大数据hadoop系列：python实现MapReduce 词频统计

map代码：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代码：red_t.py

import sys

cur_word = None
sum = 0
for line in sys.stdin:
    word, val = line.strip().split(',')
    if cur_word == None:
        cur_word = word
    if cur_word != word:
        print '%s\t%s' % (cur_word, sum)
        cur_word = word
        sum = 0
    sum += int(val)
print '%s\t%s' % (cur_word, sum)

测试shell：

cat The_Man_of_Property.txt | python map_t.py |sort -k2|python red_t.py

run.sh

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_1="/data/The_Man_of_Property.txt"
OUTPUT_PATH="/output/wc"

$HADOOP_CMD fs -rmr -skipTrash $OUTPUT_PATH

$HADOOP_CMD jar $STREAM_JAR_PATH \
    -input $INPUT_FILE_PATH_1 \
    -output $OUTPUT_PATH \
    -mapper "python map_t.py" \
    -reducer "python red_t.py" \
    -file ./map_t.py \
    -file ./red_t.py