<HTML>
<BODY BGCOLOR="white">
<PRE>
<FONT color="green">001</FONT> package org.maltparser.parser.guide.instance;<a name="line.1"></a>
<FONT color="green">002</FONT> <a name="line.2"></a>
<FONT color="green">003</FONT> import java.io.BufferedReader;<a name="line.3"></a>
<FONT color="green">004</FONT> import java.io.BufferedWriter;<a name="line.4"></a>
<FONT color="green">005</FONT> import java.io.IOException;<a name="line.5"></a>
<FONT color="green">006</FONT> import java.util.SortedMap;<a name="line.6"></a>
<FONT color="green">007</FONT> <a name="line.7"></a>
<FONT color="green">008</FONT> import java.util.ArrayList;<a name="line.8"></a>
<FONT color="green">009</FONT> import java.util.TreeMap;<a name="line.9"></a>
<FONT color="green">010</FONT> import java.util.TreeSet;<a name="line.10"></a>
<FONT color="green">011</FONT> import java.util.regex.Pattern;<a name="line.11"></a>
<FONT color="green">012</FONT> <a name="line.12"></a>
<FONT color="green">013</FONT> import org.maltparser.core.exception.MaltChainedException;<a name="line.13"></a>
<FONT color="green">014</FONT> import org.maltparser.core.feature.FeatureException;<a name="line.14"></a>
<FONT color="green">015</FONT> import org.maltparser.core.feature.FeatureVector;<a name="line.15"></a>
<FONT color="green">016</FONT> import org.maltparser.core.feature.function.FeatureFunction;<a name="line.16"></a>
<FONT color="green">017</FONT> import org.maltparser.core.feature.function.Modifiable;<a name="line.17"></a>
<FONT color="green">018</FONT> import org.maltparser.core.feature.value.SingleFeatureValue;<a name="line.18"></a>
<FONT color="green">019</FONT> import org.maltparser.core.syntaxgraph.DependencyStructure;<a name="line.19"></a>
<FONT color="green">020</FONT> import org.maltparser.parser.guide.ClassifierGuide;<a name="line.20"></a>
<FONT color="green">021</FONT> import org.maltparser.parser.guide.GuideException;<a name="line.21"></a>
<FONT color="green">022</FONT> import org.maltparser.parser.guide.Model;<a name="line.22"></a>
<FONT color="green">023</FONT> import org.maltparser.parser.history.action.SingleDecision;<a name="line.23"></a>
<FONT color="green">024</FONT> <a name="line.24"></a>
<FONT color="green">025</FONT> /**<a name="line.25"></a>
<FONT color="green">026</FONT> The feature divide model is used for divide the training instances into several models according to<a name="line.26"></a>
<FONT color="green">027</FONT> a divide feature. Usually this strategy decrease the training and classification time, but can also decrease <a name="line.27"></a>
<FONT color="green">028</FONT> the accuracy of the parser. <a name="line.28"></a>
<FONT color="green">029</FONT> <a name="line.29"></a>
<FONT color="green">030</FONT> @author Johan Hall<a name="line.30"></a>
<FONT color="green">031</FONT> @since 1.0<a name="line.31"></a>
<FONT color="green">032</FONT> */<a name="line.32"></a>
<FONT color="green">033</FONT> public class FeatureDivideModel implements InstanceModel {<a name="line.33"></a>
<FONT color="green">034</FONT> private Model parent;<a name="line.34"></a>
<FONT color="green">035</FONT> private final SortedMap<Integer,AtomicModel> divideModels;<a name="line.35"></a>
<FONT color="green">036</FONT> private FeatureVector masterFeatureVector;<a name="line.36"></a>
<FONT color="green">037</FONT> private FeatureVector divideFeatureVector;<a name="line.37"></a>
<FONT color="green">038</FONT> private int frequency = 0;<a name="line.38"></a>
<FONT color="green">039</FONT> private FeatureFunction divideFeature;<a name="line.39"></a>
<FONT color="green">040</FONT> private int divideThreshold;<a name="line.40"></a>
<FONT color="green">041</FONT> private AtomicModel masterModel;<a name="line.41"></a>
<FONT color="green">042</FONT> private ArrayList<Integer> divideFeatureIndexVector;<a name="line.42"></a>
<FONT color="green">043</FONT> <a name="line.43"></a>
<FONT color="green">044</FONT> /**<a name="line.44"></a>
<FONT color="green">045</FONT> * Constructs a feature divide model.<a name="line.45"></a>
<FONT color="green">046</FONT> * <a name="line.46"></a>
<FONT color="green">047</FONT> * @param features the feature vector used by the atomic model.<a name="line.47"></a>
<FONT color="green">048</FONT> * @param parent the parent guide model.<a name="line.48"></a>
<FONT color="green">049</FONT> * @throws MaltChainedException<a name="line.49"></a>
<FONT color="green">050</FONT> */<a name="line.50"></a>
