Initial Commit

Author: LearningJournal

02-HelloRDD/HelloRDD.py

@@ -0,0 +1,33 @@
+import sys
+
+from pyspark import SparkConf, SparkContext
+from collections import namedtuple
+
+from pyspark.sql import SparkSession
+
+from lib.logger import Log4j
+
+SurveyRecord = namedtuple("SurveyRecord", ["Age", "Gender", "Country", "State"])
+
+if __name__ == "__main__":
+    conf = SparkConf() \
+        .setMaster("local[3]") \
+        .setAppName("HelloRDD")
+
+    # sc = SparkContext(conf=conf)
+    spark = SparkSession.builder.config(conf=conf).getOrCreate()
+    sc = spark.sparkContext
+    logger = Log4j(spark)
+
+    linesRDD = sc.textFile(sys.argv[1])
+    partitionedRDD = linesRDD.repartition(2)
+
+    colsRDD = partitionedRDD.map(lambda line: line.replace('"', '').split(","))
+    selectRDD = colsRDD.map(lambda cols: SurveyRecord(int(cols[1]), cols[2], cols[3], cols[4]))
+    filteredRDD = selectRDD.filter(lambda r: r.Age < 40)
+    kvRDD = filteredRDD.map(lambda r: (r.Country, 1))
+    countRDD = kvRDD.reduceByKey(lambda v1, v2: v1 + v2)
+
+    colsList = countRDD.collect()
+    for x in colsList:
+        logger.info(x)

02-HelloRDD/data/sample.csv

@@ -0,0 +1,9 @@
+2014-08-27 11:29:31,37,"Female","United States","IL",NA,"No","Yes","Often","6-25","No","Yes","Yes","Not sure","No","Yes","Yes","Somewhat easy","No","No","Some of them","Yes","No","Maybe","Yes","No",NA
+2014-08-27 11:29:37,44,"M","United States","IN",NA,"No","No","Rarely","More than 1000","No","No","Don't know","No","Don't know","Don't know","Don't know","Don't know","Maybe","No","No","No","No","No","Don't know","No",NA
+2014-08-27 11:29:44,32,"Male","Canada",NA,NA,"No","No","Rarely","6-25","No","Yes","No","No","No","No","Don't know","Somewhat difficult","No","No","Yes","Yes","Yes","Yes","No","No",NA
+2014-08-27 11:29:46,31,"Male","United Kingdom",NA,NA,"Yes","Yes","Often","26-100","No","Yes","No","Yes","No","No","No","Somewhat difficult","Yes","Yes","Some of them","No","Maybe","Maybe","No","Yes",NA
+2014-08-27 11:30:22,31,"Male","United States","TX",NA,"No","No","Never","100-500","Yes","Yes","Yes","No","Don't know","Don't know","Don't know","Don't know","No","No","Some of them","Yes","Yes","Yes","Don't know","No",NA
+2014-08-27 11:31:22,33,"Male","United States","TN",NA,"Yes","No","Sometimes","6-25","No","Yes","Yes","Not sure","No","Don't know","Don't know","Don't know","No","No","Yes","Yes","No","Maybe","Don't know","No",NA
+2014-08-27 11:31:50,35,"Female","United States","MI",NA,"Yes","Yes","Sometimes","1-5","Yes","Yes","No","No","No","No","No","Somewhat difficult","Maybe","Maybe","Some of them","No","No","No","Don't know","No",NA
+2014-08-27 11:32:05,39,"M","Canada",NA,NA,"No","No","Never","1-5","Yes","Yes","No","Yes","No","No","Yes","Don't know","No","No","No","No","No","No","No","No",NA
+2014-08-27 11:32:39,42,"Female","United States","IL",NA,"Yes","Yes","Sometimes","100-500","No","Yes","Yes","Yes","No","No","No","Very difficult","Maybe","No","Yes","Yes","No","Maybe","No","No",NA

02-HelloRDD/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)

02-HelloRDD/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
+