/// <exception cref="System.Exception"/>
public static void Main(string[] args)
{
Properties props;
if (args.Length > 0)
{
props = StringUtils.ArgsToProperties(args);
}
else
{
props = new Properties();
}
if (!props.Contains("dcoref.conll2011"))
{
log.Info("-dcoref.conll2011 [input_CoNLL_corpus]: was not specified");
return;
}
if (!props.Contains("singleton.predictor.output"))
{
log.Info("-singleton.predictor.output [output_model_file]: was not specified");
return;
}
GeneralDataset <string, string> data = Edu.Stanford.Nlp.Coref.Misc.SingletonPredictor.GenerateFeatureVectors(props);
LogisticClassifier <string, string> classifier = Edu.Stanford.Nlp.Coref.Misc.SingletonPredictor.Train(data);
Edu.Stanford.Nlp.Coref.Misc.SingletonPredictor.SaveToSerialized(classifier, GetPathSingletonPredictor(props));
}
/// <summary>Train the singleton predictor using a logistic regression classifier.</summary>
/// <param name="pDataset">Dataset of features</param>
/// <returns>Singleton predictor</returns>
public static LogisticClassifier <string, string> Train(GeneralDataset <string, string> pDataset)
{
LogisticClassifierFactory <string, string> lcf = new LogisticClassifierFactory <string, string>();
LogisticClassifier <string, string> classifier = lcf.TrainClassifier(pDataset);
return(classifier);
}
private static void Main(string[] args)
{
Console.WriteLine("Укажите путь к файлу");
var path = Console.ReadLine();
Console.WriteLine("Укажите размерность прстранства");
var dimension =Convert.ToInt32(Console.ReadLine());
var ff = new FileFramework(@"E:\Users\Nikita\Documents\Visual Studio 2013\Projects\NSUBigData\LinearRegres\iris.csv", Convert.ToInt32(dimension));
Console.WriteLine("\nBegin Logistic Regression (binary) Classification demo");
Console.WriteLine("Goal is to demonstrate training using gradient descent");
var numFeatures = dimension-1;
var numRows = 100;
var seed = 1;
Console.WriteLine("\nGenerating " + numRows +
" artificial data items with " + numFeatures + " features");
var allData = ff.ParseFile();
Console.WriteLine("Creating train (80%) and test (20%) matrices");
double[][] trainData;
double[][] testData;
MakeTrainTest(allData, 0, out trainData, out testData);
Console.WriteLine("Done");
Console.WriteLine("\nTraining data: \n");
ShowData(trainData, 3, 2, true);
Console.WriteLine("\nTest data: \n");
ShowData(testData, 3, 2, true);
Console.WriteLine("Creating LR binary classifier");
var lc = new LogisticClassifier(numFeatures);
var maxEpochs = 1000;
Console.WriteLine("Setting maxEpochs = " + maxEpochs);
var alpha = 0.01;
Console.WriteLine("Setting learning rate = " + alpha.ToString("F2"));
Console.WriteLine("\nStarting training using (stochastic) gradient descent");
double[] weights = lc.Train(trainData, maxEpochs, alpha);
Console.WriteLine("Training complete");
Console.WriteLine("\nBest weights found:");
ShowVector(weights, 4, true);
double trainAcc = lc.Accuracy(trainData, weights);
Console.WriteLine("Prediction accuracy on training data = " +
trainAcc.ToString("F4"));
double testAcc = lc.Accuracy(testData, weights);
Console.WriteLine("Prediction accuracy on test data = " +
testAcc.ToString("F4"));
Console.WriteLine("\nEnd LR binary classification demo\n");
Console.ReadLine();
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.TypeLoadException"/>
public virtual ICounter <string> GetTopFeatures(IEnumerator <Pair <IDictionary <string, DataInstance>, File> > sentsf, double perSelectRand, double perSelectNeg, string externalFeatureWeightsFileLabel)
{
ICounter <string> features = new ClassicCounter <string>();
RVFDataset <string, string> dataset = new RVFDataset <string, string>();
Random r = new Random(10);
Random rneg = new Random(10);
int numrand = 0;
IList <Pair <string, int> > chosen = new List <Pair <string, int> >();
while (sentsf.MoveNext())
{
Pair <IDictionary <string, DataInstance>, File> sents = sentsf.Current;
numrand = this.Sample(sents.First(), r, rneg, perSelectNeg, perSelectRand, numrand, chosen, dataset);
}
/*if(batchProcessSents){
* for(File f: sentFiles){
* Map<String, List<CoreLabel>> sentsf = IOUtils.readObjectFromFile(f);
* numrand = this.sample(sentsf, r, rneg, perSelectNeg, perSelectRand, numrand, chosen, dataset);
* }
* }else
* numrand = this.sample(sents, r, rneg, perSelectNeg, perSelectRand, numrand, chosen, dataset);
*/
System.Console.Out.WriteLine("num random chosen: " + numrand);
System.Console.Out.WriteLine("Number of datums per label: " + dataset.NumDatumsPerLabel());
LogisticClassifierFactory <string, string> logfactory = new LogisticClassifierFactory <string, string>();
LogisticClassifier <string, string> classifier = logfactory.TrainClassifier(dataset);
ICounter <string> weights = classifier.WeightsAsCounter();
if (!classifier.GetLabelForInternalPositiveClass().Equals(answerLabel))
{
weights = Counters.Scale(weights, -1);
}
if (thresholdWeight != null)
{
HashSet <string> removeKeys = new HashSet <string>();
foreach (KeyValuePair <string, double> en in weights.EntrySet())
{
if (Math.Abs(en.Value) <= thresholdWeight)
{
removeKeys.Add(en.Key);
}
}
Counters.RemoveKeys(weights, removeKeys);
System.Console.Out.WriteLine("Removing " + removeKeys);
}
IOUtils.WriteStringToFile(Counters.ToSortedString(weights, weights.Size(), "%1$s:%2$f", "\n"), externalFeatureWeightsFileLabel, "utf8");
// getDecisionTree(sents, chosen, weights, wekaOptions);
return(features);
}
/// <summary>Saves the singleton predictor model to the given filename.</summary>
/// <remarks>
/// Saves the singleton predictor model to the given filename.
