<HTML>
<BODY BGCOLOR="white">
<PRE>
<FONT color="green">001</FONT>    /**<a name="line.1"></a>
<FONT color="green">002</FONT>     * Licensed to the Apache Software Foundation (ASF) under one<a name="line.2"></a>
<FONT color="green">003</FONT>     * or more contributor license agreements.  See the NOTICE file<a name="line.3"></a>
<FONT color="green">004</FONT>     * distributed with this work for additional information<a name="line.4"></a>
<FONT color="green">005</FONT>     * regarding copyright ownership.  The ASF licenses this file<a name="line.5"></a>
<FONT color="green">006</FONT>     * to you under the Apache License, Version 2.0 (the<a name="line.6"></a>
<FONT color="green">007</FONT>     * "License"); you may not use this file except in compliance<a name="line.7"></a>
<FONT color="green">008</FONT>     * with the License.  You may obtain a copy of the License at<a name="line.8"></a>
<FONT color="green">009</FONT>     *<a name="line.9"></a>
<FONT color="green">010</FONT>     *     http://www.apache.org/licenses/LICENSE-2.0<a name="line.10"></a>
<FONT color="green">011</FONT>     *<a name="line.11"></a>
<FONT color="green">012</FONT>     * Unless required by applicable law or agreed to in writing, software<a name="line.12"></a>
<FONT color="green">013</FONT>     * distributed under the License is distributed on an "AS IS" BASIS,<a name="line.13"></a>
<FONT color="green">014</FONT>     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.<a name="line.14"></a>
<FONT color="green">015</FONT>     * See the License for the specific language governing permissions and<a name="line.15"></a>
<FONT color="green">016</FONT>     * limitations under the License.<a name="line.16"></a>
<FONT color="green">017</FONT>     */<a name="line.17"></a>
<FONT color="green">018</FONT>    <a name="line.18"></a>
<FONT color="green">019</FONT>    package org.apache.hadoop.mapreduce.lib.partition;<a name="line.19"></a>
<FONT color="green">020</FONT>    <a name="line.20"></a>
<FONT color="green">021</FONT>    import java.io.IOException;<a name="line.21"></a>
<FONT color="green">022</FONT>    import java.util.ArrayList;<a name="line.22"></a>
<FONT color="green">023</FONT>    import java.util.Arrays;<a name="line.23"></a>
<FONT color="green">024</FONT>    import java.util.List;<a name="line.24"></a>
<FONT color="green">025</FONT>    import java.util.Random;<a name="line.25"></a>
<FONT color="green">026</FONT>    <a name="line.26"></a>
<FONT color="green">027</FONT>    import org.apache.commons.logging.Log;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.commons.logging.LogFactory;<a name="line.28"></a>
<FONT color="green">029</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.29"></a>
<FONT color="green">030</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.30"></a>
<FONT color="green">031</FONT>    import org.apache.hadoop.conf.Configuration;<a name="line.31"></a>
<FONT color="green">032</FONT>    import org.apache.hadoop.conf.Configured;<a name="line.32"></a>
<FONT color="green">033</FONT>    import org.apache.hadoop.fs.FileSystem;<a name="line.33"></a>
<FONT color="green">034</FONT>    import org.apache.hadoop.fs.Path;<a name="line.34"></a>
<FONT color="green">035</FONT>    import org.apache.hadoop.io.NullWritable;<a name="line.35"></a>
<FONT color="green">036</FONT>    import org.apache.hadoop.io.RawComparator;<a name="line.36"></a>
<FONT color="green">037</FONT>    import org.apache.hadoop.io.SequenceFile;<a name="line.37"></a>
<FONT color="green">038</FONT>    import org.apache.hadoop.io.WritableComparable;<a name="line.38"></a>
<FONT color="green">039</FONT>    import org.apache.hadoop.mapreduce.InputFormat;<a name="line.39"></a>
<FONT color="green">040</FONT>    import org.apache.hadoop.mapreduce.InputSplit;<a name="line.40"></a>
<FONT color="green">041</FONT>    import org.apache.hadoop.mapreduce.Job;<a name="line.41"></a>
<FONT color="green">042</FONT>    import org.apache.hadoop.mapreduce.RecordReader;<a name="line.42"></a>
<FONT color="green">043</FONT>    import org.apache.hadoop.mapreduce.TaskAttemptContext;<a name="line.43"></a>
<FONT color="green">044</FONT>    import org.apache.hadoop.mapreduce.TaskAttemptID;<a name="line.44"></a>
<FONT color="green">045</FONT>    import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;<a name="line.45"></a>
<FONT color="green">046</FONT>    import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl;<a name="line.46"></a>
<FONT color="green">047</FONT>    import org.apache.hadoop.util.ReflectionUtils;<a name="line.47"></a>
<FONT color="green">048</FONT>    import org.apache.hadoop.util.Tool;<a name="line.48"></a>
<FONT color="green">049</FONT>    import org.apache.hadoop.util.ToolRunner;<a name="line.49"></a>
<FONT color="green">050</FONT>    <a name="line.50"></a>
<FONT color="green">051</FONT>    /**<a name="line.51"></a>
<FONT color="green">052</FONT>     * Utility for collecting samples and writing a partition file for<a name="line.52"></a>
<FONT color="green">053</FONT>     * {@link TotalOrderPartitioner}.<a name="line.53"></a>
