Initial Commit

Author: LearningJournal

09-SlidingWindowDemo/SlidingWindowDemo.py

@@ -0,0 +1,55 @@
+from pyspark.sql import SparkSession
+from pyspark.sql.functions import from_json, col, to_timestamp, window
+from pyspark.sql.types import StructType, StructField, StringType, DoubleType
+
+from lib.logger import Log4j
+
+if __name__ == "__main__":
+    spark = SparkSession \
+        .builder \
+        .appName("Sliding Window Demo") \
+        .master("local[3]") \
+        .config("spark.streaming.stopGracefullyOnShutdown", "true") \
+        .getOrCreate()
+
+    logger = Log4j(spark)
+
+    invoice_schema = StructType([
+        StructField("InvoiceNumber", StringType()),
+        StructField("CreatedTime", StringType()),
+        StructField("StoreID", StringType()),
+        StructField("TotalAmount", DoubleType())
+    ])
+
+    kafka_df = spark.readStream \
+        .format("kafka") \
+        .option("kafka.bootstrap.servers", "localhost:9092") \
+        .option("subscribe", "invoices") \
+        .option("startingOffsets", "earliest") \
+        .load()
+
+    value_df = kafka_df.select(from_json(col("value").cast("string"), invoice_schema).alias("value"))
+
+    # value_df.printSchema()
+    # value_df.show(truncate=False)
+
+    invoice_df = value_df.select("value.*") \
+        .withColumn("CreatedTime", to_timestamp("CreatedTime", "yyyy-MM-dd HH:mm:ss"))
+
+    count_df = invoice_df.groupBy("StoreID",
+                                  window("CreatedTime", "5 minute", "1 minute")).count()
+
+    # count_df.printSchema()
+    # count_df.show(truncate=False)
+
+    output_df = count_df.select("StoreID", "window.start", "window.end", "count")
+
+    windowQuery = output_df.writeStream \
+        .format("console") \
+        .outputMode("update") \
+        .option("checkpointLocation", "chk-point-dir") \
+        .trigger(processingTime="1 minute") \
+        .start()
+
+    logger.info("Counting Invoices")
+    windowQuery.awaitTermination()

09-SlidingWindowDemo/data/samples.json

@@ -0,0 +1,3 @@
+STR1534:{"InvoiceNumber": 101,"CreatedTime": "2019-02-05 10:01:00","StoreID": "STR1534", "TotalAmount": 1920}
+STR1534:{"InvoiceNumber": 103,"CreatedTime": "2019-02-05 10:03:19","StoreID": "STR1534", "TotalAmount": 2400}
+STR1534:{"InvoiceNumber": 105,"CreatedTime": "2019-02-05 10:07:50","StoreID": "STR1534", "TotalAmount": 6375}

09-SlidingWindowDemo/kafka-scripts/01-start-zookeeper.cmd

@@ -0,0 +1 @@
+%KAFKA_HOME%\bin\windows\zookeeper-server-start.bat %KAFKA_HOME%\config\zookeeper.properties

09-SlidingWindowDemo/kafka-scripts/02-start-kafka.cmd

@@ -0,0 +1 @@
+%KAFKA_HOME%\bin\windows\kafka-server-start.bat %KAFKA_HOME%\config\server-0.properties

09-SlidingWindowDemo/kafka-scripts/03-create-input-topic.cmd

@@ -0,0 +1 @@
+%KAFKA_HOME%\bin\windows\kafka-topics.bat --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic invoices

09-SlidingWindowDemo/kafka-scripts/05-start-producer.cmd

@@ -0,0 +1 @@
+%KAFKA_HOME%\bin\windows\kafka-console-producer.bat --broker-list localhost:9092 --topic invoices --property "parse.key=true" --property "key.separator=:"

09-SlidingWindowDemo/lib/__init__.py

@@ -0,0 +1,21 @@
+class Log4j:
+    def __init__(self, spark):
+        log4j = spark._jvm.org.apache.log4j
+
+        root_class = "guru.learningjournal.spark.examples"
+        conf = spark.sparkContext.getConf()
+        app_name = conf.get("spark.app.name")
+
+        self.logger = log4j.LogManager.getLogger(root_class + "." + app_name)
+
+    def warn(self, message):
+        self.logger.warn(message)
+
+    def info(self, message):
+        self.logger.info(message)
+
+    def error(self, message):
+        self.logger.error(message)
+
+    def debug(self, message):
+        self.logger.debug(message)

09-SlidingWindowDemo/lib/logger.py

@@ -0,0 +1,27 @@
+# Set everything to be logged to the console
+log4j.rootCategory=WARN, console
+
+# define console appender
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.out
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n
+
+#application log
+log4j.logger.guru.learningjournal.spark.examples=INFO, console
+log4j.additivity.guru.learningjournal.spark.examples=false
+
+#define following in Java System
+# -Dlog4j.configuration=file:log4j.properties
+
+# Recommendations from Spark template
+log4j.logger.org.apache.spark.repl.Main=WARN
+log4j.logger.org.spark_project.jetty=WARN
+log4j.logger.org.spark_project.jetty.util.component.AbstractLifeCycle=ERROR
+log4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO
+log4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO
+log4j.logger.org.apache.parquet=ERROR
+log4j.logger.parquet=ERROR
+log4j.logger.org.apache.hadoop.hive.metastore.RetryingHMSHandler=FATAL
+log4j.logger.org.apache.hadoop.hive.ql.exec.FunctionRegistry=ERROR
+