Drivers folder containing driver classes that inherit from SAMDriver to implement custom functionality. More...

Collaboration diagram for SAM Drivers:

Namespaces
	SAM.SAM_Core.samOptimiser

Classes
class	SAM.SAM_Core.SAMDriver.SAMDriver
	SAM Driver parent class that defines the methods by which models are initialised, trained and saved. More...

class	SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin
	Class developed for the implementation of windowed real time action recognition. More...

class	SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction
	Class developed for the implementation of face recognition. More...

Functions
def	SAM.SAM_Core.SAMDriver.SAMDriver.__init__ (self)
	Initialisation for SAMDriver. More...

def	SAM.SAM_Core.SAMDriver.SAMDriver.loadParameters (self, parser, trainName)
	Function to load parameters from the model config.ini file. More...

def	SAM.SAM_Core.SAMDriver.SAMDriver.saveParameters (self)
	Method to store variables generated during training which are required during interaction in self.paramsDict. More...

def	SAM.SAM_Core.SAMDriver.SAMDriver.testPerformance (self, testModel, Yall, Lall, YtestAll, LtestAll, verbose)
	Method for testing the whole dataset for overall performance. More...

def	SAM.SAM_Core.SAMDriver.SAMDriver.training (self, modelNumInducing, modelNumIterations, modelInitIterations, fname, save_model, economy_save, keepIfPresent=True, kernelStr=None)
	Method to train, store and load the learned model. More...

def	SAM.SAM_Core.SAMDriver.SAMDriver.prepareData (self, model='mrd', Ntr=50, randSeed=0, normalise=True)
	Method for randomly splitting data and preparing Y dictionary. More...

def	SAM.SAM_Core.SAMDriver.SAMDriver.readData (self, root_data_dir, participant_index, args, kw)
	Method which accepts a data directory, reads all the data in and outputs self.Y which is a numpy array with n instances of m length feature vectors and self.L which is a list of text Labels of length n. More...

def	SAM.SAM_Core.SAMDriver.SAMDriver.processLiveData (self, dataList, thisModel, verbose=False)
	Method which receives a list of data frames and outputs a classification if available or 'no_classification' if it is not. More...

def	SAM.SAM_Core.SAMDriver.SAMDriver.formatGeneratedData (self, instance)
	Method which receives an instance generated from a model via a label and formats the received vector by reshaping it or adding crucial data with it for it to be deciphered at the receiving end. More...

