sales_HDFS.txt

---------------------------------------------------------------
mapper.py
#!/usr/bin/python
import sys
for line in sys.stdin:
    data = line.strip().split("\t")
    if len(data) == 6:
        date, time, store, item, cost, payment = data
        print ("{0}\t{1}".format(store, cost))

----------------------------------------------------------------
reducer.py

#!/usr/bin/python
import sys

salesTotal = 0
oldKey = None

for line in sys.stdin:
    data_mapped = line.strip().split("\t")
    if len(data_mapped) != 2:
        continue

    thisKey, thisSale = data_mapped

    if oldKey and oldKey != thisKey:
        print(oldKey, "\t", salesTotal)
        oldKey = thisKey
        salesTotal = 0

    oldKey = thisKey
    salesTotal += float(thisSale)

if oldKey is not None:
    print(oldKey, "\t", salesTotal)


> hadoop jar /usr/lib/hadoop-mapreduce/hadoop-streaming.jar \
-input /user/cloudera/input \
-output /user/cloudera/output \
-mapper /home/cloudera/mapper.py \
-reducer /home/cloudera/reducer.py

>hdfs dfsadmin -safemode leave