def __init__(self, lexicon, C=1, num_features=100):
self.training_set = None
self.classes = None
self.test_set = None
self.results = None
self.kernel = ker.Linear()
self.C = C
self.feature_data = PATH + "/learning/stored/feature.data"
self.label_data = PATH + "/learning/stored/svm_label.data"
self.lexicon = lexicon
self.num_features = len(self.lexicon.words.keys())
try:
print "Loading existing SVM..."
features = pickle.load(open(self.feature_data))
labels = pickle.load(open(self.label_data))
sparsedata = SparseDataSet(features, L=labels)
self.svm_classifier = loadSVM(PATH + "/learning/stored/svm.classifier",sparsedata)
except Exception as e:
print e
print "Existing SVM not found!"
self.svm_classifier = svm.SVM(self.kernel)
self.accuracy = None
self.predicted_labels = None
score = featsel.FeatureScore('golub')
self.filter = featsel.Filter(score)
self.feature_selector = FeatureSelect(self.svm_classifier, self.filter)
self.chain = Chain([self.feature_selector, self.svm_classifier])
def train(self, trainSet_X, trainSet_Y):
trainSet_X = numpy.array(trainSet_X).astype(float)
trainSet_Y = numpy.array(trainSet_Y).astype(float)
labels = trainSet_Y.tolist()
samples = trainSet_X.tolist()
data = datafunc.VectorDataSet(samples, L=map(str,labels))
self.svm = svm.SVM(self.kernel, C=self.C)
self.svm.train(data)
self.trained=True
self.uniqueY = numpy.unique(labels)
self.nClasses = len(self.uniqueY)