<FONT color="green">054</FONT>     */<a name="line.54"></a>
<FONT color="green">055</FONT>    @InterfaceAudience.Public<a name="line.55"></a>
<FONT color="green">056</FONT>    @InterfaceStability.Stable<a name="line.56"></a>
<FONT color="green">057</FONT>    public class InputSampler&lt;K,V&gt; extends Configured implements Tool  {<a name="line.57"></a>
<FONT color="green">058</FONT>    <a name="line.58"></a>
<FONT color="green">059</FONT>      private static final Log LOG = LogFactory.getLog(InputSampler.class);<a name="line.59"></a>
<FONT color="green">060</FONT>    <a name="line.60"></a>
<FONT color="green">061</FONT>      static int printUsage() {<a name="line.61"></a>
<FONT color="green">062</FONT>        System.out.println("sampler -r &lt;reduces&gt;\n" +<a name="line.62"></a>
<FONT color="green">063</FONT>          "      [-inFormat &lt;input format class&gt;]\n" +<a name="line.63"></a>
<FONT color="green">064</FONT>          "      [-keyClass &lt;map input &amp; output key class&gt;]\n" +<a name="line.64"></a>
<FONT color="green">065</FONT>          "      [-splitRandom &lt;double pcnt&gt; &lt;numSamples&gt; &lt;maxsplits&gt; | " +<a name="line.65"></a>
<FONT color="green">066</FONT>          "             // Sample from random splits at random (general)\n" +<a name="line.66"></a>
<FONT color="green">067</FONT>          "       -splitSample &lt;numSamples&gt; &lt;maxsplits&gt; | " +<a name="line.67"></a>
<FONT color="green">068</FONT>          "             // Sample from first records in splits (random data)\n"+<a name="line.68"></a>
<FONT color="green">069</FONT>          "       -splitInterval &lt;double pcnt&gt; &lt;maxsplits&gt;]" +<a name="line.69"></a>
<FONT color="green">070</FONT>          "             // Sample from splits at intervals (sorted data)");<a name="line.70"></a>
<FONT color="green">071</FONT>        System.out.println("Default sampler: -splitRandom 0.1 10000 10");<a name="line.71"></a>
<FONT color="green">072</FONT>        ToolRunner.printGenericCommandUsage(System.out);<a name="line.72"></a>
<FONT color="green">073</FONT>        return -1;<a name="line.73"></a>
<FONT color="green">074</FONT>      }<a name="line.74"></a>
<FONT color="green">075</FONT>    <a name="line.75"></a>
<FONT color="green">076</FONT>      public InputSampler(Configuration conf) {<a name="line.76"></a>
<FONT color="green">077</FONT>        setConf(conf);<a name="line.77"></a>
<FONT color="green">078</FONT>      }<a name="line.78"></a>
<FONT color="green">079</FONT>    <a name="line.79"></a>
<FONT color="green">080</FONT>      /**<a name="line.80"></a>
<FONT color="green">081</FONT>       * Interface to sample using an <a name="line.81"></a>
<FONT color="green">082</FONT>       * {@link org.apache.hadoop.mapreduce.InputFormat}.<a name="line.82"></a>
<FONT color="green">083</FONT>       */<a name="line.83"></a>
<FONT color="green">084</FONT>      public interface Sampler&lt;K,V&gt; {<a name="line.84"></a>
<FONT color="green">085</FONT>        /**<a name="line.85"></a>
<FONT color="green">086</FONT>         * For a given job, collect and return a subset of the keys from the<a name="line.86"></a>
<FONT color="green">087</FONT>         * input data.<a name="line.87"></a>
<FONT color="green">088</FONT>         */<a name="line.88"></a>
<FONT color="green">089</FONT>        K[] getSample(InputFormat&lt;K,V&gt; inf, Job job) <a name="line.89"></a>
<FONT color="green">090</FONT>        throws IOException, InterruptedException;<a name="line.90"></a>
<FONT color="green">091</FONT>      }<a name="line.91"></a>
<FONT color="green">092</FONT>    <a name="line.92"></a>
<FONT color="green">093</FONT>      /**<a name="line.93"></a>
<FONT color="green">094</FONT>       * Samples the first n records from s splits.<a name="line.94"></a>
<FONT color="green">095</FONT>       * Inexpensive way to sample random data.<a name="line.95"></a>
<FONT color="green">096</FONT>       */<a name="line.96"></a>
<FONT color="green">097</FONT>      public static class SplitSampler&lt;K,V&gt; implements Sampler&lt;K,V&gt; {<a name="line.97"></a>
<FONT color="green">098</FONT>    <a name="line.98"></a>
<FONT color="green">099</FONT>        private final int numSamples;<a name="line.99"></a>
<FONT color="green">100</FONT>        private final int maxSplitsSampled;<a name="line.100"></a>
<FONT color="green">101</FONT>    <a name="line.101"></a>
<FONT color="green">102</FONT>        /**<a name="line.102"></a>
<FONT color="green">103</FONT>         * Create a SplitSampler sampling &lt;em&gt;all&lt;/em&gt; splits.<a name="line.103"></a>
<FONT color="green">104</FONT>         * Takes the first numSamples / numSplits records from each split.<a name="line.104"></a>
<FONT color="green">105</FONT>         * @param numSamples Total number of samples to obtain from all selected<a name="line.105"></a>
<FONT color="green">106</FONT>         *                   splits.<a name="line.106"></a>
<FONT color="green">107</FONT>         */<a name="line.107"></a>
<FONT color="green">108</FONT>        public SplitSampler(int numSamples) {<a name="line.108"></a>
