Я довольно новичок в области больших данных.
У меня возникают проблемы при попытке выполнить задание уменьшения карты.Я пытаюсь решить проблему с подсчетом слов.
Я использую Ubuntu.На моем компьютере установлена версия python "Python 3.6.2".
Нужна помощь в определении проблемы.
Ниже приведен мой mapper.py
import sys
import re
reload(sys)
sys.setdefaultencoding('utf-8') # required to convert to unicode
for line in sys.stdin:
try:
article_id, text = unicode(line.strip()).split('\t', 1)
except ValueError as e:
continue
words = re.split("\W*\s+\W*", text, flags=re.UNICODE)
for word in words:
print >> sys.stderr, "reporter:counter:Wiki stats,Total words,%d" % 1
print ("%s\t%d" % (word.lower(), 1))
Ниже приведен мой reducer.py
import sys
current_key = None
word_sum = 0
for line in sys.stdin:
try:
key, count = line.strip().split('\t', 1)
count = int(count)
except ValueError as e:
continue
if current_key != key:
if current_key:
print "%s\t%d" % (current_key, word_sum)
word_sum = 0
current_key = key
word_sum += count
if current_key:
print "%s\t%d" % (current_key, word_sum)
Я запускаю следующую команду для выполнения задания уменьшения карты
OUT_DIR="wordcount_result_"$(date +"%s%6N")
NUM_REDUCERS=8
hdfs dfs -rm -r -skipTrash ${OUT_DIR} > /dev/null
yarn jar /opt/cloudera/parcels/CDH/lib/hadoop-mapreduce/hadoop-streaming.jar \
-D mapred.jab.name="Streaming wordCount" \
-D mapreduce.job.reduces=${NUM_REDUCERS} \
-files mapper.py,reducer.py \
-mapper "python mapper.py" \
-combiner "python reducer.py" \
-reducer "python reducer.py" \
-input /data/wiki/en_articles_part \
-output ${OUT_DIR} > /dev/null
Я получаю следующую ошибку:
rm: `wordcount_result_1548790436309903': No such file or directory
19/01/29 19:33:59 INFO client.RMProxy: Connecting to ResourceManager at /0.0.0.0:8032
19/01/29 19:33:59 INFO client.RMProxy: Connecting to ResourceManager at /0.0.0.0:8032
19/01/29 19:34:00 INFO mapred.FileInputFormat: Total input files to process : 1
19/01/29 19:34:00 INFO mapreduce.JobSubmitter: number of splits:2
19/01/29 19:34:00 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1548784954892_0004
19/01/29 19:34:00 INFO impl.YarnClientImpl: Submitted application application_1548784954892_0004
19/01/29 19:34:00 INFO mapreduce.Job: The url to track the job: http://15e399519cda:8088/proxy/application_1548784954892_0004/
19/01/29 19:34:00 INFO mapreduce.Job: Running job: job_1548784954892_0004
19/01/29 19:34:06 INFO mapreduce.Job: Job job_1548784954892_0004 running in uber mode : false
19/01/29 19:34:06 INFO mapreduce.Job: map 0% reduce 0%
19/01/29 19:34:12 INFO mapreduce.Job: Task Id : attempt_1548784954892_0004_m_000000_0, Status : FAILED
Error: java.lang.RuntimeException: PipeMapRed.waitOutputThreads(): subprocess failed with code 1
at org.apache.hadoop.streaming.PipeMapRed.waitOutputThreads(PipeMapRed.java:325)
at org.apache.hadoop.streaming.PipeMapRed.mapRedFinished(PipeMapRed.java:538)
at org.apache.hadoop.streaming.PipeMapper.close(PipeMapper.java:130)
at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:61)
at org.apache.hadoop.streaming.PipeMapRunner.run(PipeMapRunner.java:34)
at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:453)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:343)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:175)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1807)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:169)
19/01/29 19:34:12 INFO mapreduce.Job: Task Id : attempt_1548784954892_0004_m_000001_0, Status : FAILED
Error: java.lang.RuntimeException: PipeMapRed.waitOutputThreads(): subprocess failed with code 1
at org.apache.hadoop.streaming.PipeMapRed.waitOutputThreads(PipeMapRed.java:325)
at org.apache.hadoop.streaming.PipeMapRed.mapRedFinished(PipeMapRed.java:538)
at org.apache.hadoop.streaming.PipeMapper.close(PipeMapper.java:130)
at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:61)
at org.apache.hadoop.streaming.PipeMapRunner.run(PipeMapRunner.java:34)
at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:453)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:343)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:175)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1807)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:169)
19/01/29 19:34:17 INFO mapreduce.Job: Task Id : attempt_1548784954892_0004_m_000001_1, Status : FAILED
Error: java.lang.RuntimeException: PipeMapRed.waitOutputThreads(): subprocess failed with code 1