<FONT color="green">051</FONT> public FeatureDivideModel(FeatureVector features, Model parent) throws MaltChainedException {<a name="line.51"></a>
<FONT color="green">052</FONT> setParent(parent);<a name="line.52"></a>
<FONT color="green">053</FONT> setFrequency(0);<a name="line.53"></a>
<FONT color="green">054</FONT> initSplitParam(features);<a name="line.54"></a>
<FONT color="green">055</FONT> divideModels = new TreeMap<Integer,AtomicModel>();<a name="line.55"></a>
<FONT color="green">056</FONT> if (getGuide().getGuideMode() == ClassifierGuide.GuideMode.BATCH) {<a name="line.56"></a>
<FONT color="green">057</FONT> masterModel = new AtomicModel(-1, masterFeatureVector, this);<a name="line.57"></a>
<FONT color="green">058</FONT> } else if (getGuide().getGuideMode() == ClassifierGuide.GuideMode.CLASSIFY) {<a name="line.58"></a>
<FONT color="green">059</FONT> load();<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> <a name="line.62"></a>
<FONT color="green">063</FONT> public void addInstance(SingleDecision decision) throws MaltChainedException {<a name="line.63"></a>
<FONT color="green">064</FONT> if (getGuide().getGuideMode() == ClassifierGuide.GuideMode.CLASSIFY) {<a name="line.64"></a>
<FONT color="green">065</FONT> throw new GuideException("Can only add instance during learning. ");<a name="line.65"></a>
<FONT color="green">066</FONT> } else if (!(divideFeature.getFeatureValue() instanceof SingleFeatureValue)) {<a name="line.66"></a>
<FONT color="green">067</FONT> throw new GuideException("The divide feature does not have a single value. ");<a name="line.67"></a>
<FONT color="green">068</FONT> }<a name="line.68"></a>
<FONT color="green">069</FONT> <a name="line.69"></a>
<FONT color="green">070</FONT> divideFeature.update();<a name="line.70"></a>
<FONT color="green">071</FONT> if (divideModels != null) { <a name="line.71"></a>
<FONT color="green">072</FONT> if (!divideModels.containsKey(((SingleFeatureValue)divideFeature.getFeatureValue()).getCode())) {<a name="line.72"></a>
<FONT color="green">073</FONT> divideModels.put(((SingleFeatureValue)divideFeature.getFeatureValue()).getCode(), new AtomicModel(((SingleFeatureValue)divideFeature.getFeatureValue()).getCode(), divideFeatureVector, this));<a name="line.73"></a>
<FONT color="green">074</FONT> }<a name="line.74"></a>
<FONT color="green">075</FONT> divideModels.get(((SingleFeatureValue)divideFeature.getFeatureValue()).getCode()).addInstance(decision);<a name="line.75"></a>
<FONT color="green">076</FONT> } else {<a name="line.76"></a>
<FONT color="green">077</FONT> throw new GuideException("The feature divide models cannot be found. ");<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> public void noMoreInstances() throws MaltChainedException {<a name="line.81"></a>
<FONT color="green">082</FONT> // if (getGuide().getGuideMode() == Guide.GuideMode.CLASSIFY) {<a name="line.82"></a>
<FONT color="green">083</FONT> // throw new GuideException("Can only finish all data during learning. ");<a name="line.83"></a>
<FONT color="green">084</FONT> // }<a name="line.84"></a>
<FONT color="green">085</FONT> <a name="line.85"></a>
<FONT color="green">086</FONT> if (divideModels != null) {<a name="line.86"></a>
<FONT color="green">087</FONT> divideFeature.updateCardinality();<a name="line.87"></a>
<FONT color="green">088</FONT> for (Integer index : divideModels.keySet()) {<a name="line.88"></a>
<FONT color="green">089</FONT> divideModels.get(index).noMoreInstances();<a name="line.89"></a>
<FONT color="green">090</FONT> }<a name="line.90"></a>
<FONT color="green">091</FONT> final TreeSet<Integer> removeSet = new TreeSet<Integer>();<a name="line.91"></a>
<FONT color="green">092</FONT> for (Integer index : divideModels.keySet()) {<a name="line.92"></a>
<FONT color="green">093</FONT> if (divideModels.get(index).getFrequency() <= divideThreshold) {<a name="line.93"></a>
<FONT color="green">094</FONT> divideModels.get(index).moveAllInstances(masterModel, divideFeature, divideFeatureIndexVector);<a name="line.94"></a>
<FONT color="green">095</FONT> removeSet.add(index);<a name="line.95"></a>
<FONT color="green">096</FONT> }<a name="line.96"></a>
<FONT color="green">097</FONT> }<a name="line.97"></a>
<FONT color="green">098</FONT> for (Integer index : removeSet) {<a name="line.98"></a>
<FONT color="green">099</FONT> divideModels.remove(index);<a name="line.99"></a>
<FONT color="green">100</FONT> }<a name="line.100"></a>
<FONT color="green">101</FONT> masterModel.noMoreInstances();<a name="line.101"></a>
