<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.aggregate;<a name="line.19"></a>
<FONT color="green">020</FONT>    <a name="line.20"></a>
<FONT color="green">021</FONT>    import java.util.ArrayList;<a name="line.21"></a>
<FONT color="green">022</FONT>    import java.util.Iterator;<a name="line.22"></a>
<FONT color="green">023</FONT>    import java.util.TreeMap;<a name="line.23"></a>
<FONT color="green">024</FONT>    import java.util.Map.Entry;<a name="line.24"></a>
<FONT color="green">025</FONT>    import java.util.Arrays;<a name="line.25"></a>
<FONT color="green">026</FONT>    <a name="line.26"></a>
<FONT color="green">027</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.27"></a>
<FONT color="green">028</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.28"></a>
<FONT color="green">029</FONT>    <a name="line.29"></a>
<FONT color="green">030</FONT>    <a name="line.30"></a>
<FONT color="green">031</FONT>    /**<a name="line.31"></a>
<FONT color="green">032</FONT>     * This class implements a value aggregator that computes the <a name="line.32"></a>
<FONT color="green">033</FONT>     * histogram of a sequence of strings.<a name="line.33"></a>
<FONT color="green">034</FONT>     * <a name="line.34"></a>
<FONT color="green">035</FONT>     */<a name="line.35"></a>
<FONT color="green">036</FONT>    @InterfaceAudience.Public<a name="line.36"></a>
<FONT color="green">037</FONT>    @InterfaceStability.Stable<a name="line.37"></a>
<FONT color="green">038</FONT>    public class ValueHistogram implements ValueAggregator&lt;String&gt; {<a name="line.38"></a>
<FONT color="green">039</FONT>    <a name="line.39"></a>
<FONT color="green">040</FONT>      TreeMap&lt;Object, Object&gt; items = null;<a name="line.40"></a>
<FONT color="green">041</FONT>    <a name="line.41"></a>
<FONT color="green">042</FONT>      public ValueHistogram() {<a name="line.42"></a>
<FONT color="green">043</FONT>        items = new TreeMap&lt;Object, Object&gt;();<a name="line.43"></a>
<FONT color="green">044</FONT>      }<a name="line.44"></a>
<FONT color="green">045</FONT>    <a name="line.45"></a>
<FONT color="green">046</FONT>      /**<a name="line.46"></a>
<FONT color="green">047</FONT>       * add the given val to the aggregator.<a name="line.47"></a>
<FONT color="green">048</FONT>       * <a name="line.48"></a>
<FONT color="green">049</FONT>       * @param val the value to be added. It is expected to be a string<a name="line.49"></a>
<FONT color="green">050</FONT>       * in the form of xxxx\tnum, meaning xxxx has num occurrences.<a name="line.50"></a>
<FONT color="green">051</FONT>       */<a name="line.51"></a>
<FONT color="green">052</FONT>      public void addNextValue(Object val) {<a name="line.52"></a>
<FONT color="green">053</FONT>        String valCountStr = val.toString();<a name="line.53"></a>
<FONT color="green">054</FONT>        int pos = valCountStr.lastIndexOf("\t");<a name="line.54"></a>
<FONT color="green">055</FONT>        String valStr = valCountStr;<a name="line.55"></a>
<FONT color="green">056</FONT>        String countStr = "1";<a name="line.56"></a>
<FONT color="green">057</FONT>        if (pos &gt;= 0) {<a name="line.57"></a>
<FONT color="green">058</FONT>          valStr = valCountStr.substring(0, pos);<a name="line.58"></a>
<FONT color="green">059</FONT>          countStr = valCountStr.substring(pos + 1);<a name="line.59"></a>
<FONT color="green">060</FONT>        }<a name="line.60"></a>
<FONT color="green">061</FONT>        <a name="line.61"></a>
<FONT color="green">062</FONT>        Long count = (Long) this.items.get(valStr);<a name="line.62"></a>
<FONT color="green">063</FONT>        long inc = Long.parseLong(countStr);<a name="line.63"></a>
<FONT color="green">064</FONT>    <a name="line.64"></a>
<FONT color="green">065</FONT>        if (count == null) {<a name="line.65"></a>
<FONT color="green">066</FONT>          count = inc;<a name="line.66"></a>
<FONT color="green">067</FONT>        } else {<a name="line.67"></a>
<FONT color="green">068</FONT>          count = count.longValue() + inc;<a name="line.68"></a>
<FONT color="green">069</FONT>        }<a name="line.69"></a>
<FONT color="green">070</FONT>        items.put(valStr, count);<a name="line.70"></a>
<FONT color="green">071</FONT>      }<a name="line.71"></a>
<FONT color="green">072</FONT>    <a name="line.72"></a>
<FONT color="green">073</FONT>      /**<a name="line.73"></a>