at org.apache.hadoop.streaming.PipeMapRed.waitOutputThreads(PipeMapRed.java:325)
at org.apache.hadoop.streaming.PipeMapRed.mapRedFinished(PipeMapRed.java:538)
at org.apache.hadoop.streaming.PipeMapper.close(PipeMapper.java:130)
at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:61)
at org.apache.hadoop.streaming.PipeMapRunner.run(PipeMapRunner.java:34)
at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:453)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:343)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:175)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1807)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:169)
19/01/29 19:34:17 INFO mapreduce.Job: Task Id : attempt_1548784954892_0004_m_000000_1, Status : FAILED
Error: java.lang.RuntimeException: PipeMapRed.waitOutputThreads(): subprocess failed with code 1
at org.apache.hadoop.streaming.PipeMapRed.waitOutputThreads(PipeMapRed.java:325)
at org.apache.hadoop.streaming.PipeMapRed.mapRedFinished(PipeMapRed.java:538)
at org.apache.hadoop.streaming.PipeMapper.close(PipeMapper.java:130)
at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:61)
at org.apache.hadoop.streaming.PipeMapRunner.run(PipeMapRunner.java:34)
at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:453)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:343)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:175)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1807)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:169)
19/01/29 19:34:22 INFO mapreduce.Job: Task Id : attempt_1548784954892_0004_m_000001_2, Status : FAILED
Error: java.lang.RuntimeException: PipeMapRed.waitOutputThreads(): subprocess failed with code 1
at org.apache.hadoop.streaming.PipeMapRed.waitOutputThreads(PipeMapRed.java:325)
at org.apache.hadoop.streaming.PipeMapRed.mapRedFinished(PipeMapRed.java:538)
at org.apache.hadoop.streaming.PipeMapper.close(PipeMapper.java:130)
at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:61)
at org.apache.hadoop.streaming.PipeMapRunner.run(PipeMapRunner.java:34)
at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:453)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:343)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:175)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1807)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:169)
19/01/29 19:34:23 INFO mapreduce.Job: Task Id : attempt_1548784954892_0004_m_000000_2, Status : FAILED
Error: java.lang.RuntimeException: PipeMapRed.waitOutputThreads(): subprocess failed with code 1
at org.apache.hadoop.streaming.PipeMapRed.waitOutputThreads(PipeMapRed.java:325)
at org.apache.hadoop.streaming.PipeMapRed.mapRedFinished(PipeMapRed.java:538)
at org.apache.hadoop.streaming.PipeMapper.close(PipeMapper.java:130)
at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:61)
at org.apache.hadoop.streaming.PipeMapRunner.run(PipeMapRunner.java:34)
at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:453)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:343)
at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:175)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1807)
at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:169)
19/01/29 19:34:27 INFO mapreduce.Job: map 100% reduce 100%
19/01/29 19:34:28 INFO mapreduce.Job: Job job_1548784954892_0004 failed with state FAILED due to: Task failed task_1548784954892_0004_m_000001
Job failed as tasks failed. failedMaps:1 failedReduces:0
19/01/29 19:34:28 INFO mapreduce.Job: Counters: 17
Job Counters
Failed map tasks=7
Killed map tasks=1
Killed reduce tasks=8
Launched map tasks=8
Other local map tasks=6
Data-local map tasks=2
Total time spent by all maps in occupied slots (ms)=24941
Total time spent by all reduces in occupied slots (ms)=0
Total time spent by all map tasks (ms)=24941
Total time spent by all reduce tasks (ms)=0
Total vcore-milliseconds taken by all map tasks=24941
Total vcore-milliseconds taken by all reduce tasks=0
Total megabyte-milliseconds taken by all map tasks=25539584
Total megabyte-milliseconds taken by all reduce tasks=0
Map-Reduce Framework
CPU time spent (ms)=0
Physical memory (bytes) snapshot=0
Virtual memory (bytes) snapshot=0
19/01/29 19:34:28 ERROR streaming.StreamJob: Job not successful!
Streaming Command Failed!
cat: `wordcount_result_1548790436309903/part-00000': No such file or directory