本文整理汇总了Java中org.apache.hadoop.examples.WordCount.IntSumReducer类的典型用法代码示例。如果您正苦于以下问题:Java IntSumReducer类的具体用法?Java IntSumReducer怎么用?Java IntSumReducer使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
IntSumReducer类属于org.apache.hadoop.examples.WordCount包,在下文中一共展示了IntSumReducer类的6个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Java代码示例。
示例1: main
import org.apache.hadoop.examples.WordCount.IntSumReducer; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
long maxInputSplitSize = Long.parseLong(otherArgs[otherArgs.length-1]);
long minInputSplitSize = Long.parseLong(otherArgs[otherArgs.length-2]);
//added by wei
conf.setLong(CombineTextInputFormat.SPLIT_MINSIZE_PERNODE, minInputSplitSize);
conf.setLong(CombineTextInputFormat.SPLIT_MINSIZE_PERRACK, minInputSplitSize);
//----
if (otherArgs.length < 2) {
System.err.println("Usage: wordcount <in> [<in>...] <out>");
System.exit(2);
}
Job job = new Job(conf, "mulword count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
//added by wei
job.setInputFormatClass(CombineTextInputFormat.class);
CombineTextInputFormat.setMaxInputSplitSize(job, maxInputSplitSize);
//----
for (int i = 0; i < otherArgs.length - 3; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
FileOutputFormat.setOutputPath(job,
new Path(otherArgs[otherArgs.length - 3]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
开发者ID:yncxcw,项目名称:big-c,代码行数:40,代码来源:MutiWordcount.java
示例2: runWordCount
import org.apache.hadoop.examples.WordCount.IntSumReducer; //导入依赖的package包/类
private void runWordCount(Configuration conf
) throws IOException,
InterruptedException,
ClassNotFoundException {
final String COUNTER_GROUP = "org.apache.hadoop.mapred.Task$Counter";
localFs.delete(new Path(TEST_ROOT_DIR + "/in"), true);
localFs.delete(new Path(TEST_ROOT_DIR + "/out"), true);
writeFile("in/part1", "this is a test\nof word count test\ntest\n");
writeFile("in/part2", "more test");
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TrackingTextInputFormat.class);
FileInputFormat.addInputPath(job, new Path(TEST_ROOT_DIR + "/in"));
FileOutputFormat.setOutputPath(job, new Path(TEST_ROOT_DIR + "/out"));
assertNull(job.getJobID());
assertTrue(job.waitForCompletion(false));
assertNotNull(job.getJobID());
String out = readFile("out/part-r-00000");
System.out.println(out);
assertEquals("a\t1\ncount\t1\nis\t1\nmore\t1\nof\t1\ntest\t4\nthis\t1\nword\t1\n",
out);
Counters ctrs = job.getCounters();
System.out.println("Counters: " + ctrs);
long combineIn = ctrs.findCounter(COUNTER_GROUP,
"COMBINE_INPUT_RECORDS").getValue();
long combineOut = ctrs.findCounter(COUNTER_GROUP,
"COMBINE_OUTPUT_RECORDS").getValue();
long reduceIn = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_INPUT_RECORDS").getValue();
long mapOut = ctrs.findCounter(COUNTER_GROUP,
"MAP_OUTPUT_RECORDS").getValue();
long reduceOut = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_OUTPUT_RECORDS").getValue();
long reduceGrps = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_INPUT_GROUPS").getValue();
assertEquals("map out = combine in", mapOut, combineIn);
assertEquals("combine out = reduce in", combineOut, reduceIn);
assertTrue("combine in > combine out", combineIn > combineOut);
assertEquals("reduce groups = reduce out", reduceGrps, reduceOut);
String group = "Random Group";
CounterGroup ctrGrp = ctrs.getGroup(group);
assertEquals(0, ctrGrp.size());
}
开发者ID:Nextzero,项目名称:hadoop-2.6.0-cdh5.4.3,代码行数:49,代码来源:TestMapReduceLocal.java
示例3: runWordCount
import org.apache.hadoop.examples.WordCount.IntSumReducer; //导入依赖的package包/类
private void runWordCount(Configuration conf
) throws IOException,
InterruptedException,
ClassNotFoundException {
final String COUNTER_GROUP = "org.apache.hadoop.mapred.Task$Counter";
localFs.delete(new Path(TEST_ROOT_DIR + "/in"), true);
localFs.delete(new Path(TEST_ROOT_DIR + "/out"), true);
writeFile("in/part1", "this is a test\nof word count test\ntest\n");
writeFile("in/part2", "more test");
