Initial Commit

Author: LearningJournal

12-MiscDemo/MiscDemo.py

@@ -0,0 +1,37 @@
+from pyspark.sql import SparkSession
+from pyspark.sql.functions import col, monotonically_increasing_id, when, expr
+from pyspark.sql.types import *
+
+from lib.logger import Log4j
+
+if __name__ == "__main__":
+    spark = SparkSession \
+        .builder \
+        .appName("Misc Demo") \
+        .master("local[2]") \
+        .getOrCreate()
+
+    logger = Log4j(spark)
+
+    data_list = [("Ravi", "28", "1", "2002"),
+                 ("Abdul", "23", "5", "81"),  # 1981
+                 ("John", "12", "12", "6"),  # 2006
+                 ("Rosy", "7", "8", "63"),  # 1963
+                 ("Abdul", "23", "5", "81")]  # 1981
+
+    raw_df = spark.createDataFrame(data_list).toDF("name", "day", "month", "year").repartition(3)
+    raw_df.printSchema()
+
+    final_df = raw_df.withColumn("id", monotonically_increasing_id()) \
+        .withColumn("day", col("day").cast(IntegerType())) \
+        .withColumn("month", col("month").cast(IntegerType())) \
+        .withColumn("year", col("year").cast(IntegerType())) \
+        .withColumn("year", when(col("year") < 20, col("year") + 2000)
+                    .when(col("year") < 100, col("year") + 1900)
+                    .otherwise(col("year"))) \
+        .withColumn("dob", expr("to_date(concat(day,'/',month,'/',year), 'd/M/y')")) \
+        .drop("day", "month", "year") \
+        .dropDuplicates(["name", "dob"]) \
+        .sort(expr("dob desc"))
+
+    final_df.show()

12-MiscDemo/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)

12-MiscDemo/lib/logger.py

@@ -0,0 +1,38 @@
+# 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, file
+log4j.additivity.guru.learningjournal.spark.examples=false
+
+#define rolling file appender
+log4j.appender.file=org.apache.log4j.RollingFileAppender
+log4j.appender.file.File=${spark.yarn.app.container.log.dir}/${logfile.name}.log
+#define following in Java System
+# -Dlog4j.configuration=file:log4j.properties
+# -Dlogfile.name=hello-spark
+# -Dspark.yarn.app.container.log.dir=app-logs
+log4j.appender.file.ImmediateFlush=true
+log4j.appender.file.Append=false
+log4j.appender.file.MaxFileSize=500MB
+log4j.appender.file.MaxBackupIndex=2
+log4j.appender.file.layout=org.apache.log4j.PatternLayout
+log4j.appender.file.layout.conversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n
+
+# 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
+