<FONT color="green">074</FONT>       * @return the string representation of this aggregator.<a name="line.74"></a>
<FONT color="green">075</FONT>       * It includes the following basic statistics of the histogram:<a name="line.75"></a>
<FONT color="green">076</FONT>       *    the number of unique values<a name="line.76"></a>
<FONT color="green">077</FONT>       *    the minimum value<a name="line.77"></a>
<FONT color="green">078</FONT>       *    the media value<a name="line.78"></a>
<FONT color="green">079</FONT>       *    the maximum value<a name="line.79"></a>
<FONT color="green">080</FONT>       *    the average value<a name="line.80"></a>
<FONT color="green">081</FONT>       *    the standard deviation<a name="line.81"></a>
<FONT color="green">082</FONT>       */<a name="line.82"></a>
<FONT color="green">083</FONT>      public String getReport() {<a name="line.83"></a>
<FONT color="green">084</FONT>        long[] counts = new long[items.size()];<a name="line.84"></a>
<FONT color="green">085</FONT>    <a name="line.85"></a>
<FONT color="green">086</FONT>        StringBuffer sb = new StringBuffer();<a name="line.86"></a>
<FONT color="green">087</FONT>        Iterator&lt;Object&gt; iter = items.values().iterator();<a name="line.87"></a>
<FONT color="green">088</FONT>        int i = 0;<a name="line.88"></a>
<FONT color="green">089</FONT>        while (iter.hasNext()) {<a name="line.89"></a>
<FONT color="green">090</FONT>          Long count = (Long) iter.next();<a name="line.90"></a>
<FONT color="green">091</FONT>          counts[i] = count.longValue();<a name="line.91"></a>
<FONT color="green">092</FONT>          i += 1;<a name="line.92"></a>
<FONT color="green">093</FONT>        }<a name="line.93"></a>
<FONT color="green">094</FONT>        Arrays.sort(counts);<a name="line.94"></a>
<FONT color="green">095</FONT>        sb.append(counts.length);<a name="line.95"></a>
<FONT color="green">096</FONT>        i = 0;<a name="line.96"></a>
<FONT color="green">097</FONT>        long acc = 0;<a name="line.97"></a>
<FONT color="green">098</FONT>        while (i &lt; counts.length) {<a name="line.98"></a>
<FONT color="green">099</FONT>          long nextVal = counts[i];<a name="line.99"></a>
<FONT color="green">100</FONT>          int j = i + 1;<a name="line.100"></a>
<FONT color="green">101</FONT>          while (j &lt; counts.length &amp;&amp; counts[j] == nextVal) {<a name="line.101"></a>
<FONT color="green">102</FONT>            j++;<a name="line.102"></a>
<FONT color="green">103</FONT>          }<a name="line.103"></a>
<FONT color="green">104</FONT>          acc += nextVal * (j - i);<a name="line.104"></a>
<FONT color="green">105</FONT>          i = j;<a name="line.105"></a>
<FONT color="green">106</FONT>        }<a name="line.106"></a>
<FONT color="green">107</FONT>        double average = 0.0;<a name="line.107"></a>
<FONT color="green">108</FONT>        double sd = 0.0;<a name="line.108"></a>
<FONT color="green">109</FONT>        if (counts.length &gt; 0) {<a name="line.109"></a>
<FONT color="green">110</FONT>          sb.append("\t").append(counts[0]);<a name="line.110"></a>
<FONT color="green">111</FONT>          sb.append("\t").append(counts[counts.length / 2]);<a name="line.111"></a>
<FONT color="green">112</FONT>          sb.append("\t").append(counts[counts.length - 1]);<a name="line.112"></a>
<FONT color="green">113</FONT>    <a name="line.113"></a>
<FONT color="green">114</FONT>          average = acc * 1.0 / counts.length;<a name="line.114"></a>
<FONT color="green">115</FONT>          sb.append("\t").append(average);<a name="line.115"></a>
<FONT color="green">116</FONT>    <a name="line.116"></a>
<FONT color="green">117</FONT>          i = 0;<a name="line.117"></a>
<FONT color="green">118</FONT>          while (i &lt; counts.length) {<a name="line.118"></a>
<FONT color="green">119</FONT>            double nextDiff = counts[i] - average;<a name="line.119"></a>
<FONT color="green">120</FONT>            sd += nextDiff * nextDiff;<a name="line.120"></a>
<FONT color="green">121</FONT>            i += 1;<a name="line.121"></a>
<FONT color="green">122</FONT>          }<a name="line.122"></a>
<FONT color="green">123</FONT>          sd = Math.sqrt(sd / counts.length);<a name="line.123"></a>
<FONT color="green">124</FONT>          sb.append("\t").append(sd);<a name="line.124"></a>
<FONT color="green">125</FONT>    <a name="line.125"></a>
