MapReduce数据清洗
Result文件数据说明：
Ip：106.39.41.166,（城市）
Date：10/Nov/2016:00:01:02 +0800,（日期）
Day：10,（天数）
Traffic: 54 ,（流量）
Type: video,（类型：视频video或文章article）
Id: 8701（视频或者文章的id）
测试要求：
2、数据处理：
·统计最受欢迎的视频/文章的Top10访问次数 （video/article）
·按照地市统计最受欢迎的Top10课程 （ip）
·按照流量统计最受欢迎的Top10课程 （traffic）
1、
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
|
package test4;import java.io.IOException; import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.io.WritableComparable;import org.apache.hadoop.mapreduce.Job;import org.apache.hadoop.mapreduce.Mapper;import org.apache.hadoop.mapreduce.Reducer;import org.apache.hadoop.mapreduce.Reducer.Context;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;public class quchong {public static void main(String[] args) throws IOException,ClassNotFoundException,InterruptedException {Job job = Job.getInstance();job.setJobName("paixu");job.setJarByClass(quchong.class);job.setMapperClass(doMapper.class);job.setReducerClass(doReducer.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(IntWritable.class);Path in = new Path("hdfs://localhost:9000/test/in/result");Path out = new Path("hdfs://localhost:9000/test/stage3/out1");FileInputFormat.addInputPath(job,in);FileOutputFormat.setOutputPath(job,out);////if(job.waitForCompletion(true)){Job job2 = Job.getInstance();job2.setJobName("paixu"); job2.setJarByClass(quchong.class); job2.setMapperClass(doMapper2.class); job2.setReducerClass(doReduce2.class); job2.setOutputKeyClass(IntWritable.class); job2.setOutputValueClass(Text.class); job2.setSortComparatorClass(IntWritableDecreasingComparator.class); job2.setInputFormatClass(TextInputFormat.class); job2.setOutputFormatClass(TextOutputFormat.class); Path in2=new Path("hdfs://localhost:9000/test/stage3/out1/part-r-00000"); Path out2=new Path("hdfs://localhost:9000/test/stage3/out2"); FileInputFormat.addInputPath(job2,in2); FileOutputFormat.setOutputPath(job2,out2); System.exit(job2.waitForCompletion(true) ? 0 : 1);}}public static class doMapper extends Mapper<Object,Text,Text,IntWritable>{public static final IntWritable one = new IntWritable(1);public static Text word = new Text();@Overrideprotected void map(Object key, Text value, Context context)throws IOException,InterruptedException {//StringTokenizer tokenizer = new StringTokenizer(value.toString()," "); String[] strNlist = value.toString().split(","); // String str=strNlist[3].trim(); String str2=strNlist[4]+strNlist[5];// Integer temp= Integer.valueOf(str);word.set(str2);//IntWritable abc = new IntWritable(temp);context.write(word,one);}}public static class doReducer extends Reducer<Text,IntWritable,Text,IntWritable>{private IntWritable result = new IntWritable();@Overrideprotected void reduce(Text key,Iterable<IntWritable> values,Context context)throws IOException,InterruptedException{int sum = 0;for (IntWritable value : values){sum += value.get();}result.set(sum);context.write(key,result);}}/////////////////public static class doMapper2 extends Mapper<Object , Text , IntWritable,Text>{private static Text goods=new Text(); private static IntWritable num=new IntWritable(); @Overrideprotected void map(Object key, Text value, Context context)throws IOException,InterruptedException { String line=value.toString(); String arr[]=line.split(" "); num.set(Integer.parseInt(arr[1])); goods.set(arr[0]); context.write(num,goods);}}public static class doReduce2 extends Reducer< IntWritable, Text, IntWritable, Text>{ private static IntWritable result= new IntWritable(); int i=0; public void reduce(IntWritable key,Iterable<Text> values,Context context) throws IOException, InterruptedException{ for(Text val:values){ if(i<10) { context.write(key,val); i++; } } } } private static class IntWritableDecreasingComparator extends IntWritable.Comparator { public int compare(WritableComparable a, WritableComparable b) { return -super.compare(a, b); } public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) { return -super.compare(b1, s1, l1, b2, s2, l2); }}} |