<FONT color="green">109</FONT>          this(numSamples, Integer.MAX_VALUE);<a name="line.109"></a>
<FONT color="green">110</FONT>        }<a name="line.110"></a>
<FONT color="green">111</FONT>    <a name="line.111"></a>
<FONT color="green">112</FONT>        /**<a name="line.112"></a>
<FONT color="green">113</FONT>         * Create a new SplitSampler.<a name="line.113"></a>
<FONT color="green">114</FONT>         * @param numSamples Total number of samples to obtain from all selected<a name="line.114"></a>
<FONT color="green">115</FONT>         *                   splits.<a name="line.115"></a>
<FONT color="green">116</FONT>         * @param maxSplitsSampled The maximum number of splits to examine.<a name="line.116"></a>
<FONT color="green">117</FONT>         */<a name="line.117"></a>
<FONT color="green">118</FONT>        public SplitSampler(int numSamples, int maxSplitsSampled) {<a name="line.118"></a>
<FONT color="green">119</FONT>          this.numSamples = numSamples;<a name="line.119"></a>
<FONT color="green">120</FONT>          this.maxSplitsSampled = maxSplitsSampled;<a name="line.120"></a>
<FONT color="green">121</FONT>        }<a name="line.121"></a>
<FONT color="green">122</FONT>    <a name="line.122"></a>
<FONT color="green">123</FONT>        /**<a name="line.123"></a>
<FONT color="green">124</FONT>         * From each split sampled, take the first numSamples / numSplits records.<a name="line.124"></a>
<FONT color="green">125</FONT>         */<a name="line.125"></a>
<FONT color="green">126</FONT>        @SuppressWarnings("unchecked") // ArrayList::toArray doesn't preserve type<a name="line.126"></a>
<FONT color="green">127</FONT>        public K[] getSample(InputFormat&lt;K,V&gt; inf, Job job) <a name="line.127"></a>
<FONT color="green">128</FONT>            throws IOException, InterruptedException {<a name="line.128"></a>
<FONT color="green">129</FONT>          List&lt;InputSplit&gt; splits = inf.getSplits(job);<a name="line.129"></a>
<FONT color="green">130</FONT>          ArrayList&lt;K&gt; samples = new ArrayList&lt;K&gt;(numSamples);<a name="line.130"></a>
<FONT color="green">131</FONT>          int splitsToSample = Math.min(maxSplitsSampled, splits.size());<a name="line.131"></a>
<FONT color="green">132</FONT>          int samplesPerSplit = numSamples / splitsToSample;<a name="line.132"></a>
<FONT color="green">133</FONT>          long records = 0;<a name="line.133"></a>
<FONT color="green">134</FONT>          for (int i = 0; i &lt; splitsToSample; ++i) {<a name="line.134"></a>
<FONT color="green">135</FONT>            TaskAttemptContext samplingContext = new TaskAttemptContextImpl(<a name="line.135"></a>
<FONT color="green">136</FONT>                job.getConfiguration(), new TaskAttemptID());<a name="line.136"></a>
<FONT color="green">137</FONT>            RecordReader&lt;K,V&gt; reader = inf.createRecordReader(<a name="line.137"></a>
<FONT color="green">138</FONT>                splits.get(i), samplingContext);<a name="line.138"></a>
<FONT color="green">139</FONT>            reader.initialize(splits.get(i), samplingContext);<a name="line.139"></a>
<FONT color="green">140</FONT>            while (reader.nextKeyValue()) {<a name="line.140"></a>
<FONT color="green">141</FONT>              samples.add(ReflectionUtils.copy(job.getConfiguration(),<a name="line.141"></a>
<FONT color="green">142</FONT>                                               reader.getCurrentKey(), null));<a name="line.142"></a>
<FONT color="green">143</FONT>              ++records;<a name="line.143"></a>
<FONT color="green">144</FONT>              if ((i+1) * samplesPerSplit &lt;= records) {<a name="line.144"></a>
<FONT color="green">145</FONT>                break;<a name="line.145"></a>
<FONT color="green">146</FONT>              }<a name="line.146"></a>
<FONT color="green">147</FONT>            }<a name="line.147"></a>
<FONT color="green">148</FONT>            reader.close();<a name="line.148"></a>
<FONT color="green">149</FONT>          }<a name="line.149"></a>
<FONT color="green">150</FONT>          return (K[])samples.toArray();<a name="line.150"></a>
<FONT color="green">151</FONT>        }<a name="line.151"></a>
<FONT color="green">152</FONT>      }<a name="line.152"></a>
<FONT color="green">153</FONT>    <a name="line.153"></a>
<FONT color="green">154</FONT>      /**<a name="line.154"></a>
<FONT color="green">155</FONT>       * Sample from random points in the input.<a name="line.155"></a>
<FONT color="green">156</FONT>       * General-purpose sampler. Takes numSamples / maxSplitsSampled inputs from<a name="line.156"></a>
<FONT color="green">157</FONT>       * each split.<a name="line.157"></a>
<FONT color="green">158</FONT>       */<a name="line.158"></a>
<FONT color="green">159</FONT>      public static class RandomSampler&lt;K,V&gt; implements Sampler&lt;K,V&gt; {<a name="line.159"></a>
<FONT color="green">160</FONT>        private double freq;<a name="line.160"></a>
<FONT color="green">161</FONT>        private final int numSamples;<a name="line.161"></a>
