Python MapReduce 案例

map_t.py

import sys
import re

p = re.compile(r'\w+')
for line in sys.stdin:
    ss = line.strip().split(' ')
    for s in ss:
        if len(p.findall(s)) < 1:
            continue
        s_low = p.findall(s)[0].lower()
        print(s_low + ',' + '1')

reduce_t.py 

import sys

cur_word = None
s = 0
for line in sys.stdin:
    word, val = line.strip().split(',')

    if cur_word is None:
        cur_word = word
    if cur_word != word:
        print('%s\t%s' % (cur_word, s))
        cur_word = word
        s = 0
    s += int(val)
print('%s\t%s' % (cur_word, sum))

HADOOP_CMD="/usr/local/src/hadoop-2.6.1/bin/hadoop"
STREAM_JAR_PATH="/usr/local/src/hadoop-2.6.1/share/hadoop/tools/lib/hadoop-streaming-2.6.1.jar"

INPUT_FILE_PATH="/data/words.txt"
OUTPUT_PATH="/output/wc"

$HADOOP_CMD fs -rmr -skipTrash $OUTPUT_PATH

# Step 1.
$HADOOP_CMD jar $STREAM_JAR_PATH \
    -input $INPUT_FILE_PATH \
    -output $OUTPUT_PATH \
    -mapper "python map_t.py" \
    -reducer "python red_t.py" \
    -file ./map_t.py \
    -file ./red_t.py