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TrackingTextInputFormat.class);
FileInputFormat.addInputPath(job, new Path(TEST_ROOT_DIR + "/in"));
FileOutputFormat.setOutputPath(job, new Path(TEST_ROOT_DIR + "/out"));
assertTrue(job.waitForCompletion(false));
String out = readFile("out/part-r-00000");
System.out.println(out);
assertEquals("a\t1\ncount\t1\nis\t1\nmore\t1\nof\t1\ntest\t4\nthis\t1\nword\t1\n",
out);
Counters ctrs = job.getCounters();
System.out.println("Counters: " + ctrs);
long combineIn = ctrs.findCounter(COUNTER_GROUP,
"COMBINE_INPUT_RECORDS").getValue();
long combineOut = ctrs.findCounter(COUNTER_GROUP,
"COMBINE_OUTPUT_RECORDS").getValue();
long reduceIn = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_INPUT_RECORDS").getValue();
long mapOut = ctrs.findCounter(COUNTER_GROUP,
"MAP_OUTPUT_RECORDS").getValue();
long reduceOut = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_OUTPUT_RECORDS").getValue();
long reduceGrps = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_INPUT_GROUPS").getValue();
assertEquals("map out = combine in", mapOut, combineIn);
assertEquals("combine out = reduce in", combineOut, reduceIn);
assertTrue("combine in > combine out", combineIn > combineOut);
assertEquals("reduce groups = reduce out", reduceGrps, reduceOut);
String group = "Random Group";
CounterGroup ctrGrp = ctrs.getGroup(group);
assertEquals(0, ctrGrp.size());
}
开发者ID:rhli,项目名称:hadoop-EAR,代码行数:47,代码来源:TestMapReduceLocal.java
示例4: runWordCount
import org.apache.hadoop.examples.WordCount.IntSumReducer; //导入依赖的package包/类
private void runWordCount(Configuration conf
) throws IOException,
InterruptedException,
ClassNotFoundException {
final String COUNTER_GROUP = "org.apache.hadoop.mapred.Task$Counter";
localFs.delete(new Path(TEST_ROOT_DIR + "/in"), true);
localFs.delete(new Path(TEST_ROOT_DIR + "/out"), true);
writeFile("in/part1", "this is a test\nof word count test\ntest\n");
writeFile("in/part2", "more test");
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TrackingTextInputFormat.class);
FileInputFormat.addInputPath(job, new Path(TEST_ROOT_DIR + "/in"));
FileOutputFormat.setOutputPath(job, new Path(TEST_ROOT_DIR + "/out"));
assertNull("job.getJobID() must be null before the job is submitted",
job.getJobID());
job.submit();
assertNotNull("job.getJobID() can't be null after the job is submitted",
job.getJobID());
assertTrue(job.waitForCompletion(false));
assertNotNull("job.getJobID() can't be null again after the job is finished",
job.getJobID());
String out = readFile("out/part-r-00000");
System.out.println(out);
assertEquals("a\t1\ncount\t1\nis\t1\nmore\t1\nof\t1\ntest\t4\nthis\t1\nword\t1\n",
out);
Counters ctrs = job.getCounters();
System.out.println("Counters: " + ctrs);
long combineIn = ctrs.findCounter(COUNTER_GROUP,
"COMBINE_INPUT_RECORDS").getValue();
long combineOut = ctrs.findCounter(COUNTER_GROUP,
"COMBINE_OUTPUT_RECORDS").getValue();
long reduceIn = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_INPUT_RECORDS").getValue();
long mapOut = ctrs.findCounter(COUNTER_GROUP,
"MAP_OUTPUT_RECORDS").getValue();
long reduceOut = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_OUTPUT_RECORDS").getValue();
long reduceGrps = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_INPUT_GROUPS").getValue();
assertEquals("map out = combine in", mapOut, combineIn);
assertEquals("combine out = reduce in", combineOut, reduceIn);
assertTrue("combine in > combine out", combineIn > combineOut);
assertEquals("reduce groups = reduce out", reduceGrps, reduceOut);
String group = "Random Group";
CounterGroup ctrGrp = ctrs.getGroup(group);
assertEquals(0, ctrGrp.size());
}
开发者ID:Seagate,项目名称:hadoop-on-lustre,代码行数:54,代码来源:TestMapReduceLocal.java
示例5: runWordCount
import org.apache.hadoop.examples.WordCount.IntSumReducer; //导入依赖的package包/类
private void runWordCount(Configuration conf
) throws IOException,
InterruptedException,
ClassNotFoundException {
final String COUNTER_GROUP = "org.apache.hadoop.mapreduce.TaskCounter";