<FONT color="green">162</FONT>        private final int maxSplitsSampled;<a name="line.162"></a>
<FONT color="green">163</FONT>    <a name="line.163"></a>
<FONT color="green">164</FONT>        /**<a name="line.164"></a>
<FONT color="green">165</FONT>         * Create a new RandomSampler sampling &lt;em&gt;all&lt;/em&gt; splits.<a name="line.165"></a>
<FONT color="green">166</FONT>         * This will read every split at the client, which is very expensive.<a name="line.166"></a>
<FONT color="green">167</FONT>         * @param freq Probability with which a key will be chosen.<a name="line.167"></a>
<FONT color="green">168</FONT>         * @param numSamples Total number of samples to obtain from all selected<a name="line.168"></a>
<FONT color="green">169</FONT>         *                   splits.<a name="line.169"></a>
<FONT color="green">170</FONT>         */<a name="line.170"></a>
<FONT color="green">171</FONT>        public RandomSampler(double freq, int numSamples) {<a name="line.171"></a>
<FONT color="green">172</FONT>          this(freq, numSamples, Integer.MAX_VALUE);<a name="line.172"></a>
<FONT color="green">173</FONT>        }<a name="line.173"></a>
<FONT color="green">174</FONT>    <a name="line.174"></a>
<FONT color="green">175</FONT>        /**<a name="line.175"></a>
<FONT color="green">176</FONT>         * Create a new RandomSampler.<a name="line.176"></a>
<FONT color="green">177</FONT>         * @param freq Probability with which a key will be chosen.<a name="line.177"></a>
<FONT color="green">178</FONT>         * @param numSamples Total number of samples to obtain from all selected<a name="line.178"></a>
<FONT color="green">179</FONT>         *                   splits.<a name="line.179"></a>
<FONT color="green">180</FONT>         * @param maxSplitsSampled The maximum number of splits to examine.<a name="line.180"></a>
<FONT color="green">181</FONT>         */<a name="line.181"></a>
<FONT color="green">182</FONT>        public RandomSampler(double freq, int numSamples, int maxSplitsSampled) {<a name="line.182"></a>
<FONT color="green">183</FONT>          this.freq = freq;<a name="line.183"></a>
<FONT color="green">184</FONT>          this.numSamples = numSamples;<a name="line.184"></a>
<FONT color="green">185</FONT>          this.maxSplitsSampled = maxSplitsSampled;<a name="line.185"></a>
<FONT color="green">186</FONT>        }<a name="line.186"></a>
<FONT color="green">187</FONT>    <a name="line.187"></a>
<FONT color="green">188</FONT>        /**<a name="line.188"></a>
<FONT color="green">189</FONT>         * Randomize the split order, then take the specified number of keys from<a name="line.189"></a>
<FONT color="green">190</FONT>         * each split sampled, where each key is selected with the specified<a name="line.190"></a>
<FONT color="green">191</FONT>         * probability and possibly replaced by a subsequently selected key when<a name="line.191"></a>
<FONT color="green">192</FONT>         * the quota of keys from that split is satisfied.<a name="line.192"></a>
<FONT color="green">193</FONT>         */<a name="line.193"></a>
<FONT color="green">194</FONT>        @SuppressWarnings("unchecked") // ArrayList::toArray doesn't preserve type<a name="line.194"></a>
<FONT color="green">195</FONT>        public K[] getSample(InputFormat&lt;K,V&gt; inf, Job job) <a name="line.195"></a>
<FONT color="green">196</FONT>            throws IOException, InterruptedException {<a name="line.196"></a>
<FONT color="green">197</FONT>          List&lt;InputSplit&gt; splits = inf.getSplits(job);<a name="line.197"></a>
<FONT color="green">198</FONT>          ArrayList&lt;K&gt; samples = new ArrayList&lt;K&gt;(numSamples);<a name="line.198"></a>
<FONT color="green">199</FONT>          int splitsToSample = Math.min(maxSplitsSampled, splits.size());<a name="line.199"></a>
<FONT color="green">200</FONT>    <a name="line.200"></a>
<FONT color="green">201</FONT>          Random r = new Random();<a name="line.201"></a>
<FONT color="green">202</FONT>          long seed = r.nextLong();<a name="line.202"></a>
<FONT color="green">203</FONT>          r.setSeed(seed);<a name="line.203"></a>
<FONT color="green">204</FONT>          LOG.debug("seed: " + seed);<a name="line.204"></a>
<FONT color="green">205</FONT>          // shuffle splits<a name="line.205"></a>
<FONT color="green">206</FONT>          for (int i = 0; i &lt; splits.size(); ++i) {<a name="line.206"></a>
<FONT color="green">207</FONT>            InputSplit tmp = splits.get(i);<a name="line.207"></a>
<FONT color="green">208</FONT>            int j = r.nextInt(splits.size());<a name="line.208"></a>
<FONT color="green">209</FONT>            splits.set(i, splits.get(j));<a name="line.209"></a>
<FONT color="green">210</FONT>            splits.set(j, tmp);<a name="line.210"></a>
<FONT color="green">211</FONT>          }<a name="line.211"></a>
<FONT color="green">212</FONT>          // our target rate is in terms of the maximum number of sample splits,<a name="line.212"></a>