<FONT color="green">102</FONT> <a name="line.102"></a>
<FONT color="green">103</FONT> } else {<a name="line.103"></a>
<FONT color="green">104</FONT> throw new GuideException("The feature divide models cannot be found. ");<a name="line.104"></a>
<FONT color="green">105</FONT> }<a name="line.105"></a>
<FONT color="green">106</FONT> }<a name="line.106"></a>
<FONT color="green">107</FONT> <a name="line.107"></a>
<FONT color="green">108</FONT> public void finalizeSentence(DependencyStructure dependencyGraph) throws MaltChainedException {<a name="line.108"></a>
<FONT color="green">109</FONT> // if (getGuide().getGuideMode() == Guide.GuideMode.CLASSIFY) {<a name="line.109"></a>
<FONT color="green">110</FONT> // throw new GuideException("Can only finish sentence during learning. ");<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> if (divideModels != null) { <a name="line.113"></a>
<FONT color="green">114</FONT> for (AtomicModel divideModel : divideModels.values()) {<a name="line.114"></a>
<FONT color="green">115</FONT> divideModel.finalizeSentence(dependencyGraph);<a name="line.115"></a>
<FONT color="green">116</FONT> }<a name="line.116"></a>
<FONT color="green">117</FONT> } else {<a name="line.117"></a>
<FONT color="green">118</FONT> throw new GuideException("The feature divide models cannot be found. ");<a name="line.118"></a>
<FONT color="green">119</FONT> }<a name="line.119"></a>
<FONT color="green">120</FONT> }<a name="line.120"></a>
<FONT color="green">121</FONT> <a name="line.121"></a>
<FONT color="green">122</FONT> public boolean predict(SingleDecision decision) throws MaltChainedException {<a name="line.122"></a>
<FONT color="green">123</FONT> if (getGuide().getGuideMode() == ClassifierGuide.GuideMode.BATCH) {<a name="line.123"></a>
<FONT color="green">124</FONT> throw new GuideException("Can only predict during parsing. ");<a name="line.124"></a>
<FONT color="green">125</FONT> } else if (!(divideFeature.getFeatureValue() instanceof SingleFeatureValue)) {<a name="line.125"></a>
<FONT color="green">126</FONT> throw new GuideException("The divide feature does not have a single value. ");<a name="line.126"></a>
<FONT color="green">127</FONT> }<a name="line.127"></a>
<FONT color="green">128</FONT> <a name="line.128"></a>
<FONT color="green">129</FONT> //divideFeature.update();<a name="line.129"></a>
<FONT color="green">130</FONT> if (divideModels != null && divideModels.containsKey(((SingleFeatureValue)divideFeature.getFeatureValue()).getCode())) {<a name="line.130"></a>
<FONT color="green">131</FONT> return divideModels.get(((SingleFeatureValue)divideFeature.getFeatureValue()).getCode()).predict(decision);<a name="line.131"></a>
<FONT color="green">132</FONT> } else if (masterModel != null && masterModel.getFrequency() > 0) {<a name="line.132"></a>
<FONT color="green">133</FONT> return masterModel.predict(decision);<a name="line.133"></a>
<FONT color="green">134</FONT> } else {<a name="line.134"></a>
<FONT color="green">135</FONT> getGuide().getConfiguration().getConfigLogger().info("Could not predict the next parser decision because there is " +<a name="line.135"></a>
<FONT color="green">136</FONT> "no divide or master model that covers the divide value '"+((SingleFeatureValue)divideFeature.getFeatureValue()).getCode()+"', as default" +<a name="line.136"></a>
<FONT color="green">137</FONT> " class code '1' is used. ");<a name="line.137"></a>
<FONT color="green">138</FONT> <a name="line.138"></a>
<FONT color="green">139</FONT> decision.addDecision(1); // default prediction<a name="line.139"></a>
<FONT color="green">140</FONT> //classCodeTable.getEmptyKBestList().addKBestItem(1); <a name="line.140"></a>
<FONT color="green">141</FONT> }<a name="line.141"></a>
<FONT color="green">142</FONT> return true;<a name="line.142"></a>
<FONT color="green">143</FONT> }<a name="line.143"></a>
<FONT color="green">144</FONT> <a name="line.144"></a>
<FONT color="green">145</FONT> public FeatureVector predictExtract(SingleDecision decision) throws MaltChainedException {<a name="line.145"></a>
<FONT color="green">146</FONT> return getAtomicModel().predictExtract(decision);<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> public FeatureVector extract() throws MaltChainedException {<a name="line.149"></a>
<FONT color="green">150</FONT> return getAtomicModel().extract();<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> private AtomicModel getAtomicModel() throws MaltChainedException {<a name="line.153"></a>
