/// <summary>Get the sentiment of a sentence.</summary>
/// <param name="sentence">
/// The sentence as a core map.
/// POS tags and Lemmas are a prerequisite.
/// See
/// <see cref="Edu.Stanford.Nlp.Ling.CoreAnnotations.PartOfSpeechAnnotation"/>
/// and
/// <see cref="Edu.Stanford.Nlp.Ling.CoreAnnotations.LemmaAnnotation"/>
/// .
/// </param>
/// <returns>The sentiment class of this sentence.</returns>
public virtual SentimentClass Classify(ICoreMap sentence)
{
ICounter <string> features = Featurize(sentence);
RVFDatum <SentimentClass, string> datum = new RVFDatum <SentimentClass, string>(features);
return(impl.ClassOf(datum));
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.TypeLoadException"/>
private static void DemonstrateSerialization()
{
System.Console.Out.WriteLine();
System.Console.Out.WriteLine("Demonstrating working with a serialized classifier");
ColumnDataClassifier cdc = new ColumnDataClassifier(where + "examples/cheese2007.prop");
IClassifier <string, string> cl = cdc.MakeClassifier(cdc.ReadTrainingExamples(where + "examples/cheeseDisease.train"));
// Exhibit serialization and deserialization working. Serialized to bytes in memory for simplicity
System.Console.Out.WriteLine();
ByteArrayOutputStream baos = new ByteArrayOutputStream();
ObjectOutputStream oos = new ObjectOutputStream(baos);
oos.WriteObject(cl);
oos.Close();
byte[] @object = baos.ToByteArray();
ByteArrayInputStream bais = new ByteArrayInputStream(@object);
ObjectInputStream ois = new ObjectInputStream(bais);
LinearClassifier <string, string> lc = ErasureUtils.UncheckedCast(ois.ReadObject());
ois.Close();
ColumnDataClassifier cdc2 = new ColumnDataClassifier(where + "examples/cheese2007.prop");
// We compare the output of the deserialized classifier lc versus the original one cl
// For both we use a ColumnDataClassifier to convert text lines to examples
System.Console.Out.WriteLine();
System.Console.Out.WriteLine("Making predictions with both classifiers");
foreach (string line in ObjectBank.GetLineIterator(where + "examples/cheeseDisease.test", "utf-8"))
{
IDatum <string, string> d = cdc.MakeDatumFromLine(line);
IDatum <string, string> d2 = cdc2.MakeDatumFromLine(line);
System.Console.Out.Printf("%s =origi=> %s (%.4f)%n", line, cl.ClassOf(d), cl.ScoresOf(d).GetCount(cl.ClassOf(d)));
System.Console.Out.Printf("%s =deser=> %s (%.4f)%n", line, lc.ClassOf(d2), lc.ScoresOf(d).GetCount(lc.ClassOf(d)));
}
}
public virtual double Score <F>(IClassifier <L, F> classifier, GeneralDataset <L, F> data)
{
IList <L> guesses = new List <L>();
IList <L> labels = new List <L>();
for (int i = 0; i < data.Size(); i++)
{
IDatum <L, F> d = data.GetRVFDatum(i);
L guess = classifier.ClassOf(d);
guesses.Add(guess);
}
int[] labelsArr = data.GetLabelsArray();
labelIndex = data.labelIndex;
for (int i_1 = 0; i_1 < data.Size(); i_1++)
{
labels.Add(labelIndex.Get(labelsArr[i_1]));
}
labelIndex = new HashIndex <L>();
labelIndex.AddAll(data.LabelIndex().ObjectsList());
labelIndex.AddAll(classifier.Labels());
int numClasses = labelIndex.Size();
tpCount = new int[numClasses];
fpCount = new int[numClasses];
fnCount = new int[numClasses];
negIndex = labelIndex.IndexOf(negLabel);
for (int i_2 = 0; i_2 < guesses.Count; ++i_2)
{
L guess = guesses[i_2];
int guessIndex = labelIndex.IndexOf(guess);
L label = labels[i_2];
int trueIndex = labelIndex.IndexOf(label);
if (guessIndex == trueIndex)
{
if (guessIndex != negIndex)
{
tpCount[guessIndex]++;
}
}
else
{
if (guessIndex != negIndex)
{
fpCount[guessIndex]++;
}
if (trueIndex != negIndex)
{
fnCount[trueIndex]++;
}
}
}
return(GetFMeasure());
}
public override double Score <F>(IClassifier <L, F> classifier, GeneralDataset <L, F> data)
{
labelIndex = new HashIndex <L>();
labelIndex.AddAll(classifier.Labels());
labelIndex.AddAll(data.labelIndex.ObjectsList());
ClearCounts();
int[] labelsArr = data.GetLabelsArray();
for (int i = 0; i < data.Size(); i++)
{
IDatum <L, F> d = data.GetRVFDatum(i);
L guess = classifier.ClassOf(d);
AddGuess(guess, labelIndex.Get(labelsArr[i]));
}
FinalizeCounts();
return(GetFMeasure());
}
public PrecisionRecallStats(IClassifier <L, F> classifier, Dataset <L, F> data, L positiveClass)
{
for (int i = 0; i < data.Size(); ++i)
{
IDatum <L, F> d = data.GetDatum(i);
L guess = classifier.ClassOf(d);
L label = d.Label();
bool guessPositive = guess.Equals(positiveClass);
bool isPositive = label.Equals(positiveClass);
if (isPositive && guessPositive)
{
tpCount++;
}
if (isPositive && !guessPositive)
{
fnCount++;
}
if (!isPositive && guessPositive)
{
fpCount++;
}
}
}