<FONT color="green">213</FONT>          // but we accept the possibility of sampling additional splits to hit<a name="line.213"></a>
<FONT color="green">214</FONT>          // the target sample keyset<a name="line.214"></a>
<FONT color="green">215</FONT>          for (int i = 0; i &lt; splitsToSample ||<a name="line.215"></a>
<FONT color="green">216</FONT>                         (i &lt; splits.size() &amp;&amp; samples.size() &lt; numSamples); ++i) {<a name="line.216"></a>
<FONT color="green">217</FONT>            TaskAttemptContext samplingContext = new TaskAttemptContextImpl(<a name="line.217"></a>
<FONT color="green">218</FONT>                job.getConfiguration(), new TaskAttemptID());<a name="line.218"></a>
<FONT color="green">219</FONT>            RecordReader&lt;K,V&gt; reader = inf.createRecordReader(<a name="line.219"></a>
<FONT color="green">220</FONT>                splits.get(i), samplingContext);<a name="line.220"></a>
<FONT color="green">221</FONT>            reader.initialize(splits.get(i), samplingContext);<a name="line.221"></a>
<FONT color="green">222</FONT>            while (reader.nextKeyValue()) {<a name="line.222"></a>
<FONT color="green">223</FONT>              if (r.nextDouble() &lt;= freq) {<a name="line.223"></a>
<FONT color="green">224</FONT>                if (samples.size() &lt; numSamples) {<a name="line.224"></a>
<FONT color="green">225</FONT>                  samples.add(ReflectionUtils.copy(job.getConfiguration(),<a name="line.225"></a>
<FONT color="green">226</FONT>                                                   reader.getCurrentKey(), null));<a name="line.226"></a>
<FONT color="green">227</FONT>                } else {<a name="line.227"></a>
<FONT color="green">228</FONT>                  // When exceeding the maximum number of samples, replace a<a name="line.228"></a>
<FONT color="green">229</FONT>                  // random element with this one, then adjust the frequency<a name="line.229"></a>
<FONT color="green">230</FONT>                  // to reflect the possibility of existing elements being<a name="line.230"></a>
<FONT color="green">231</FONT>                  // pushed out<a name="line.231"></a>
<FONT color="green">232</FONT>                  int ind = r.nextInt(numSamples);<a name="line.232"></a>
<FONT color="green">233</FONT>                  if (ind != numSamples) {<a name="line.233"></a>
<FONT color="green">234</FONT>                    samples.set(ind, ReflectionUtils.copy(job.getConfiguration(),<a name="line.234"></a>
<FONT color="green">235</FONT>                                     reader.getCurrentKey(), null));<a name="line.235"></a>
<FONT color="green">236</FONT>                  }<a name="line.236"></a>
<FONT color="green">237</FONT>                  freq *= (numSamples - 1) / (double) numSamples;<a name="line.237"></a>
<FONT color="green">238</FONT>                }<a name="line.238"></a>
<FONT color="green">239</FONT>              }<a name="line.239"></a>
<FONT color="green">240</FONT>            }<a name="line.240"></a>
<FONT color="green">241</FONT>            reader.close();<a name="line.241"></a>
<FONT color="green">242</FONT>          }<a name="line.242"></a>
<FONT color="green">243</FONT>          return (K[])samples.toArray();<a name="line.243"></a>
<FONT color="green">244</FONT>        }<a name="line.244"></a>
<FONT color="green">245</FONT>      }<a name="line.245"></a>
<FONT color="green">246</FONT>    <a name="line.246"></a>
<FONT color="green">247</FONT>      /**<a name="line.247"></a>
<FONT color="green">248</FONT>       * Sample from s splits at regular intervals.<a name="line.248"></a>
<FONT color="green">249</FONT>       * Useful for sorted data.<a name="line.249"></a>
<FONT color="green">250</FONT>       */<a name="line.250"></a>
<FONT color="green">251</FONT>      public static class IntervalSampler&lt;K,V&gt; implements Sampler&lt;K,V&gt; {<a name="line.251"></a>
<FONT color="green">252</FONT>        private final double freq;<a name="line.252"></a>
<FONT color="green">253</FONT>        private final int maxSplitsSampled;<a name="line.253"></a>
<FONT color="green">254</FONT>    <a name="line.254"></a>
<FONT color="green">255</FONT>        /**<a name="line.255"></a>
<FONT color="green">256</FONT>         * Create a new IntervalSampler sampling &lt;em&gt;all&lt;/em&gt; splits.<a name="line.256"></a>
<FONT color="green">257</FONT>         * @param freq The frequency with which records will be emitted.<a name="line.257"></a>
<FONT color="green">258</FONT>         */<a name="line.258"></a>
<FONT color="green">259</FONT>        public IntervalSampler(double freq) {<a name="line.259"></a>
<FONT color="green">260</FONT>          this(freq, Integer.MAX_VALUE);<a name="line.260"></a>
<FONT color="green">261</FONT>        }<a name="line.261"></a>
<FONT color="green">262</FONT>    <a name="line.262"></a>
<FONT color="green">263</FONT>        /**<a name="line.263"></a>
<FONT color="green">264</FONT>         * Create a new IntervalSampler.<a name="line.264"></a>
<FONT color="green">265</FONT>         * @param freq The frequency with which records will be emitted.<a name="line.265"></a>