<FONT color="green">154</FONT> if (getGuide().getGuideMode() == ClassifierGuide.GuideMode.BATCH) {<a name="line.154"></a>
<FONT color="green">155</FONT> throw new GuideException("Can only predict during parsing. ");<a name="line.155"></a>
<FONT color="green">156</FONT> } else if (!(divideFeature.getFeatureValue() instanceof SingleFeatureValue)) {<a name="line.156"></a>
<FONT color="green">157</FONT> throw new GuideException("The divide feature does not have a single value. ");<a name="line.157"></a>
<FONT color="green">158</FONT> }<a name="line.158"></a>
<FONT color="green">159</FONT> <a name="line.159"></a>
<FONT color="green">160</FONT> if (divideModels != null && divideModels.containsKey(((SingleFeatureValue)divideFeature.getFeatureValue()).getCode())) {<a name="line.160"></a>
<FONT color="green">161</FONT> return divideModels.get(((SingleFeatureValue)divideFeature.getFeatureValue()).getCode());<a name="line.161"></a>
<FONT color="green">162</FONT> } else if (masterModel != null && masterModel.getFrequency() > 0) {<a name="line.162"></a>
<FONT color="green">163</FONT> return masterModel;<a name="line.163"></a>
<FONT color="green">164</FONT> } else {<a name="line.164"></a>
<FONT color="green">165</FONT> getGuide().getConfiguration().getConfigLogger().info("Could not predict the next parser decision because there is " +<a name="line.165"></a>
<FONT color="green">166</FONT> "no divide or master model that covers the divide value '"+((SingleFeatureValue)divideFeature.getFeatureValue()).getCode()+"', as default" +<a name="line.166"></a>
<FONT color="green">167</FONT> " class code '1' is used. ");<a name="line.167"></a>
<FONT color="green">168</FONT> }<a name="line.168"></a>
<FONT color="green">169</FONT> return null;<a name="line.169"></a>
<FONT color="green">170</FONT> }<a name="line.170"></a>
<FONT color="green">171</FONT> <a name="line.171"></a>
<FONT color="green">172</FONT> public void terminate() throws MaltChainedException {<a name="line.172"></a>
<FONT color="green">173</FONT> if (divideModels != null) {<a name="line.173"></a>
<FONT color="green">174</FONT> for (AtomicModel divideModel : divideModels.values()) { <a name="line.174"></a>
<FONT color="green">175</FONT> divideModel.terminate();<a name="line.175"></a>
<FONT color="green">176</FONT> }<a name="line.176"></a>
<FONT color="green">177</FONT> }<a name="line.177"></a>
<FONT color="green">178</FONT> if (masterModel != null) {<a name="line.178"></a>
<FONT color="green">179</FONT> masterModel.terminate();<a name="line.179"></a>
<FONT color="green">180</FONT> }<a name="line.180"></a>
<FONT color="green">181</FONT> }<a name="line.181"></a>
<FONT color="green">182</FONT> <a name="line.182"></a>
<FONT color="green">183</FONT> public void train() throws MaltChainedException {<a name="line.183"></a>
<FONT color="green">184</FONT> for (AtomicModel divideModel : divideModels.values()) {<a name="line.184"></a>
<FONT color="green">185</FONT> divideModel.train();<a name="line.185"></a>
<FONT color="green">186</FONT> }<a name="line.186"></a>
<FONT color="green">187</FONT> masterModel.train();<a name="line.187"></a>
<FONT color="green">188</FONT> save();<a name="line.188"></a>
<FONT color="green">189</FONT> for (AtomicModel divideModel : divideModels.values()) {<a name="line.189"></a>
<FONT color="green">190</FONT> divideModel.terminate();<a name="line.190"></a>
<FONT color="green">191</FONT> }<a name="line.191"></a>
<FONT color="green">192</FONT> masterModel.terminate();<a name="line.192"></a>
<FONT color="green">193</FONT> }<a name="line.193"></a>
<FONT color="green">194</FONT> <a name="line.194"></a>
<FONT color="green">195</FONT> /**<a name="line.195"></a>
<FONT color="green">196</FONT> * Initialize the feature split parameters and the split feature vector and master feature vector<a name="line.196"></a>
<FONT color="green">197</FONT> * according to the behavior strategy.<a name="line.197"></a>
<FONT color="green">198</FONT> * <a name="line.198"></a>
<FONT color="green">199</FONT> * @param featureVector the parent guide model's feature vector.<a name="line.199"></a>
<FONT color="green">200</FONT> * @throws MaltChainedException<a name="line.200"></a>
<FONT color="green">201</FONT> */<a name="line.201"></a>
<FONT color="green">202</FONT> protected void initSplitParam(FeatureVector featureVector) throws MaltChainedException {<a name="line.202"></a>
<FONT color="green">203</FONT> if (getGuide().getConfiguration().getOptionValue("guide", "data_split_column") == null <a name="line.203"></a>