localFs.delete(new Path(TEST_ROOT_DIR + "/in"), true);
localFs.delete(new Path(TEST_ROOT_DIR + "/out"), true);
writeFile("in/part1", "this is a test\nof word count test\ntest\n");
writeFile("in/part2", "more test");
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TrackingTextInputFormat.class);
FileInputFormat.addInputPath(job, new Path(TEST_ROOT_DIR + "/in"));
FileOutputFormat.setOutputPath(job, new Path(TEST_ROOT_DIR + "/out"));
assertTrue(job.waitForCompletion(false));
String out = readFile("out/part-r-00000");
System.out.println(out);
assertEquals("a\t1\ncount\t1\nis\t1\nmore\t1\nof\t1\ntest\t4\nthis\t1\nword\t1\n",
out);
Counters ctrs = job.getCounters();
System.out.println("Counters: " + ctrs);
long mapIn = ctrs.findCounter(FileInputFormat.COUNTER_GROUP,
FileInputFormat.BYTES_READ).getValue();
assertTrue(mapIn != 0);
long combineIn = ctrs.findCounter(COUNTER_GROUP,
"COMBINE_INPUT_RECORDS").getValue();
long combineOut = ctrs.findCounter(COUNTER_GROUP,
"COMBINE_OUTPUT_RECORDS").getValue();
long reduceIn = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_INPUT_RECORDS").getValue();
long mapOut = ctrs.findCounter(COUNTER_GROUP,
"MAP_OUTPUT_RECORDS").getValue();
long reduceOut = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_OUTPUT_RECORDS").getValue();
long reduceGrps = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_INPUT_GROUPS").getValue();
long mergedMapOutputs = ctrs.findCounter(COUNTER_GROUP,
"MERGED_MAP_OUTPUTS").getValue();
long shuffledMaps = ctrs.findCounter(COUNTER_GROUP,
"SHUFFLED_MAPS").getValue();
assertEquals("map out = combine in", mapOut, combineIn);
assertEquals("combine out = reduce in", combineOut, reduceIn);
assertTrue("combine in > combine out", combineIn > combineOut);
assertEquals("reduce groups = reduce out", reduceGrps, reduceOut);
assertEquals("Mismatch in mergedMapOutputs", mergedMapOutputs, 2);
assertEquals("Mismatch in shuffledMaps", shuffledMaps, 2);
String group = "Random Group";
CounterGroup ctrGrp = ctrs.getGroup(group);
assertEquals(0, ctrGrp.size());
}
开发者ID:rekhajoshm,项目名称:mapreduce-fork,代码行数:56,代码来源:TestMapReduceLocal.java
示例6: runWordCount
import org.apache.hadoop.examples.WordCount.IntSumReducer; //导入依赖的package包/类
private void runWordCount(Configuration conf
) throws IOException,
InterruptedException,
ClassNotFoundException {
final String COUNTER_GROUP = "org.apache.hadoop.mapred.Task$Counter";
localFs.delete(new Path(TEST_ROOT_DIR + "/in"), true);
localFs.delete(new Path(TEST_ROOT_DIR + "/out"), true);
writeFile("in/part1", "this is a test\nof word count test\ntest\n");
writeFile("in/part2", "more test");
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TrackingTextInputFormat.class);
FileInputFormat.addInputPath(job, new Path(TEST_ROOT_DIR + "/in"));
FileOutputFormat.setOutputPath(job, new Path(TEST_ROOT_DIR + "/out"));
assertTrue(job.waitForCompletion(false));
String out = readFile("out/part-r-00000");
System.out.println(out);
assertEquals("a\t1\ncount\t1\nis\t1\nmore\t1\nof\t1\ntest\t4\nthis\t1\nword\t1\n",
out);
Counters ctrs = job.getCounters();
System.out.println("Counters: " + ctrs);
long combineIn = ctrs.findCounter(COUNTER_GROUP,
"COMBINE_INPUT_RECORDS").getValue();
long combineOut = ctrs.findCounter(COUNTER_GROUP,
"COMBINE_OUTPUT_RECORDS").getValue();
long reduceIn = ctrs.findCounter(COUNTER_GROUP,
"REDUCE_INPUT_RECORDS").getValue();
long mapOut = ctrs.findCounter(COUNTER_GROUP,
"MAP_OUTPUT_RECORDS").getValue();
assertEquals("map out = combine in", mapOut, combineIn);
assertEquals("combine out = reduce in", combineOut, reduceIn);
assertTrue("combine in > combine out", combineIn > combineOut);
String group = "Random Group";
CounterGroup ctrGrp = ctrs.getGroup(group);
assertEquals(0, ctrGrp.size());
}
开发者ID:koichi626,项目名称:hadoop-gpu,代码行数:42,代码来源:TestMapReduceLocal.java
注:本文中的org.apache.hadoop.examples.WordCount.IntSumReducer类示例整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。 |
请发表评论