<FONT color="green">266</FONT>         * @param maxSplitsSampled The maximum number of splits to examine.<a name="line.266"></a>
<FONT color="green">267</FONT>         * @see #getSample<a name="line.267"></a>
<FONT color="green">268</FONT>         */<a name="line.268"></a>
<FONT color="green">269</FONT>        public IntervalSampler(double freq, int maxSplitsSampled) {<a name="line.269"></a>
<FONT color="green">270</FONT>          this.freq = freq;<a name="line.270"></a>
<FONT color="green">271</FONT>          this.maxSplitsSampled = maxSplitsSampled;<a name="line.271"></a>
<FONT color="green">272</FONT>        }<a name="line.272"></a>
<FONT color="green">273</FONT>    <a name="line.273"></a>
<FONT color="green">274</FONT>        /**<a name="line.274"></a>
<FONT color="green">275</FONT>         * For each split sampled, emit when the ratio of the number of records<a name="line.275"></a>
<FONT color="green">276</FONT>         * retained to the total record count is less than the specified<a name="line.276"></a>
<FONT color="green">277</FONT>         * frequency.<a name="line.277"></a>
<FONT color="green">278</FONT>         */<a name="line.278"></a>
<FONT color="green">279</FONT>        @SuppressWarnings("unchecked") // ArrayList::toArray doesn't preserve type<a name="line.279"></a>
<FONT color="green">280</FONT>        public K[] getSample(InputFormat&lt;K,V&gt; inf, Job job) <a name="line.280"></a>
<FONT color="green">281</FONT>            throws IOException, InterruptedException {<a name="line.281"></a>
<FONT color="green">282</FONT>          List&lt;InputSplit&gt; splits = inf.getSplits(job);<a name="line.282"></a>
<FONT color="green">283</FONT>          ArrayList&lt;K&gt; samples = new ArrayList&lt;K&gt;();<a name="line.283"></a>
<FONT color="green">284</FONT>          int splitsToSample = Math.min(maxSplitsSampled, splits.size());<a name="line.284"></a>
<FONT color="green">285</FONT>          long records = 0;<a name="line.285"></a>
<FONT color="green">286</FONT>          long kept = 0;<a name="line.286"></a>
<FONT color="green">287</FONT>          for (int i = 0; i &lt; splitsToSample; ++i) {<a name="line.287"></a>
<FONT color="green">288</FONT>            TaskAttemptContext samplingContext = new TaskAttemptContextImpl(<a name="line.288"></a>
<FONT color="green">289</FONT>                job.getConfiguration(), new TaskAttemptID());<a name="line.289"></a>
<FONT color="green">290</FONT>            RecordReader&lt;K,V&gt; reader = inf.createRecordReader(<a name="line.290"></a>
<FONT color="green">291</FONT>                splits.get(i), samplingContext);<a name="line.291"></a>
<FONT color="green">292</FONT>            reader.initialize(splits.get(i), samplingContext);<a name="line.292"></a>
<FONT color="green">293</FONT>            while (reader.nextKeyValue()) {<a name="line.293"></a>
<FONT color="green">294</FONT>              ++records;<a name="line.294"></a>
<FONT color="green">295</FONT>              if ((double) kept / records &lt; freq) {<a name="line.295"></a>
<FONT color="green">296</FONT>                samples.add(ReflectionUtils.copy(job.getConfiguration(),<a name="line.296"></a>
<FONT color="green">297</FONT>                                     reader.getCurrentKey(), null));<a name="line.297"></a>
<FONT color="green">298</FONT>                ++kept;<a name="line.298"></a>
<FONT color="green">299</FONT>              }<a name="line.299"></a>
<FONT color="green">300</FONT>            }<a name="line.300"></a>
<FONT color="green">301</FONT>            reader.close();<a name="line.301"></a>
<FONT color="green">302</FONT>          }<a name="line.302"></a>
<FONT color="green">303</FONT>          return (K[])samples.toArray();<a name="line.303"></a>
<FONT color="green">304</FONT>        }<a name="line.304"></a>
<FONT color="green">305</FONT>      }<a name="line.305"></a>
<FONT color="green">306</FONT>    <a name="line.306"></a>
<FONT color="green">307</FONT>      /**<a name="line.307"></a>
<FONT color="green">308</FONT>       * Write a partition file for the given job, using the Sampler provided.<a name="line.308"></a>
<FONT color="green">309</FONT>       * Queries the sampler for a sample keyset, sorts by the output key<a name="line.309"></a>
<FONT color="green">310</FONT>       * comparator, selects the keys for each rank, and writes to the destination<a name="line.310"></a>
<FONT color="green">311</FONT>       * returned from {@link TotalOrderPartitioner#getPartitionFile}.<a name="line.311"></a>
<FONT color="green">312</FONT>       */<a name="line.312"></a>
<FONT color="green">313</FONT>      @SuppressWarnings("unchecked") // getInputFormat, getOutputKeyComparator<a name="line.313"></a>
<FONT color="green">314</FONT>      public static &lt;K,V&gt; void writePartitionFile(Job job, Sampler&lt;K,V&gt; sampler) <a name="line.314"></a>
<FONT color="green">315</FONT>          throws IOException, ClassNotFoundException, InterruptedException {<a name="line.315"></a>
<FONT color="green">316</FONT>        Configuration conf = job.getConfiguration();<a name="line.316"></a>