<FONT color="green">204</FONT> || getGuide().getConfiguration().getOptionValue("guide", "data_split_column").toString().length() == 0) {<a name="line.204"></a>
<FONT color="green">205</FONT> throw new GuideException("The option '--guide-data_split_column' cannot be found, when initializing the data split. ");<a name="line.205"></a>
<FONT color="green">206</FONT> }<a name="line.206"></a>
<FONT color="green">207</FONT> if (getGuide().getConfiguration().getOptionValue("guide", "data_split_structure") == null <a name="line.207"></a>
<FONT color="green">208</FONT> || getGuide().getConfiguration().getOptionValue("guide", "data_split_structure").toString().length() == 0) {<a name="line.208"></a>
<FONT color="green">209</FONT> throw new GuideException("The option '--guide-data_split_structure' cannot be found, when initializing the data split. ");<a name="line.209"></a>
<FONT color="green">210</FONT> }<a name="line.210"></a>
<FONT color="green">211</FONT> try {<a name="line.211"></a>
<FONT color="green">212</FONT> final String spec = "InputColumn(" + getGuide().getConfiguration().getOptionValue("guide", "data_split_column").toString().trim()+<a name="line.212"></a>
<FONT color="green">213</FONT> ", "+getGuide().getConfiguration().getOptionValue("guide", "data_split_structure").toString().trim() +")";<a name="line.213"></a>
<FONT color="green">214</FONT> divideFeature = featureVector.getFeatureModel().identifyFeature(spec);<a name="line.214"></a>
<FONT color="green">215</FONT> } catch (FeatureException e) {<a name="line.215"></a>
<FONT color="green">216</FONT> throw new GuideException("The data split feature 'InputColumn("+getGuide().getConfiguration().getOptionValue("guide", "data_split_column").toString()+", "+getGuide().getConfiguration().getOptionValue("guide", "data_split_structure").toString()+") cannot be initialized. ", e);<a name="line.216"></a>
<FONT color="green">217</FONT> }<a name="line.217"></a>
<FONT color="green">218</FONT> if (!(divideFeature instanceof Modifiable)) {<a name="line.218"></a>
<FONT color="green">219</FONT> throw new GuideException("The data split feature 'InputColumn("+getGuide().getConfiguration().getOptionValue("guide", "data_split_column").toString()+", "+getGuide().getConfiguration().getOptionValue("guide", "data_split_structure").toString()+") does not implement Modifiable interface. ");<a name="line.219"></a>
<FONT color="green">220</FONT> }<a name="line.220"></a>
<FONT color="green">221</FONT> divideFeatureIndexVector = new ArrayList<Integer>();<a name="line.221"></a>
<FONT color="green">222</FONT> for (int i = 0; i < featureVector.size(); i++) {<a name="line.222"></a>
<FONT color="green">223</FONT> if (featureVector.get(i).equals(divideFeature)) {<a name="line.223"></a>
<FONT color="green">224</FONT> divideFeatureIndexVector.add(i);<a name="line.224"></a>
<FONT color="green">225</FONT> }<a name="line.225"></a>
<FONT color="green">226</FONT> }<a name="line.226"></a>
<FONT color="green">227</FONT> <a name="line.227"></a>
<FONT color="green">228</FONT> // if ((Boolean)getGuide().getConfiguration().getOptionValue("malt0.4", "behavior") == true) {<a name="line.228"></a>
<FONT color="green">229</FONT> // /* MaltParser 0.4 removes the divide feature for all divide models. For the "Sum-up" model or<a name="line.229"></a>
<FONT color="green">230</FONT> // * master model adds the divide feature in the end of the feature vector.<a name="line.230"></a>
<FONT color="green">231</FONT> // */<a name="line.231"></a>
<FONT color="green">232</FONT> // masterFeatureVector = (FeatureVector)featureVector.clone();<a name="line.232"></a>
<FONT color="green">233</FONT> // for (Integer i : divideFeatureIndexVector) {<a name="line.233"></a>
<FONT color="green">234</FONT> // masterFeatureVector.remove(masterFeatureVector.get(i));<a name="line.234"></a>
<FONT color="green">235</FONT> // }<a name="line.235"></a>
<FONT color="green">236</FONT> // for (Integer i : divideFeatureIndexVector) {<a name="line.236"></a>
<FONT color="green">237</FONT> // masterFeatureVector.add(featureVector.get(i));<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> // divideFeatureVector = (FeatureVector)featureVector.clone();<a name="line.240"></a>
<FONT color="green">241</FONT> // for (Integer i : divideFeatureIndexVector) {<a name="line.241"></a>
<FONT color="green">242</FONT> // divideFeatureVector.remove(divideFeatureVector.get(i));<a name="line.242"></a>
