├── .gitignore ├── Dataframe_examples.ipynb ├── Flint Timeseries.ipynb ├── LICENSE ├── Profiling.ipynb ├── RDD+Basics.ipynb ├── RDD_Operations.ipynb ├── README.md ├── Spark Dataframe Pivot.ipynb ├── Spark ML - Credit card Fraud.ipynb ├── Spark ML - Graphx.ipynb ├── SparkML - 01 Regression.ipynb ├── SparkML - 02 Credit Default.ipynb ├── SparkML - 03 Image Classification (MNIST).ipynb ├── SparkML - 04 Text_Analysis.ipynb ├── Stocks Analyser.ipynb ├── data-conversion.py ├── kafka-clients ├── Load to Cassandra.ipynb ├── avro_consumer.py ├── avro_producer.py ├── cassandra_schema.cql ├── json_consumer.py ├── json_producer.py ├── requirements.txt ├── spark_streaming.py └── transactions.avsc ├── kafka_stream_zk_dstream.py ├── random_file_generator.py ├── spark-stream-socket-hbase.py ├── spark_dstream_socket.py ├── spark_file_dstream.py ├── spark_kafka_dstream.py ├── spark_stream_json_messages.py ├── spark_streaming_hbase.py ├── spark_streaming_kafka_direct.py ├── stocks.py ├── stream_twitter_from_file.py ├── structured-streaming-socket.py ├── structured_streaming_file_source.py ├── structured_streaming_file_to_maprdb.py ├── structured_streaming_kafka.py ├── structured_streaming_kafka_aggregate.py └── twitter_stream_api.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/.gitignore -------------------------------------------------------------------------------- /Dataframe_examples.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/Dataframe_examples.ipynb -------------------------------------------------------------------------------- /Flint Timeseries.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/Flint Timeseries.ipynb -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/LICENSE -------------------------------------------------------------------------------- /Profiling.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/Profiling.ipynb -------------------------------------------------------------------------------- /RDD+Basics.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/RDD+Basics.ipynb -------------------------------------------------------------------------------- /RDD_Operations.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/RDD_Operations.ipynb -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/README.md -------------------------------------------------------------------------------- /Spark Dataframe Pivot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/Spark Dataframe Pivot.ipynb -------------------------------------------------------------------------------- /Spark ML - Credit card Fraud.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/Spark ML - Credit card Fraud.ipynb -------------------------------------------------------------------------------- /Spark ML - Graphx.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/Spark ML - Graphx.ipynb -------------------------------------------------------------------------------- /SparkML - 01 Regression.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/SparkML - 01 Regression.ipynb -------------------------------------------------------------------------------- /SparkML - 02 Credit Default.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/SparkML - 02 Credit Default.ipynb -------------------------------------------------------------------------------- /SparkML - 03 Image Classification (MNIST).ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/SparkML - 03 Image Classification (MNIST).ipynb -------------------------------------------------------------------------------- /SparkML - 04 Text_Analysis.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/SparkML - 04 Text_Analysis.ipynb -------------------------------------------------------------------------------- /Stocks Analyser.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/Stocks Analyser.ipynb -------------------------------------------------------------------------------- /data-conversion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/data-conversion.py -------------------------------------------------------------------------------- /kafka-clients/Load to Cassandra.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/kafka-clients/Load to Cassandra.ipynb -------------------------------------------------------------------------------- /kafka-clients/avro_consumer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/kafka-clients/avro_consumer.py -------------------------------------------------------------------------------- /kafka-clients/avro_producer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/kafka-clients/avro_producer.py -------------------------------------------------------------------------------- /kafka-clients/cassandra_schema.cql: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/kafka-clients/cassandra_schema.cql -------------------------------------------------------------------------------- /kafka-clients/json_consumer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/kafka-clients/json_consumer.py -------------------------------------------------------------------------------- /kafka-clients/json_producer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/kafka-clients/json_producer.py -------------------------------------------------------------------------------- /kafka-clients/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/kafka-clients/requirements.txt -------------------------------------------------------------------------------- /kafka-clients/spark_streaming.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/kafka-clients/spark_streaming.py -------------------------------------------------------------------------------- /kafka-clients/transactions.avsc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/kafka-clients/transactions.avsc -------------------------------------------------------------------------------- /kafka_stream_zk_dstream.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/kafka_stream_zk_dstream.py -------------------------------------------------------------------------------- /random_file_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/random_file_generator.py -------------------------------------------------------------------------------- /spark-stream-socket-hbase.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/spark-stream-socket-hbase.py -------------------------------------------------------------------------------- /spark_dstream_socket.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/spark_dstream_socket.py -------------------------------------------------------------------------------- /spark_file_dstream.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/spark_file_dstream.py -------------------------------------------------------------------------------- /spark_kafka_dstream.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/spark_kafka_dstream.py -------------------------------------------------------------------------------- /spark_stream_json_messages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/spark_stream_json_messages.py -------------------------------------------------------------------------------- /spark_streaming_hbase.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/spark_streaming_hbase.py -------------------------------------------------------------------------------- /spark_streaming_kafka_direct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/spark_streaming_kafka_direct.py -------------------------------------------------------------------------------- /stocks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/stocks.py -------------------------------------------------------------------------------- /stream_twitter_from_file.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/stream_twitter_from_file.py -------------------------------------------------------------------------------- /structured-streaming-socket.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/structured-streaming-socket.py -------------------------------------------------------------------------------- /structured_streaming_file_source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/structured_streaming_file_source.py -------------------------------------------------------------------------------- /structured_streaming_file_to_maprdb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/structured_streaming_file_to_maprdb.py -------------------------------------------------------------------------------- /structured_streaming_kafka.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/structured_streaming_kafka.py -------------------------------------------------------------------------------- /structured_streaming_kafka_aggregate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/structured_streaming_kafka_aggregate.py -------------------------------------------------------------------------------- /twitter_stream_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/abulbasar/pyspark-examples/HEAD/twitter_stream_api.py --------------------------------------------------------------------------------