SVMWrapper

class pyopenms.SVMWrapper

Bases: object

Cython implementation of _SVMWrapper

Original C++ documentation is available here

__init__()

Overload:

__init__(self) → None

Overload:

__init__(self, in_0: SVMWrapper) → None

Methods

__init__	Overload:
calculateGaussTable(self, border_length, ...)
createRandomPartitions(self, problem, ...)
getDoubleParameter(self, type_)
getIntParameter(self, type_)
getPValue(self, sigma1, sigma2, point)
getSVRProbability(self)
getSignificanceBorders(self, data, sigmas, ...)
loadModel(self, modelFilename)	The svm-model is loaded.
mergePartitions(self, problems, except_, ...)
predict(self, problem, results)	The prediction process is started and the results are stored in 'predicted_labels'
saveModel(self, modelFilename)	The model of the trained svm is saved into 'modelFilename'
setParameter	Overload:
setTrainingSample(self, training_sample)
setWeights(self, weight_labels, weights)
train(self, problem)	The svm is trained with the data stored in the 'svm_problem' structure

SVM_kernel_type

alias of pyopenms._pyopenms_4.__SVM_kernel_type

SVM_parameter_type

alias of pyopenms._pyopenms_4.__SVM_parameter_type

calculateGaussTable(self, border_length: int, sigma: float, gauss_table: List[float]) → None

createRandomPartitions(self, problem: SVMData, number: int, problems: List[SVMData]) → None

getDoubleParameter(self, type_: int) → float

getIntParameter(self, type_: int) → int

getPValue(self, sigma1: float, sigma2: float, point: List[float, float]) → float

getSVRProbability(self) → float

getSignificanceBorders(self, data: SVMData, sigmas: List[float, float], confidence: float, number_of_runs: int, number_of_partitions: int, step_size: float, max_iterations: int) → None

loadModel(self, modelFilename: Union[bytes, str, String]) → None

The svm-model is loaded. After this, the svm is ready for prediction

mergePartitions(self, problems: List[SVMData], except_: int, merged_problem: SVMData) → None

predict(self, problem: SVMData, results: List[float]) → None

The prediction process is started and the results are stored in ‘predicted_labels’

saveModel(self, modelFilename: Union[bytes, str, String]) → None

The model of the trained svm is saved into ‘modelFilename’

setParameter()

Overload:

setParameter(self, type_: int, value: int) → None

Overload:

setParameter(self, type_: int, value: float) → None

setTrainingSample(self, training_sample: SVMData) → None

setWeights(self, weight_labels: List[int], weights: List[float]) → None

train(self, problem: SVMData) → int

The svm is trained with the data stored in the ‘svm_problem’ structure