<FONT color="green">243</FONT> // }<a name="line.243"></a>
<FONT color="green">244</FONT> // } else {<a name="line.244"></a>
<FONT color="green">245</FONT> masterFeatureVector = featureVector;<a name="line.245"></a>
<FONT color="green">246</FONT> divideFeatureVector = (FeatureVector)featureVector.clone();<a name="line.246"></a>
<FONT color="green">247</FONT> for (Integer i : divideFeatureIndexVector) {<a name="line.247"></a>
<FONT color="green">248</FONT> divideFeatureVector.remove(divideFeatureVector.get(i));<a name="line.248"></a>
<FONT color="green">249</FONT> }<a name="line.249"></a>
<FONT color="green">250</FONT> // }<a name="line.250"></a>
<FONT color="green">251</FONT> try {<a name="line.251"></a>
<FONT color="green">252</FONT> if (getGuide().getConfiguration().getOptionValue("guide", "data_split_threshold").toString() != null) {<a name="line.252"></a>
<FONT color="green">253</FONT> divideThreshold = Integer.parseInt(getGuide().getConfiguration().getOptionValue("guide", "data_split_threshold").toString());<a name="line.253"></a>
<FONT color="green">254</FONT> } else {<a name="line.254"></a>
<FONT color="green">255</FONT> divideThreshold = 0;<a name="line.255"></a>
<FONT color="green">256</FONT> }<a name="line.256"></a>
<FONT color="green">257</FONT> } catch (NumberFormatException e) {<a name="line.257"></a>
<FONT color="green">258</FONT> throw new GuideException("The --guide-data_split_threshold option is not an integer value. ", e);<a name="line.258"></a>
<FONT color="green">259</FONT> }<a name="line.259"></a>
<FONT color="green">260</FONT> }<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> * Saves the feature divide model settings .fsm file.<a name="line.263"></a>
<FONT color="green">264</FONT> * <a name="line.264"></a>
<FONT color="green">265</FONT> * @throws MaltChainedException<a name="line.265"></a>
<FONT color="green">266</FONT> */<a name="line.266"></a>
<FONT color="green">267</FONT> protected void save() throws MaltChainedException {<a name="line.267"></a>
<FONT color="green">268</FONT> try {<a name="line.268"></a>
<FONT color="green">269</FONT> final BufferedWriter out = new BufferedWriter(getGuide().getConfiguration().getConfigurationDir().getOutputStreamWriter(getModelName()+".dsm"));<a name="line.269"></a>
<FONT color="green">270</FONT> out.write(masterModel.getIndex() + "\t" + masterModel.getFrequency() + "\n");<a name="line.270"></a>
<FONT color="green">271</FONT> <a name="line.271"></a>
<FONT color="green">272</FONT> if (divideModels != null) {<a name="line.272"></a>
<FONT color="green">273</FONT> for (AtomicModel divideModel : divideModels.values()) {<a name="line.273"></a>
<FONT color="green">274</FONT> out.write(divideModel.getIndex() + "\t" + divideModel.getFrequency() + "\n");<a name="line.274"></a>
<FONT color="green">275</FONT> }<a name="line.275"></a>
<FONT color="green">276</FONT> }<a name="line.276"></a>
<FONT color="green">277</FONT> out.close();<a name="line.277"></a>
<FONT color="green">278</FONT> } catch (IOException e) {<a name="line.278"></a>
<FONT color="green">279</FONT> throw new GuideException("Could not write to the guide model settings file '"+getModelName()+".dsm"+"', when " +<a name="line.279"></a>
<FONT color="green">280</FONT> "saving the guide model settings to file. ", e);<a name="line.280"></a>
<FONT color="green">281</FONT> }<a name="line.281"></a>
<FONT color="green">282</FONT> }<a name="line.282"></a>
<FONT color="green">283</FONT> <a name="line.283"></a>
<FONT color="green">284</FONT> /**<a name="line.284"></a>
<FONT color="green">285</FONT> * Loads the feature divide model settings .fsm file.<a name="line.285"></a>
<FONT color="green">286</FONT> * <a name="line.286"></a>
<FONT color="green">287</FONT> * @throws MaltChainedException<a name="line.287"></a>
<FONT color="green">288</FONT> */<a name="line.288"></a>
<FONT color="green">289</FONT> protected void load() throws MaltChainedException {<a name="line.289"></a>
<FONT color="green">290</FONT> try {<a name="line.290"></a>
<FONT color="green">291</FONT> final BufferedReader in = new BufferedReader(getGuide().getConfiguration().getConfigurationDir().getInputStreamReaderFromConfigFile(getModelName()+".dsm"));<a name="line.291"></a>
<FONT color="green">292</FONT> final Pattern tabPattern = Pattern.compile("\t");<a name="line.292"></a>
<FONT color="green">293</FONT> while(true) {<a name="line.293"></a>
<FONT color="green">294</FONT> String line = in.readLine();<a name="line.294"></a>