（去重，并输出访问次数）
（排序，输出Top10）
2、
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
|
package test3; import java.io.IOException; import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.io.WritableComparable;import org.apache.hadoop.mapreduce.Job;import org.apache.hadoop.mapreduce.Mapper;import org.apache.hadoop.mapreduce.Reducer;import org.apache.hadoop.mapreduce.Reducer.Context;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;import test4.quchong.doMapper2;import test4.quchong.doReduce2;public class quchong {public static void main(String[] args) throws IOException,ClassNotFoundException,InterruptedException {Job job = Job.getInstance();job.setJobName("paixu");job.setJarByClass(quchong.class);job.setMapperClass(doMapper.class);job.setReducerClass(doReducer.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(IntWritable.class);Path in = new Path("hdfs://localhost:9000/test/in/result");Path out = new Path("hdfs://localhost:9000/test/stage2/out1");FileInputFormat.addInputPath(job,in);FileOutputFormat.setOutputPath(job,out);if(job.waitForCompletion(true)){Job job2 = Job.getInstance();job2.setJobName("paixu"); job2.setJarByClass(quchong.class); job2.setMapperClass(doMapper2.class); job2.setReducerClass(doReduce2.class); job2.setOutputKeyClass(IntWritable.class); job2.setOutputValueClass(Text.class); job2.setSortComparatorClass(IntWritableDecreasingComparator.class); job2.setInputFormatClass(TextInputFormat.class); job2.setOutputFormatClass(TextOutputFormat.class); Path in2=new Path("hdfs://localhost:9000/test/stage2/out1/part-r-00000"); Path out2=new Path("hdfs://localhost:9000/test/stage2/out2"); FileInputFormat.addInputPath(job2,in2); FileOutputFormat.setOutputPath(job2,out2); System.exit(job2.waitForCompletion(true) ? 0 : 1);}}public static class doMapper extends Mapper<Object,Text,Text,IntWritable>{public static final IntWritable one = new IntWritable(1);public static Text word = new Text();@Overrideprotected void map(Object key, Text value, Context context)throws IOException,InterruptedException {//StringTokenizer tokenizer = new StringTokenizer(value.toString()," "); String[] strNlist = value.toString().split(","); // String str=strNlist[3].trim(); String str2=strNlist[0];// Integer temp= Integer.valueOf(str);word.set(str2);//IntWritable abc = new IntWritable(temp);context.write(word,one);}}public static class doReducer extends Reducer<Text,IntWritable,Text,IntWritable>{private IntWritable result = new IntWritable();@Overrideprotected void reduce(Text key,Iterable<IntWritable> values,Context context)throws IOException,InterruptedException{int sum = 0;for (IntWritable value : values){sum += value.get();}result.set(sum);context.write(key,result);}}////////////////public static class doMapper2 extends Mapper<Object , Text , IntWritable,Text>{private static Text goods=new Text(); private static IntWritable num=new IntWritable(); @Overrideprotected void map(Object key, Text value, Context context)throws IOException,InterruptedException { String line=value.toString(); String arr[]=line.split(" "); num.set(Integer.parseInt(arr[1])); goods.set(arr[0]); context.write(num,goods);}}public static class doReduce2 extends Reducer< IntWritable, Text, IntWritable, Text>{ private static IntWritable result= new IntWritable(); int i=0; public void reduce(IntWritable key,Iterable<Text> values,Context context) throws IOException, InterruptedException{ for(Text val:values){ if(i<10) { context.write(key,val); i++; } } } } private static class IntWritableDecreasingComparator extends IntWritable.Comparator { public int compare(WritableComparable a, WritableComparable b) { return -super.compare(a, b); } public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) { return -super.compare(b1, s1, l1, b2, s2, l2); }}} |
（去重，显示ip次数）
（排序，输出Top10）
3、
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
|
