def trainSVM():
svm = ml.SVM_create()
svm.setType(ml.SVM_C_SVC)
svm.setKernel(ml.SVM_RBF)
td = ml.TrainData_create(trainData, ml.ROW_SAMPLE, np.array(trainLabels))
# svm.train(td)
svm.trainAuto(trainData, ml.ROW_SAMPLE, np.array(trainLabels))
svm.save("../svm_data.yaml")
return svm
def __init__(self,
type=ml.SVM_C_SVC,
kernel=ml.SVM_LINEAR,
c=2.,
gamma=1.,
nu=0.5,
degree=1):
self.model = ml.SVM_create()
self.model.setType(type)
self.model.setKernel(kernel)
self.model.setC(c)
self.model.setGamma(gamma)
self.model.setNu(nu)
self.model.setDegree(degree)
print(len(classes[classes == 'Class 4']))
print(len(classes[classes == 'Class 5']))
print(len(classes[classes == 'Class 6']))
print(len(classes[classes == 'Class 7']))
for x, y in enumerate(base):
oDataSet.add_sample_of_attribute(
np.array(list(np.float32(y)) + [classes[x]]))
oDataSet.attributes = oDataSet.attributes.astype(float)
oDataSet.normalize_data_set()
for j in range(50):
print(j)
oData = Data(7, 11, samples=47)
oData.random_training_test_by_percent([352, 382, 378, 382, 376, 360, 361],
0.8)
svm = ml.SVM_create()
svm.setKernel(ml.SVM_RBF)
oData.params = dict(kernel=ml.SVM_RBF, kFold=10)
svm.trainAuto(np.float32(oDataSet.attributes[oData.Training_indexes]),
ml.ROW_SAMPLE,
np.int32(oDataSet.labels[oData.Training_indexes]),
kFold=10)
# svm.train_auto(np.float32(oDataSet.attributes[oData.Training_indexes]),
# np.float32(oDataSet.labels[oData.Training_indexes]), None, None, params=oData.params)
results = [
] # svm.predict_all(np.float32(oDataSet.attributes[oData.Testing_indexes]))
for i in (oDataSet.attributes[oData.Testing_indexes]):
res, cls = svm.predict(np.float32([i]))
results.append(cls[0])
oData.set_results_from_classifier(results,
oDataSet.labels[oData.Testing_indexes])