<FONT color="green">295</FONT> if(line == null) break;<a name="line.295"></a>
<FONT color="green">296</FONT> String[] cols = tabPattern.split(line);<a name="line.296"></a>
<FONT color="green">297</FONT> if (cols.length != 2) { <a name="line.297"></a>
<FONT color="green">298</FONT> throw new GuideException("");<a name="line.298"></a>
<FONT color="green">299</FONT> }<a name="line.299"></a>
<FONT color="green">300</FONT> int code = -1;<a name="line.300"></a>
<FONT color="green">301</FONT> int freq = 0;<a name="line.301"></a>
<FONT color="green">302</FONT> try {<a name="line.302"></a>
<FONT color="green">303</FONT> code = Integer.parseInt(cols[0]);<a name="line.303"></a>
<FONT color="green">304</FONT> freq = Integer.parseInt(cols[1]);<a name="line.304"></a>
<FONT color="green">305</FONT> } catch (NumberFormatException e) {<a name="line.305"></a>
<FONT color="green">306</FONT> throw new GuideException("Could not convert a string value into an integer value when loading the feature divide model settings (.fsm). ", e);<a name="line.306"></a>
<FONT color="green">307</FONT> }<a name="line.307"></a>
<FONT color="green">308</FONT> if (code == -1) { <a name="line.308"></a>
<FONT color="green">309</FONT> masterModel = new AtomicModel(-1, masterFeatureVector, this);<a name="line.309"></a>
<FONT color="green">310</FONT> masterModel.setFrequency(freq);<a name="line.310"></a>
<FONT color="green">311</FONT> } else if (divideModels != null) {<a name="line.311"></a>
<FONT color="green">312</FONT> divideModels.put(code, new AtomicModel(code, divideFeatureVector, this));<a name="line.312"></a>
<FONT color="green">313</FONT> divideModels.get(code).setFrequency(freq);<a name="line.313"></a>
<FONT color="green">314</FONT> }<a name="line.314"></a>
<FONT color="green">315</FONT> setFrequency(getFrequency()+freq);<a name="line.315"></a>
<FONT color="green">316</FONT> }<a name="line.316"></a>
<FONT color="green">317</FONT> in.close();<a name="line.317"></a>
<FONT color="green">318</FONT> } catch (IOException e) {<a name="line.318"></a>
<FONT color="green">319</FONT> throw new GuideException("Could not read from the guide model settings file '"+getModelName()+".dsm"+"', when " +<a name="line.319"></a>
<FONT color="green">320</FONT> "loading the guide model settings. ", e);<a name="line.320"></a>
<FONT color="green">321</FONT> } <a name="line.321"></a>
<FONT color="green">322</FONT> }<a name="line.322"></a>
<FONT color="green">323</FONT> <a name="line.323"></a>
<FONT color="green">324</FONT> /**<a name="line.324"></a>
<FONT color="green">325</FONT> * Returns the parent model<a name="line.325"></a>
<FONT color="green">326</FONT> * <a name="line.326"></a>
<FONT color="green">327</FONT> * @return the parent model<a name="line.327"></a>
<FONT color="green">328</FONT> */<a name="line.328"></a>
<FONT color="green">329</FONT> public Model getParent() {<a name="line.329"></a>
<FONT color="green">330</FONT> return parent;<a name="line.330"></a>
<FONT color="green">331</FONT> }<a name="line.331"></a>
<FONT color="green">332</FONT> <a name="line.332"></a>
<FONT color="green">333</FONT> public ClassifierGuide getGuide() {<a name="line.333"></a>
<FONT color="green">334</FONT> return parent.getGuide();<a name="line.334"></a>
<FONT color="green">335</FONT> }<a name="line.335"></a>
<FONT color="green">336</FONT> <a name="line.336"></a>
<FONT color="green">337</FONT> /**<a name="line.337"></a>
<FONT color="green">338</FONT> * Sets the parent model<a name="line.338"></a>
<FONT color="green">339</FONT> * <a name="line.339"></a>
<FONT color="green">340</FONT> * @param parent the parent model<a name="line.340"></a>
<FONT color="green">341</FONT> */<a name="line.341"></a>
<FONT color="green">342</FONT> protected void setParent(Model parent) throws MaltChainedException {<a name="line.342"></a>
<FONT color="green">343</FONT> this.parent = parent;<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> public String getModelName() throws MaltChainedException {<a name="line.347"></a>
<FONT color="green">348</FONT> try {<a name="line.348"></a>
<FONT color="green">349</FONT> return parent.getModelName();<a name="line.349"></a>
<FONT color="green">350</FONT> } catch (NullPointerException e) {<a name="line.350"></a>
<FONT color="green">351</FONT> throw new GuideException("The parent guide model cannot be found. ", e);<a name="line.351"></a>
<FONT color="green">352</FONT> }<a name="line.352"></a>
<FONT color="green">353</FONT> }<a name="line.353"></a>
