0
님이 hadoop에서 알고리즘을 구현하려고합니다. 은 내가 하둡의 코드의 일부를 실행하려고하지만, 작업을 스트리밍 내가 있는지 잘 모릅니다hadoop에서 스트리밍 작업이 실패했습니다.
#!/usr/bin/env python
import sys
import itertools
for line in sys.stdin:
input_key, input_value=line.split(' ',1)
input_key = input_key.strip()
input_value = input_value.strip()
input_key = int(input_key)
input_value = float(input_value)
print str(input_key)+' '+str(input_value)
$ /home/hadoop/hadoop/bin/hadoop jar contrib/streaming/hadoop-*-streaming.jar -file /home/hadoop/hadoop/PR/mapper.py -mapper mapper.py -file /home/hadoop/hadoop/PR/reducer.py -reducer reducer.py -input pagerank/* -output PRoutput6
packageJobJar: [/home/hadoop/hadoop/PR/mapper.py, /home/hadoop/hadoop/PR/reducer.py, /home/hadoop/hadoop/tmp/dir/hadoop-hadoop/hadoop-unjar7101759175212283428/] [] /tmp/streamjob6286075675343269479.jar tmpDir=null
11/04/23 01:03:24 INFO mapred.FileInputFormat: Total input paths to process : 1
11/04/23 01:03:24 INFO streaming.StreamJob: getLocalDirs(): [/home/hadoop/hadoop/tmp/dir/hadoop-hadoop/mapred/local]
11/04/23 01:03:24 INFO streaming.StreamJob: Running job: job_201104222325_0021
11/04/23 01:03:24 INFO streaming.StreamJob: To kill this job, run:
11/04/23 01:03:24 INFO streaming.StreamJob: /home/hadoop/hadoop/bin/../bin/hadoop job -Dmapred.job.tracker=localhost:54311 -kill job_201104222325_0021
11/04/23 01:03:24 INFO streaming.StreamJob: Tracking URL: http://localhost:50030/jobdetails.jsp?jobid=job_201104222325_0021
11/04/23 01:03:25 INFO streaming.StreamJob: map 0% reduce 0%
11/04/23 01:03:31 INFO streaming.StreamJob: map 50% reduce 0%
11/04/23 01:03:41 INFO streaming.StreamJob: map 50% reduce 17%
11/04/23 01:03:56 INFO streaming.StreamJob: map 100% reduce 100%
11/04/23 01:03:56 INFO streaming.StreamJob: To kill this job, run:
11/04/23 01:03:56 INFO streaming.StreamJob: /home/hadoop/hadoop/bin/../bin/hadoop job -Dmapred.job.tracker=localhost:54311 -kill job_201104222325_0021
11/04/23 01:03:56 INFO streaming.StreamJob: Tracking URL: http://localhost:50030/jobdetails.jsp?jobid=job_201104222325_0021
11/04/23 01:03:56 ERROR streaming.StreamJob: Job not Successful!
11/04/23 01:03:56 INFO streaming.StreamJob: killJob...
Streaming Job Failed!
mapper.py
#!/usr/bin/env python
import sys
import itertools
def ipsum(input_key,input_value_list):
return sum(input_value_list)
n= 20 # works up to about 1000000 pages
i = {}
for j in xrange(n): i[j] = [1.0/n,0,[]]
j=0
u=0
for line in sys.stdin:
if j<n:
i[j][1]=int(line)
j=j+1
if j > n:
if line != "-1\n":
i[u][2] = line.split(',')
else:
i[u][2]=[]
u=u+1
for j in xrange(n):
if i[j][1] != 0:
i[j][2] = map(int,i[j][2])
intermediate=[]
for (input_key,input_value) in i.items():
if input_value[1] == 0: intermediate.extend([(1,input_value[0])])
else: intermediate.extend([])
grp = {}
for key, group in itertools.groupby(sorted(intermediate),lambda x: x[0]):
grp[key] = list([y for x, y in group])
iplist = [ipsum(intermediate_key,grp[intermediate_key]) for intermediate_key in grp]
inter=[]
for (input_key,input_value) in i.items():
if input_value[1] == 0: inter.extend([(input_key,0.0)]+[(outlink,input_value[0]/input_value[1]) for outlink in input_value[2]])
else: inter.extend([])
for value in inter:
value1 = value[0]
value2 = value[1]
print '%s %s' % (value1,value2)
reducer.py 실패 오류는 내 코드 또는 hadoop 구성에 ...를 사용하여 코드를 실행할 수 있었기 때문에$ cat /home/hadoop/hadoop/PR/pagerank/input.txt | python /home/hadoop/hadoop/PR/mapper.py | 정렬 | python /home/hadoop/hadoop/PR/reducer.py
도움을 주시면 감사하겠습니다. 감사합니다.