/// If there is an error, a RuntimeIOException is thrown.
/// </remarks>
private static void SaveToSerialized(LogisticClassifier <string, string> predictor, string filename)
{
try
{
log.Info("Writing singleton predictor in serialized format to file " + filename + ' ');
ObjectOutputStream @out = IOUtils.WriteStreamFromString(filename);
@out.WriteObject(predictor);
@out.Close();
log.Info("done.");
}
catch (IOException ioe)
{
throw new RuntimeIOException(ioe);
}
}
public void AndTest()
{
LogisticClassifier regr = new LogisticClassifier(2);
regr.AddSample(new double[] { 0, 0 }, 0);
regr.AddSample(new double[] { 0, 1 }, 0);
regr.AddSample(new double[] { 1, 0 }, 0);
regr.AddSample(new double[] { 1, 1 }, 1);
//regr.AddSample(new double[] { 1, 1 }, 1);
//regr.AddSample(new double[] { 1, 1 }, 1);
//regr.AddSample(new double[] { 1, 1 }, 1);
int times = 1000;
regr.Alpha = 3;
regr.Lambda = 0.01;
List <BinaryClassificationTrainResult> results = regr.Train(times);
for (int i = 0; i < times; i++)
{
if (i % 100 != 0)
{
continue;
}
Debug.Print(results[i].Cost.ToString());
for (int t = 0; t < results[i].Theta.Length; t++)
{
Debug.Print("\t" + results[i].Theta[t].ToString());
}
}
double[] h = new double[4];
h[0] = regr.H(new double[] { 1, 0, 0 });
h[1] = regr.H(new double[] { 1, 0, 1 });
h[2] = regr.H(new double[] { 1, 1, 0 });
h[3] = regr.H(new double[] { 1, 1, 1 });
for (int i = 0; i < 4; i++)
{
Debug.Print(h[i].ToString());
}
Assert.AreEqual(regr.Predict(new double[] { 0, 0 }), 0);
Assert.AreEqual(regr.Predict(new double[] { 0, 1 }), 0);
Assert.AreEqual(regr.Predict(new double[] { 1, 0 }), 0);
Assert.AreEqual(regr.Predict(new double[] { 1, 1 }), 1);
}
private static void Main(string[] args)
{
Console.WriteLine("Укажите путь к файлу");
var path = Console.ReadLine();
Console.WriteLine("Укажите размерность прстранства");
var dimension = Convert.ToInt32(Console.ReadLine());
var ff = new FileFramework(@"E:\Users\Nikita\Documents\Visual Studio 2013\Projects\NSUBigData\LinearRegres\iris.csv", Convert.ToInt32(dimension));
Console.WriteLine("\nBegin Logistic Regression (binary) Classification demo");
Console.WriteLine("Goal is to demonstrate training using gradient descent");
var numFeatures = dimension - 1;
var numRows = 100;
var seed = 1;
Console.WriteLine("\nGenerating " + numRows +
" artificial data items with " + numFeatures + " features");
var allData = ff.ParseFile();
Console.WriteLine("Creating train (80%) and test (20%) matrices");
double[][] trainData;
double[][] testData;
MakeTrainTest(allData, 0, out trainData, out testData);
Console.WriteLine("Done");
Console.WriteLine("\nTraining data: \n");
ShowData(trainData, 3, 2, true);
Console.WriteLine("\nTest data: \n");
ShowData(testData, 3, 2, true);
Console.WriteLine("Creating LR binary classifier");
var lc = new LogisticClassifier(numFeatures);
var maxEpochs = 1000;
Console.WriteLine("Setting maxEpochs = " + maxEpochs);
var alpha = 0.01;
Console.WriteLine("Setting learning rate = " + alpha.ToString("F2"));
Console.WriteLine("\nStarting training using (stochastic) gradient descent");
double[] weights = lc.Train(trainData, maxEpochs, alpha);
Console.WriteLine("Training complete");
Console.WriteLine("\nBest weights found:");
ShowVector(weights, 4, true);
double trainAcc = lc.Accuracy(trainData, weights);
Console.WriteLine("Prediction accuracy on training data = " +
trainAcc.ToString("F4"));
double testAcc = lc.Accuracy(testData, weights);
Console.WriteLine("Prediction accuracy on test data = " +
testAcc.ToString("F4"));
Console.WriteLine("\nEnd LR binary classification demo\n");
Console.ReadLine();
}
/// <exception cref="System.Exception"/>
public CoNLLMentionExtractor(Dictionaries dict, Properties props, Semantics semantics, LogisticClassifier <string, string> singletonModel)
: this(dict, props, semantics)
{
singletonPredictor = singletonModel;
}