package test2; import java.io.IOException;import java.text.SimpleDateFormat;import java.util.Date;import java.util.Locale;import java.util.StringTokenizer;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.io.WritableComparable;import org.apache.hadoop.mapreduce.Job;import org.apache.hadoop.mapreduce.Mapper;import org.apache.hadoop.mapreduce.Reducer;import org.apache.hadoop.mapreduce.Reducer.Context;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import test3.quchong;import test3.quchong.doMapper2;import test3.quchong.doReduce2;public class paixu {public static void main(String[] args) throws IOException,ClassNotFoundException,InterruptedException {Job job = Job.getInstance();job.setJobName("paixu");job.setJarByClass(paixu.class);job.setMapperClass(doMapper.class);job.setReducerClass(doReducer.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(IntWritable.class);Path in = new Path("hdfs://localhost:9000/test/in/result");Path out = new Path("hdfs://localhost:9000/test/stage1/out1");FileInputFormat.addInputPath(job,in);FileOutputFormat.setOutputPath(job,out);if(job.waitForCompletion(true)){Job job2 = Job.getInstance();job2.setJobName("paixu"); job2.setJarByClass(quchong.class); job2.setMapperClass(doMapper2.class); job2.setReducerClass(doReduce2.class); job2.setOutputKeyClass(IntWritable.class); job2.setOutputValueClass(Text.class); job2.setSortComparatorClass(IntWritableDecreasingComparator.class); job2.setInputFormatClass(TextInputFormat.class); job2.setOutputFormatClass(TextOutputFormat.class); Path in2=new Path("hdfs://localhost:9000/test/stage1/out1/part-r-00000"); Path out2=new Path("hdfs://localhost:9000/test/stage1/out2"); FileInputFormat.addInputPath(job2,in2); FileOutputFormat.setOutputPath(job2,out2); System.exit(job2.waitForCompletion(true) ? 0 : 1);}}public static class doMapper extends Mapper<Object,Text,Text,IntWritable>{public static final IntWritable one = new IntWritable(1);public static Text word = new Text();@Overrideprotected void map(Object key, Text value, Context context)throws IOException,InterruptedException {//StringTokenizer tokenizer = new StringTokenizer(value.toString()," "); String[] strNlist = value.toString().split(","); String str=strNlist[3].trim(); String str2=strNlist[4]+strNlist[5]; Integer temp= Integer.valueOf(str);word.set(str2);IntWritable abc = new IntWritable(temp);context.write(word,abc);}}public static class doReducer extends Reducer<Text,IntWritable,Text,IntWritable>{private IntWritable result = new IntWritable();@Overrideprotected void reduce(Text key,Iterable<IntWritable> values,Context context)throws IOException,InterruptedException{int sum = 0;for (IntWritable value : values){sum += value.get();}result.set(sum);context.write(key,result);}}/////////////public static class doMapper2 extends Mapper<Object , Text , IntWritable,Text>{private static Text goods=new Text(); private static IntWritable num=new IntWritable(); @Overrideprotected void map(Object key, Text value, Context context)throws IOException,InterruptedException { String line=value.toString(); String arr[]=line.split(" "); num.set(Integer.parseInt(arr[1])); goods.set(arr[0]); context.write(num,goods);}}public static class doReduce2 extends Reducer< IntWritable, Text, IntWritable, Text>{ private static IntWritable result= new IntWritable(); int i=0; public void reduce(IntWritable key,Iterable<Text> values,Context context) throws IOException, InterruptedException{ for(Text val:values){ if(i<10) { context.write(key,val); i++; } } } } private static class IntWritableDecreasingComparator extends IntWritable.Comparator { public int compare(WritableComparable a, WritableComparable b) { return -super.compare(a, b); } public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) { return -super.compare(b1, s1, l1, b2, s2, l2); }}} |
（去重、显示流量总量）
（排序，输出Top10）
总结：
本来我是通过两个类来实现的，后来我发现在一个类中可以进行多个job，我就定义两个job,job1进行去重，输出总数。job2进行排序，输出Top10。
在for(Intwritable val:values)遍历时，根据主键升序遍历，但我们需要的结果是降序，那么在这里我们需要引入一个比较器。
