forked from xldrx/cloudapp-mp2
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathTopTitleStatistics.java
301 lines (243 loc) · 10.2 KB
/
TopTitleStatistics.java
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
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.ArrayWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.lang.Integer;
import java.util.Arrays;
import java.util.List;
import java.util.StringTokenizer;
import java.util.TreeSet;
// Don't Change >>>
public class TopTitleStatistics extends Configured implements Tool {
public static void main(String[] args) throws Exception {
int res = ToolRunner.run(new Configuration(), new TopTitleStatistics(), args);
System.exit(res);
}
@Override
public int run(String[] args) throws Exception {
Configuration conf = this.getConf();
FileSystem fs = FileSystem.get(conf);
Path tmpPath = new Path("/mp2/tmp");
fs.delete(tmpPath, true);
Job jobA = Job.getInstance(conf, "Title Count");
jobA.setOutputKeyClass(Text.class);
jobA.setOutputValueClass(IntWritable.class);
jobA.setMapperClass(TitleCountMap.class);
jobA.setReducerClass(TitleCountReduce.class);
FileInputFormat.setInputPaths(jobA, new Path(args[0]));
FileOutputFormat.setOutputPath(jobA, tmpPath);
jobA.setJarByClass(TopTitleStatistics.class);
jobA.waitForCompletion(true);
Job jobB = Job.getInstance(conf, "Top Titles Statistics");
jobB.setOutputKeyClass(Text.class);
jobB.setOutputValueClass(IntWritable.class);
jobB.setMapOutputKeyClass(NullWritable.class);
jobB.setMapOutputValueClass(TextArrayWritable.class);
jobB.setMapperClass(TopTitlesStatMap.class);
jobB.setReducerClass(TopTitlesStatReduce.class);
jobB.setNumReduceTasks(1);
FileInputFormat.setInputPaths(jobB, tmpPath);
FileOutputFormat.setOutputPath(jobB, new Path(args[1]));
jobB.setInputFormatClass(KeyValueTextInputFormat.class);
jobB.setOutputFormatClass(TextOutputFormat.class);
jobB.setJarByClass(TopTitleStatistics.class);
return jobB.waitForCompletion(true) ? 0 : 1;
}
public static String readHDFSFile(String path, Configuration conf) throws IOException{
Path pt=new Path(path);
FileSystem fs = FileSystem.get(pt.toUri(), conf);
FSDataInputStream file = fs.open(pt);
BufferedReader buffIn=new BufferedReader(new InputStreamReader(file));
StringBuilder everything = new StringBuilder();
String line;
while( (line = buffIn.readLine()) != null) {
everything.append(line);
everything.append("\n");
}
return everything.toString();
}
public static class TextArrayWritable extends ArrayWritable {
public TextArrayWritable() {
super(Text.class);
}
public TextArrayWritable(String[] strings) {
super(Text.class);
Text[] texts = new Text[strings.length];
for (int i = 0; i < strings.length; i++) {
texts[i] = new Text(strings[i]);
}
set(texts);
}
}
// <<< Don't Change
public static class TitleCountMap extends Mapper<Object, Text, Text, IntWritable> {
List<String> stopWords;
String delimiters;
@Override
protected void setup(Context context) throws IOException,InterruptedException {
Configuration conf = context.getConfiguration();
String stopWordsPath = conf.get("stopwords");
String delimitersPath = conf.get("delimiters");
this.stopWords = Arrays.asList(readHDFSFile(stopWordsPath, conf).split("\n"));
this.delimiters = readHDFSFile(delimitersPath, conf);
}
@Override
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
final String line = value.toString();
final StringTokenizer tokenizer = new StringTokenizer(line, delimiters);
while (tokenizer.hasMoreTokens()) {
final String nextToken = tokenizer.nextToken().trim().toLowerCase();
if ( !stopWords.contains(nextToken) ) {
context.write(new Text(nextToken), new IntWritable(1));
}
}
}
}
public static class TitleCountReduce extends Reducer<Text, IntWritable, Text, IntWritable> {
@Override
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
