------------- /09-SlidingWindowDemo/data/samples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/09-SlidingWindowDemo/data/samples.json -------------------------------------------------------------------------------- /09-SlidingWindowDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/09-SlidingWindowDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /09-SlidingWindowDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/09-SlidingWindowDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /09-SlidingWindowDemo/kafka-scripts/03-create-input-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/09-SlidingWindowDemo/kafka-scripts/03-create-input-topic.cmd -------------------------------------------------------------------------------- /09-SlidingWindowDemo/kafka-scripts/05-start-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/09-SlidingWindowDemo/kafka-scripts/05-start-producer.cmd -------------------------------------------------------------------------------- /09-SlidingWindowDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /09-SlidingWindowDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/09-SlidingWindowDemo/lib/logger.py -------------------------------------------------------------------------------- /09-SlidingWindowDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/09-SlidingWindowDemo/log4j.properties -------------------------------------------------------------------------------- /10-WatermarkDemo/WatermarkDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/10-WatermarkDemo/WatermarkDemo.py -------------------------------------------------------------------------------- /10-WatermarkDemo/data/samples.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/10-WatermarkDemo/data/samples.txt -------------------------------------------------------------------------------- /10-WatermarkDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/10-WatermarkDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /10-WatermarkDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/10-WatermarkDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /10-WatermarkDemo/kafka-scripts/03-create-input-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/10-WatermarkDemo/kafka-scripts/03-create-input-topic.cmd -------------------------------------------------------------------------------- /10-WatermarkDemo/kafka-scripts/05-start-producer.cmd: -------------------------------------------------------------------------------- 1 | %KAFKA_HOME%\bin\windows\kafka-console-producer.bat --broker-list localhost:9092 --topic trades -------------------------------------------------------------------------------- /10-WatermarkDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /10-WatermarkDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/10-WatermarkDemo/lib/logger.py -------------------------------------------------------------------------------- /10-WatermarkDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/10-WatermarkDemo/log4j.properties -------------------------------------------------------------------------------- /11-StreamTableJoinDemo/StreamTableJoinDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/11-StreamTableJoinDemo/StreamTableJoinDemo.py -------------------------------------------------------------------------------- /11-StreamTableJoinDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/11-StreamTableJoinDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /11-StreamTableJoinDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/11-StreamTableJoinDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /11-StreamTableJoinDemo/kafka-scripts/03-create-input-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/11-StreamTableJoinDemo/kafka-scripts/03-create-input-topic.cmd -------------------------------------------------------------------------------- /11-StreamTableJoinDemo/kafka-scripts/05-start-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/11-StreamTableJoinDemo/kafka-scripts/05-start-producer.cmd -------------------------------------------------------------------------------- /11-StreamTableJoinDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /11-StreamTableJoinDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/11-StreamTableJoinDemo/lib/logger.py -------------------------------------------------------------------------------- /11-StreamTableJoinDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/11-StreamTableJoinDemo/log4j.properties -------------------------------------------------------------------------------- /11-StreamTableJoinDemo/static-data/user.cql: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/11-StreamTableJoinDemo/static-data/user.cql -------------------------------------------------------------------------------- /11-StreamTableJoinDemo/streaming-data/logins.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/11-StreamTableJoinDemo/streaming-data/logins.txt -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/StreamStreamJoinDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/12-StreamStreamJoinDemo/StreamStreamJoinDemo.py -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/data/events.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/12-StreamStreamJoinDemo/data/events.txt -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/12-StreamStreamJoinDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/12-StreamStreamJoinDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/kafka-scripts/03-create-impression-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/12-StreamStreamJoinDemo/kafka-scripts/03-create-impression-topic.cmd -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/kafka-scripts/04-create-click-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/12-StreamStreamJoinDemo/kafka-scripts/04-create-click-topic.cmd -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/kafka-scripts/05-start-impression-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/12-StreamStreamJoinDemo/kafka-scripts/05-start-impression-producer.cmd -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/kafka-scripts/06-start-click-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/12-StreamStreamJoinDemo/kafka-scripts/06-start-click-producer.cmd -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/12-StreamStreamJoinDemo/lib/logger.py -------------------------------------------------------------------------------- /12-StreamStreamJoinDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/12-StreamStreamJoinDemo/log4j.properties -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/StreamingWatermarkDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/13-StreamingWatermarkDemo/StreamingWatermarkDemo.py -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/data/events.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/13-StreamingWatermarkDemo/data/events.txt -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/13-StreamingWatermarkDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/13-StreamingWatermarkDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/kafka-scripts/03-create-impression-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/13-StreamingWatermarkDemo/kafka-scripts/03-create-impression-topic.cmd -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/kafka-scripts/04-create-click-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/13-StreamingWatermarkDemo/kafka-scripts/04-create-click-topic.cmd -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/kafka-scripts/05-start-impression-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/13-StreamingWatermarkDemo/kafka-scripts/05-start-impression-producer.cmd -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/kafka-scripts/06-start-click-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/13-StreamingWatermarkDemo/kafka-scripts/06-start-click-producer.cmd -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/13-StreamingWatermarkDemo/lib/logger.py -------------------------------------------------------------------------------- /13-StreamingWatermarkDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/13-StreamingWatermarkDemo/log4j.properties -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/StreamingOuterJoinDemo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/14-StreamingOuterJoinDemo/StreamingOuterJoinDemo.py -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/data/events.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/14-StreamingOuterJoinDemo/data/events.txt -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/kafka-scripts/01-start-zookeeper.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/14-StreamingOuterJoinDemo/kafka-scripts/01-start-zookeeper.cmd -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/kafka-scripts/02-start-kafka.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/14-StreamingOuterJoinDemo/kafka-scripts/02-start-kafka.cmd -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/kafka-scripts/03-create-impression-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/14-StreamingOuterJoinDemo/kafka-scripts/03-create-impression-topic.cmd -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/kafka-scripts/04-create-click-topic.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/14-StreamingOuterJoinDemo/kafka-scripts/04-create-click-topic.cmd -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/kafka-scripts/05-start-impression-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/14-StreamingOuterJoinDemo/kafka-scripts/05-start-impression-producer.cmd -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/kafka-scripts/06-start-click-producer.cmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/14-StreamingOuterJoinDemo/kafka-scripts/06-start-click-producer.cmd -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/lib/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/14-StreamingOuterJoinDemo/lib/logger.py -------------------------------------------------------------------------------- /14-StreamingOuterJoinDemo/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/14-StreamingOuterJoinDemo/log4j.properties -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LearningJournal/Spark-Streaming-In-Python/HEAD/README.md --------------------------------------------------------------------------------