<FONT color="green">354</FONT> <a name="line.354"></a>
<FONT color="green">355</FONT> /**<a name="line.355"></a>
<FONT color="green">356</FONT> * Returns the "sum-up" or master feature vector<a name="line.356"></a>
<FONT color="green">357</FONT> * <a name="line.357"></a>
<FONT color="green">358</FONT> * @return a feature vector object<a name="line.358"></a>
<FONT color="green">359</FONT> */<a name="line.359"></a>
<FONT color="green">360</FONT> public FeatureVector getMasterFeatureVector() {<a name="line.360"></a>
<FONT color="green">361</FONT> return masterFeatureVector;<a name="line.361"></a>
<FONT color="green">362</FONT> }<a name="line.362"></a>
<FONT color="green">363</FONT> <a name="line.363"></a>
<FONT color="green">364</FONT> /**<a name="line.364"></a>
<FONT color="green">365</FONT> * Returns the divide feature vector<a name="line.365"></a>
<FONT color="green">366</FONT> * <a name="line.366"></a>
<FONT color="green">367</FONT> * @return a feature vector object<a name="line.367"></a>
<FONT color="green">368</FONT> */<a name="line.368"></a>
<FONT color="green">369</FONT> public FeatureVector getDivideFeatureVector() {<a name="line.369"></a>
<FONT color="green">370</FONT> return divideFeatureVector;<a name="line.370"></a>
<FONT color="green">371</FONT> }<a name="line.371"></a>
<FONT color="green">372</FONT> <a name="line.372"></a>
<FONT color="green">373</FONT> /**<a name="line.373"></a>
<FONT color="green">374</FONT> * Returns the frequency (number of instances)<a name="line.374"></a>
<FONT color="green">375</FONT> * <a name="line.375"></a>
<FONT color="green">376</FONT> * @return the frequency (number of instances)<a name="line.376"></a>
<FONT color="green">377</FONT> */<a name="line.377"></a>
<FONT color="green">378</FONT> public int getFrequency() {<a name="line.378"></a>
<FONT color="green">379</FONT> return frequency;<a name="line.379"></a>
<FONT color="green">380</FONT> }<a name="line.380"></a>
<FONT color="green">381</FONT> <a name="line.381"></a>
<FONT color="green">382</FONT> /**<a name="line.382"></a>
<FONT color="green">383</FONT> * Increase the frequency by 1<a name="line.383"></a>
<FONT color="green">384</FONT> */<a name="line.384"></a>
<FONT color="green">385</FONT> public void increaseFrequency() {<a name="line.385"></a>
<FONT color="green">386</FONT> if (parent instanceof InstanceModel) {<a name="line.386"></a>
<FONT color="green">387</FONT> ((InstanceModel)parent).increaseFrequency();<a name="line.387"></a>
<FONT color="green">388</FONT> }<a name="line.388"></a>
<FONT color="green">389</FONT> frequency++;<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> public void decreaseFrequency() {<a name="line.392"></a>
<FONT color="green">393</FONT> if (parent instanceof InstanceModel) {<a name="line.393"></a>
<FONT color="green">394</FONT> ((InstanceModel)parent).decreaseFrequency();<a name="line.394"></a>
<FONT color="green">395</FONT> }<a name="line.395"></a>
<FONT color="green">396</FONT> frequency--;<a name="line.396"></a>
<FONT color="green">397</FONT> }<a name="line.397"></a>
<FONT color="green">398</FONT> <a name="line.398"></a>
<FONT color="green">399</FONT> /**<a name="line.399"></a>
<FONT color="green">400</FONT> * Sets the frequency (number of instances)<a name="line.400"></a>
<FONT color="green">401</FONT> * <a name="line.401"></a>
<FONT color="green">402</FONT> * @param frequency (number of instances)<a name="line.402"></a>
<FONT color="green">403</FONT> */<a name="line.403"></a>
<FONT color="green">404</FONT> protected void setFrequency(int frequency) {<a name="line.404"></a>
<FONT color="green">405</FONT> this.frequency = frequency;<a name="line.405"></a>
<FONT color="green">406</FONT> }<a name="line.406"></a>
<FONT color="green">407</FONT> <a name="line.407"></a>
<FONT color="green">408</FONT> <a name="line.408"></a>
<FONT color="green">409</FONT> /* (non-Javadoc)<a name="line.409"></a>
<FONT color="green">410</FONT> * @see java.lang.Object#toString()<a name="line.410"></a>
<FONT color="green">411</FONT> */<a name="line.411"></a>
<FONT color="green">412</FONT> public String toString() {<a name="line.412"></a>
<FONT color="green">413</FONT> final StringBuilder sb = new StringBuilder();<a name="line.413"></a>
<FONT color="green">414</FONT> //TODO<a name="line.414"></a>
<FONT color="green">415</FONT> return sb.toString();<a name="line.415"></a>
<FONT color="green">416</FONT> }<a name="line.416"></a>
<FONT color="green">417</FONT> }<a name="line.417"></a>
</PRE>
</BODY>
</HTML>