context.write(key, new IntWritable(sum));
}
}
public static class TopTitlesStatMap extends Mapper<Text, Text, NullWritable, TextArrayWritable> {
Integer N;
TreeSet<Pair<Integer, String>> countToWordMap = new TreeSet<Pair<Integer, String>>();
@Override
protected void setup(Context context) throws IOException,InterruptedException {
Configuration conf = context.getConfiguration();
this.N = conf.getInt("N", 10);
}
@Override
public void map(Text key, Text value, Context context) throws IOException, InterruptedException {
Integer count = Integer.parseInt(value.toString());
String word = key.toString();
countToWordMap.add(new Pair<Integer, String>(count, word));
if (countToWordMap.size() > N) {
countToWordMap.remove(countToWordMap.first());
}
}
@Override
protected void cleanup(Context context) throws IOException, InterruptedException {
for (Pair<Integer, String> item : countToWordMap) {
String[] strings = { item.second, item.first.toString() };
TextArrayWritable val = new TextArrayWritable(strings);
context.write(NullWritable.get(), val);
}
}
}
public static class TopTitlesStatReduce extends Reducer<NullWritable, TextArrayWritable, Text, IntWritable> {
Integer N;
TreeSet<Pair<Integer, String>> countToWordMap = new TreeSet<Pair<Integer, String>>();
@Override
protected void setup(Context context) throws IOException,InterruptedException {
Configuration conf = context.getConfiguration();
this.N = conf.getInt("N", 10);
}
@Override
public void reduce(NullWritable key, Iterable<TextArrayWritable> values, Context context) throws IOException, InterruptedException {
Integer sum = 0;
Integer mean = 0;
Integer max = null;
Integer min = null;
Integer var = 0;
for (TextArrayWritable val: values) {
Text[] pair= (Text[]) val.toArray();
String word = pair[0].toString();
Integer count = Integer.parseInt(pair[1].toString());
countToWordMap.add(new Pair<Integer, String>(count, word));
if (countToWordMap.size() > N) {
countToWordMap.remove(countToWordMap.first());
}
}
int count = 0;
for (Pair<Integer, String> item: countToWordMap) {
Integer v = item.first;
sum = sum + v;
++count; // for mean
max = (null == max || v > max) ? v : max;
min = (null == min || v < min) ? v : min;
}
mean = sum / count;
// variance
for (Pair<Integer, String> item: countToWordMap) {
Integer v = item.first;
Integer varItem = v - mean;
var = var + varItem*varItem;
}
var = var / count;
context.write(new Text("Mean"), new IntWritable(mean));
context.write(new Text("Sum"), new IntWritable(sum));
context.write(new Text("Min"), new IntWritable(min));
context.write(new Text("Max"), new IntWritable(max));
context.write(new Text("Var"), new IntWritable(var));
}
}
}
// >>> Don't Change
class Pair<A extends Comparable<? super A>,
B extends Comparable<? super B>>
implements Comparable<Pair<A, B>> {
public final A first;
public final B second;
public Pair(A first, B second) {
this.first = first;
this.second = second;
}
public static <A extends Comparable<? super A>,
B extends Comparable<? super B>>
Pair<A, B> of(A first, B second) {
return new Pair<A, B>(first, second);
}
@Override
public int compareTo(Pair<A, B> o) {
int cmp = o == null ? 1 : (this.first).compareTo(o.first);
return cmp == 0 ? (this.second).compareTo(o.second) : cmp;
}
@Override
public int hashCode() {
return 31 * hashcode(first) + hashcode(second);
}
private static int hashcode(Object o) {
return o == null ? 0 : o.hashCode();
}
@Override
public boolean equals(Object obj) {
if (!(obj instanceof Pair))
return false;
if (this == obj)
return true;
return equal(first, ((Pair<?, ?>) obj).first)
&& equal(second, ((Pair<?, ?>) obj).second);
}
private boolean equal(Object o1, Object o2) {
return o1 == o2 || (o1 != null && o1.equals(o2));
}
@Override
public String toString() {
return "(" + first + ", " + second + ')';
}
}
// <<< Don't Change