<FONT color="green">126</FONT>        }<a name="line.126"></a>
<FONT color="green">127</FONT>        return sb.toString();<a name="line.127"></a>
<FONT color="green">128</FONT>      }<a name="line.128"></a>
<FONT color="green">129</FONT>    <a name="line.129"></a>
<FONT color="green">130</FONT>      /** <a name="line.130"></a>
<FONT color="green">131</FONT>       * <a name="line.131"></a>
<FONT color="green">132</FONT>       * @return a string representation of the list of value/frequence pairs of <a name="line.132"></a>
<FONT color="green">133</FONT>       * the histogram<a name="line.133"></a>
<FONT color="green">134</FONT>       */<a name="line.134"></a>
<FONT color="green">135</FONT>      public String getReportDetails() {<a name="line.135"></a>
<FONT color="green">136</FONT>        StringBuffer sb = new StringBuffer();<a name="line.136"></a>
<FONT color="green">137</FONT>        Iterator&lt;Entry&lt;Object,Object&gt;&gt; iter = items.entrySet().iterator();<a name="line.137"></a>
<FONT color="green">138</FONT>        while (iter.hasNext()) {<a name="line.138"></a>
<FONT color="green">139</FONT>          Entry&lt;Object,Object&gt; en = iter.next();<a name="line.139"></a>
<FONT color="green">140</FONT>          Object val = en.getKey();<a name="line.140"></a>
<FONT color="green">141</FONT>          Long count = (Long) en.getValue();<a name="line.141"></a>
<FONT color="green">142</FONT>          sb.append("\t").append(val.toString()).append("\t").<a name="line.142"></a>
<FONT color="green">143</FONT>             append(count.longValue()).append("\n");<a name="line.143"></a>
<FONT color="green">144</FONT>        }<a name="line.144"></a>
<FONT color="green">145</FONT>        return sb.toString();<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>      /**<a name="line.148"></a>
<FONT color="green">149</FONT>       *  @return a list value/frequence pairs.<a name="line.149"></a>
<FONT color="green">150</FONT>       *  The return value is expected to be used by the reducer.<a name="line.150"></a>
<FONT color="green">151</FONT>       */<a name="line.151"></a>
<FONT color="green">152</FONT>      public ArrayList&lt;String&gt; getCombinerOutput() {<a name="line.152"></a>
<FONT color="green">153</FONT>        ArrayList&lt;String&gt; retv = new ArrayList&lt;String&gt;();<a name="line.153"></a>
<FONT color="green">154</FONT>        Iterator&lt;Entry&lt;Object,Object&gt;&gt; iter = items.entrySet().iterator();<a name="line.154"></a>
<FONT color="green">155</FONT>    <a name="line.155"></a>
<FONT color="green">156</FONT>        while (iter.hasNext()) {<a name="line.156"></a>
<FONT color="green">157</FONT>          Entry&lt;Object,Object&gt; en =  iter.next();<a name="line.157"></a>
<FONT color="green">158</FONT>          Object val = en.getKey();<a name="line.158"></a>
<FONT color="green">159</FONT>          Long count = (Long) en.getValue();<a name="line.159"></a>
<FONT color="green">160</FONT>          retv.add(val.toString() + "\t" + count.longValue());<a name="line.160"></a>
<FONT color="green">161</FONT>        }<a name="line.161"></a>
<FONT color="green">162</FONT>        return retv;<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>      /** <a name="line.165"></a>
<FONT color="green">166</FONT>       * <a name="line.166"></a>
<FONT color="green">167</FONT>       * @return a TreeMap representation of the histogram<a name="line.167"></a>
<FONT color="green">168</FONT>       */<a name="line.168"></a>
<FONT color="green">169</FONT>      public TreeMap&lt;Object,Object&gt; getReportItems() {<a name="line.169"></a>
<FONT color="green">170</FONT>        return items;<a name="line.170"></a>
<FONT color="green">171</FONT>      }<a name="line.171"></a>
<FONT color="green">172</FONT>    <a name="line.172"></a>
<FONT color="green">173</FONT>      /** <a name="line.173"></a>
<FONT color="green">174</FONT>       * reset the aggregator<a name="line.174"></a>
<FONT color="green">175</FONT>       */<a name="line.175"></a>
<FONT color="green">176</FONT>      public void reset() {<a name="line.176"></a>
<FONT color="green">177</FONT>        items = new TreeMap&lt;Object, Object&gt;();<a name="line.177"></a>
<FONT color="green">178</FONT>      }<a name="line.178"></a>
<FONT color="green">179</FONT>    <a name="line.179"></a>
<FONT color="green">180</FONT>    }<a name="line.180"></a>




























































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