func (c *SvmClassifier) TrainClassifier(trainDataSetFile1 string, trainDataSetFile2 string) error {
// Perform training
fmt.Println("Start Training")
start := time.Now()
// train the model
trainingData1, err := c.loadTrainDataSet(trainDataSetFile1, 2, 3)
if err != nil {
return err
}
trainingData2, err := c.loadTrainDataSet(trainDataSetFile2, 2, 3)
if err != nil {
return err
}
err = c.createBagOfWords(5, 800, trainingData1, trainingData2)
if err != nil {
return err
}
problem := gosvm.NewProblem()
// We use all features from the bagofWords
for _, val := range trainingData1 {
problem.Add(gosvm.TrainingInstance{float64(val.sentimentLabel), gosvm.FromDenseVector(c.createFeatureVector(val.text))})
}
for _, val := range trainingData2 {
problem.Add(gosvm.TrainingInstance{float64(val.sentimentLabel), gosvm.FromDenseVector(c.createFeatureVector(val.text))})
}
param := gosvm.DefaultParameters()
param.Kernel = gosvm.NewLinearKernel()
param.SVMType = gosvm.NewCSVC(0.1)
c.model, err = gosvm.TrainModel(param, problem)
if err != nil {
return err
}
elapsed := time.Now().Sub(start)
fmt.Println(elapsed)
fmt.Println("Training finished!")
err = c.model.Save("svm_model")
fmt.Println("Svm model saved!")
return err
}
func (c *SvmClassifier) TestClassifier(testDataSetFile string) error {
fmt.Println("Start Testing")
start := time.Now()
// test the model
testData, err := c.loadTestDataSet(testDataSetFile, 2, 3)
if err != nil {
return err
}
flailCounter := 0
counter := 0
for _, val := range testData {
label := c.model.Predict(gosvm.FromDenseVector(c.createFeatureVector(val.text)))
if int(label) != val.sentimentLabel {
flailCounter++
}
counter++
}
// print error rate
fmt.Println("Error:", float64(flailCounter)/float64(counter))
elapsed := time.Now().Sub(start)
fmt.Println(elapsed)
fmt.Println("Test finished!")
return nil
}
func (c *SvmClassifier) ClassifyTweet(tweet string) float64 {
label := c.model.Predict(gosvm.FromDenseVector(c.createFeatureVector(tweet)))
return label
}