<FONT color="green">317</FONT>        final InputFormat inf = <a name="line.317"></a>
<FONT color="green">318</FONT>            ReflectionUtils.newInstance(job.getInputFormatClass(), conf);<a name="line.318"></a>
<FONT color="green">319</FONT>        int numPartitions = job.getNumReduceTasks();<a name="line.319"></a>
<FONT color="green">320</FONT>        K[] samples = sampler.getSample(inf, job);<a name="line.320"></a>
<FONT color="green">321</FONT>        LOG.info("Using " + samples.length + " samples");<a name="line.321"></a>
<FONT color="green">322</FONT>        RawComparator&lt;K&gt; comparator =<a name="line.322"></a>
<FONT color="green">323</FONT>          (RawComparator&lt;K&gt;) job.getSortComparator();<a name="line.323"></a>
<FONT color="green">324</FONT>        Arrays.sort(samples, comparator);<a name="line.324"></a>
<FONT color="green">325</FONT>        Path dst = new Path(TotalOrderPartitioner.getPartitionFile(conf));<a name="line.325"></a>
<FONT color="green">326</FONT>        FileSystem fs = dst.getFileSystem(conf);<a name="line.326"></a>
<FONT color="green">327</FONT>        if (fs.exists(dst)) {<a name="line.327"></a>
<FONT color="green">328</FONT>          fs.delete(dst, false);<a name="line.328"></a>
<FONT color="green">329</FONT>        }<a name="line.329"></a>
<FONT color="green">330</FONT>        SequenceFile.Writer writer = SequenceFile.createWriter(fs, <a name="line.330"></a>
<FONT color="green">331</FONT>          conf, dst, job.getMapOutputKeyClass(), NullWritable.class);<a name="line.331"></a>
<FONT color="green">332</FONT>        NullWritable nullValue = NullWritable.get();<a name="line.332"></a>
<FONT color="green">333</FONT>        float stepSize = samples.length / (float) numPartitions;<a name="line.333"></a>
<FONT color="green">334</FONT>        int last = -1;<a name="line.334"></a>
<FONT color="green">335</FONT>        for(int i = 1; i &lt; numPartitions; ++i) {<a name="line.335"></a>
<FONT color="green">336</FONT>          int k = Math.round(stepSize * i);<a name="line.336"></a>
<FONT color="green">337</FONT>          while (last &gt;= k &amp;&amp; comparator.compare(samples[last], samples[k]) == 0) {<a name="line.337"></a>
<FONT color="green">338</FONT>            ++k;<a name="line.338"></a>
<FONT color="green">339</FONT>          }<a name="line.339"></a>
<FONT color="green">340</FONT>          writer.append(samples[k], nullValue);<a name="line.340"></a>
<FONT color="green">341</FONT>          last = k;<a name="line.341"></a>
<FONT color="green">342</FONT>        }<a name="line.342"></a>
<FONT color="green">343</FONT>        writer.close();<a name="line.343"></a>
<FONT color="green">344</FONT>      }<a name="line.344"></a>
<FONT color="green">345</FONT>    <a name="line.345"></a>
<FONT color="green">346</FONT>      /**<a name="line.346"></a>
<FONT color="green">347</FONT>       * Driver for InputSampler from the command line.<a name="line.347"></a>
<FONT color="green">348</FONT>       * Configures a JobConf instance and calls {@link #writePartitionFile}.<a name="line.348"></a>
<FONT color="green">349</FONT>       */<a name="line.349"></a>
<FONT color="green">350</FONT>      public int run(String[] args) throws Exception {<a name="line.350"></a>
<FONT color="green">351</FONT>        Job job = new Job(getConf());<a name="line.351"></a>
<FONT color="green">352</FONT>        ArrayList&lt;String&gt; otherArgs = new ArrayList&lt;String&gt;();<a name="line.352"></a>
<FONT color="green">353</FONT>        Sampler&lt;K,V&gt; sampler = null;<a name="line.353"></a>
<FONT color="green">354</FONT>        for(int i=0; i &lt; args.length; ++i) {<a name="line.354"></a>
<FONT color="green">355</FONT>          try {<a name="line.355"></a>
<FONT color="green">356</FONT>            if ("-r".equals(args[i])) {<a name="line.356"></a>
<FONT color="green">357</FONT>              job.setNumReduceTasks(Integer.parseInt(args[++i]));<a name="line.357"></a>
<FONT color="green">358</FONT>            } else if ("-inFormat".equals(args[i])) {<a name="line.358"></a>
<FONT color="green">359</FONT>              job.setInputFormatClass(<a name="line.359"></a>
<FONT color="green">360</FONT>                  Class.forName(args[++i]).asSubclass(InputFormat.class));<a name="line.360"></a>
<FONT color="green">361</FONT>            } else if ("-keyClass".equals(args[i])) {<a name="line.361"></a>
<FONT color="green">362</FONT>              job.setMapOutputKeyClass(<a name="line.362"></a>
<FONT color="green">363</FONT>                  Class.forName(args[++i]).asSubclass(WritableComparable.class));<a name="line.363"></a>
<FONT color="green">364</FONT>            } else if ("-splitSample".equals(args[i])) {<a name="line.364"></a>
<FONT color="green">365</FONT>              int numSamples = Integer.parseInt(args[++i]);<a name="line.365"></a>
<FONT color="green">366</FONT>              int maxSplits = Integer.parseInt(args[++i]);<a name="line.366"></a>
<FONT color="green">367</FONT>              if (0 &gt;= maxSplits) maxSplits = Integer.MAX_VALUE;<a name="line.367"></a>
