gistfile1.txt

su hdfs
hadoop fs –mkdir /user/root

hadoop fs –chmod 777 /user/root 
hadoop fs –chmod 777 /user/guest
exit


wget http://www.gutenberg.org/files/50831/50831-0.txt

hadoop fs -copyFromLocal ./50831-0.txt /user/guest/


hadoop fs -put ./install.log /user/guest/install.log



pyspark... 

text_file = sc.textFile("hdfs://sandbox.hortonworks.com/user/guest/install.log")
counts = text_file.flatMap( lambda line: line.split(" ")) \
.map(lambda word: (word, 1) ) \
.reduceByKey(lambda a, b : a + b)
counts.saveAsTextFile("hdfs://sandbox.hortonworks.com/user/guest/output1.txt")