word count: mapper and reducer in python using hadoop streaming

mapper.py

#!/usr/bin/env python
import sys

# input comes from STDIN (standard input)
for line in sys.stdin:
    #clean and split in words
    linechars = [c for c in line.lower() if c.isalpha() or c==' ']
    words     = ''.join(linechars).strip().split()

    #emit the key-balue pairs
    for word in words:
        print '%s\t%s' % (word, 1)

reducer.py

#!/usr/bin/env python

from operator import itemgetter
import sys

current_word = None
current_count = 0
word = None

# input comes from STDIN
for line in sys.stdin:
    # remove leading and trailing whitespace
    line = line.strip()

    # parse the input we got from mapper.py
    word, count = line.split('\t', 1)

    # convert count (currently a string) to int
    try:
        count = int(count)
    except ValueError:
        # count was not a number, so silently
        # ignore/discard this line
        continue

    # this IF-switch only works because Hadoop sorts map output
    # by key (here: word) before it is passed to the reducer
    if current_word == word:
        current_count += count
    else:
        if current_word:
            # write result to STDOUT
            print '%s\t%s' % (current_word, current_count)
        current_count = count
        current_word = word

# do not forget to output the last word if needed!
if current_word == word:
    print '%s\t%s' % (current_word, current_count)

run.sh

$HADOOP_HOME/bin/hadoop jar $HADOOP_HOME/share/hadoop/tools/lib/hadoop-streaming-2.3.0.jar \
  -mapper  ./mapper.py 
  -reducer ./reducer.py 
  -input wordcount-input 
  -output wordcount-mapreduce-streaming-python-output

$HADOOP_HOME/bin/hadoop fs cat wordcount-mapreduce-streaming-python-output/*