<FONT color="green">368</FONT>              sampler = new SplitSampler&lt;K,V&gt;(numSamples, maxSplits);<a name="line.368"></a>
<FONT color="green">369</FONT>            } else if ("-splitRandom".equals(args[i])) {<a name="line.369"></a>
<FONT color="green">370</FONT>              double pcnt = Double.parseDouble(args[++i]);<a name="line.370"></a>
<FONT color="green">371</FONT>              int numSamples = Integer.parseInt(args[++i]);<a name="line.371"></a>
<FONT color="green">372</FONT>              int maxSplits = Integer.parseInt(args[++i]);<a name="line.372"></a>
<FONT color="green">373</FONT>              if (0 &gt;= maxSplits) maxSplits = Integer.MAX_VALUE;<a name="line.373"></a>
<FONT color="green">374</FONT>              sampler = new RandomSampler&lt;K,V&gt;(pcnt, numSamples, maxSplits);<a name="line.374"></a>
<FONT color="green">375</FONT>            } else if ("-splitInterval".equals(args[i])) {<a name="line.375"></a>
<FONT color="green">376</FONT>              double pcnt = Double.parseDouble(args[++i]);<a name="line.376"></a>
<FONT color="green">377</FONT>              int maxSplits = Integer.parseInt(args[++i]);<a name="line.377"></a>
<FONT color="green">378</FONT>              if (0 &gt;= maxSplits) maxSplits = Integer.MAX_VALUE;<a name="line.378"></a>
<FONT color="green">379</FONT>              sampler = new IntervalSampler&lt;K,V&gt;(pcnt, maxSplits);<a name="line.379"></a>
<FONT color="green">380</FONT>            } else {<a name="line.380"></a>
<FONT color="green">381</FONT>              otherArgs.add(args[i]);<a name="line.381"></a>
<FONT color="green">382</FONT>            }<a name="line.382"></a>
<FONT color="green">383</FONT>          } catch (NumberFormatException except) {<a name="line.383"></a>
<FONT color="green">384</FONT>            System.out.println("ERROR: Integer expected instead of " + args[i]);<a name="line.384"></a>
<FONT color="green">385</FONT>            return printUsage();<a name="line.385"></a>
<FONT color="green">386</FONT>          } catch (ArrayIndexOutOfBoundsException except) {<a name="line.386"></a>
<FONT color="green">387</FONT>            System.out.println("ERROR: Required parameter missing from " +<a name="line.387"></a>
<FONT color="green">388</FONT>                args[i-1]);<a name="line.388"></a>
<FONT color="green">389</FONT>            return printUsage();<a name="line.389"></a>
<FONT color="green">390</FONT>          }<a name="line.390"></a>
<FONT color="green">391</FONT>        }<a name="line.391"></a>
<FONT color="green">392</FONT>        if (job.getNumReduceTasks() &lt;= 1) {<a name="line.392"></a>
<FONT color="green">393</FONT>          System.err.println("Sampler requires more than one reducer");<a name="line.393"></a>
<FONT color="green">394</FONT>          return printUsage();<a name="line.394"></a>
<FONT color="green">395</FONT>        }<a name="line.395"></a>
<FONT color="green">396</FONT>        if (otherArgs.size() &lt; 2) {<a name="line.396"></a>
<FONT color="green">397</FONT>          System.out.println("ERROR: Wrong number of parameters: ");<a name="line.397"></a>
<FONT color="green">398</FONT>          return printUsage();<a name="line.398"></a>
<FONT color="green">399</FONT>        }<a name="line.399"></a>
<FONT color="green">400</FONT>        if (null == sampler) {<a name="line.400"></a>
<FONT color="green">401</FONT>          sampler = new RandomSampler&lt;K,V&gt;(0.1, 10000, 10);<a name="line.401"></a>
<FONT color="green">402</FONT>        }<a name="line.402"></a>
<FONT color="green">403</FONT>    <a name="line.403"></a>
<FONT color="green">404</FONT>        Path outf = new Path(otherArgs.remove(otherArgs.size() - 1));<a name="line.404"></a>
<FONT color="green">405</FONT>        TotalOrderPartitioner.setPartitionFile(getConf(), outf);<a name="line.405"></a>
<FONT color="green">406</FONT>        for (String s : otherArgs) {<a name="line.406"></a>
<FONT color="green">407</FONT>          FileInputFormat.addInputPath(job, new Path(s));<a name="line.407"></a>
<FONT color="green">408</FONT>        }<a name="line.408"></a>
<FONT color="green">409</FONT>        InputSampler.&lt;K,V&gt;writePartitionFile(job, sampler);<a name="line.409"></a>
<FONT color="green">410</FONT>    <a name="line.410"></a>
<FONT color="green">411</FONT>        return 0;<a name="line.411"></a>
<FONT color="green">412</FONT>      }<a name="line.412"></a>
<FONT color="green">413</FONT>    <a name="line.413"></a>
<FONT color="green">414</FONT>      public static void main(String[] args) throws Exception {<a name="line.414"></a>
<FONT color="green">415</FONT>        InputSampler&lt;?,?&gt; sampler = new InputSampler(new Configuration());<a name="line.415"></a>
<FONT color="green">416</FONT>        int res = ToolRunner.run(sampler, args);<a name="line.416"></a>
<FONT color="green">417</FONT>        System.exit(res);<a name="line.417"></a>
<FONT color="green">418</FONT>      }<a name="line.418"></a>
<FONT color="green">419</FONT>    }<a name="line.419"></a>




























































</PRE>
</BODY>
</HTML>