Variables
	SAM.SAM_Core.SAMDriver.SAMDriver.SAMObject

	SAM.SAM_Core.SAMDriver.SAMDriver.Y

	SAM.SAM_Core.SAMDriver.SAMDriver.L

	SAM.SAM_Core.SAMDriver.SAMDriver.X

	SAM.SAM_Core.SAMDriver.SAMDriver.Ytest

	SAM.SAM_Core.SAMDriver.SAMDriver.Ltest

	SAM.SAM_Core.SAMDriver.SAMDriver.Ytestn

	SAM.SAM_Core.SAMDriver.SAMDriver.Ltestn

	SAM.SAM_Core.SAMDriver.SAMDriver.Ymean

	SAM.SAM_Core.SAMDriver.SAMDriver.Ystd

	SAM.SAM_Core.SAMDriver.SAMDriver.Yn

	SAM.SAM_Core.SAMDriver.SAMDriver.Ln

	SAM.SAM_Core.SAMDriver.SAMDriver.segTrainConf

	SAM.SAM_Core.SAMDriver.SAMDriver.segTrainPerc

	SAM.SAM_Core.SAMDriver.SAMDriver.segTestConf

	SAM.SAM_Core.SAMDriver.SAMDriver.segTestPerc

	SAM.SAM_Core.SAMDriver.SAMDriver.data_labels

	SAM.SAM_Core.SAMDriver.SAMDriver.paramsDict

	SAM.SAM_Core.SAMDriver.SAMDriver.verbose

	SAM.SAM_Core.SAMDriver.SAMDriver.model_mode

	SAM.SAM_Core.SAMDriver.SAMDriver.Quser

	SAM.SAM_Core.SAMDriver.SAMDriver.listOfModels

	SAM.SAM_Core.SAMDriver.SAMDriver.model_type

	SAM.SAM_Core.SAMDriver.SAMDriver.modelLabel

	SAM.SAM_Core.SAMDriver.SAMDriver.textLabels

	SAM.SAM_Core.SAMDriver.SAMDriver.participantList

	SAM.SAM_Core.SAMDriver.SAMDriver.varianceThreshold

	SAM.SAM_Core.SAMDriver.SAMDriver.fname

	SAM.SAM_Core.SAMDriver.SAMDriver.optimiseRecall

	SAM.SAM_Core.SAMDriver.SAMDriver.modelLoaded

	SAM.SAM_Core.SAMDriver.SAMDriver.parallelOperation

	SAM.SAM_Core.SAMDriver.SAMDriver.calibrated

	SAM.SAM_Core.SAMDriver.SAMDriver.rawTextData

	SAM.SAM_Core.SAMDriver.SAMDriver.rawData

	SAM.SAM_Core.SAMDriver.SAMDriver.Yall

	SAM.SAM_Core.SAMDriver.SAMDriver.Lall

	SAM.SAM_Core.SAMDriver.SAMDriver.YtestAll

	SAM.SAM_Core.SAMDriver.SAMDriver.LtestAll

	SAM.SAM_Core.SAMDriver.SAMDriver.classifiers

	SAM.SAM_Core.SAMDriver.SAMDriver.classif_thresh

	SAM.SAM_Core.SAMDriver.SAMDriver.model_num_inducing

	SAM.SAM_Core.SAMDriver.SAMDriver.model_num_iterations

	SAM.SAM_Core.SAMDriver.SAMDriver.model_init_iterations

	SAM.SAM_Core.SAMDriver.SAMDriver.additionalParametersList

Detailed Description

Drivers folder containing driver classes that inherit from SAMDriver to implement custom functionality.

Class Documentation

◆ SAM::SAM_Core::SAMDriver::SAMDriver

class SAM::SAM_Core::SAMDriver::SAMDriver

SAM Driver parent class that defines the methods by which models are initialised, trained and saved.

Definition at line 35 of file SAMDriver.py.

Inheritance diagram for SAM.SAM_Core.SAMDriver.SAMDriver:

Public Member Functions
def	__init__ (self)
	Initialisation for SAMDriver. More...

def	loadParameters (self, parser, trainName)
	Function to load parameters from the model config.ini file. More...

def	saveParameters (self)
	Method to store variables generated during training which are required during interaction in self.paramsDict. More...

def	testPerformance (self, testModel, Yall, Lall, YtestAll, LtestAll, verbose)
	Method for testing the whole dataset for overall performance. More...

def	training (self, modelNumInducing, modelNumIterations, modelInitIterations, fname, save_model, economy_save, keepIfPresent=True, kernelStr=None)
	Method to train, store and load the learned model. More...

def	prepareData (self, model='mrd', Ntr=50, randSeed=0, normalise=True)
	Method for randomly splitting data and preparing Y dictionary. More...

def	readData (self, root_data_dir, participant_index, args, kw)
	Method which accepts a data directory, reads all the data in and outputs self.Y which is a numpy array with n instances of m length feature vectors and self.L which is a list of text Labels of length n. More...

def	processLiveData (self, dataList, thisModel, verbose=False)
	Method which receives a list of data frames and outputs a classification if available or 'no_classification' if it is not. More...

def	formatGeneratedData (self, instance)
	Method which receives an instance generated from a model via a label and formats the received vector by reshaping it or adding crucial data with it for it to be deciphered at the receiving end. More...

Public Attributes
	SAMObject

	Y

	L

	X

	Ytest

	Ltest

	Ytestn

	Ltestn

	Ymean

	Ystd

	Yn

	Ln

	segTrainConf

	segTrainPerc

	segTestConf

	segTestPerc

	data_labels

	paramsDict

	verbose

	model_mode

	Quser

	listOfModels

	model_type

	modelLabel

	textLabels

	participantList

	varianceThreshold

	fname

	optimiseRecall

	modelLoaded

	parallelOperation

	calibrated

	rawTextData

	rawData

	Yall

	Lall

	YtestAll

	LtestAll

	classifiers

	classif_thresh

	model_num_inducing

	model_num_iterations

	model_init_iterations

	additionalParametersList

◆ SAM::SAM_Drivers::SAMDriver_ARWin::SAMDriver_ARWin

class SAM::SAM_Drivers::SAMDriver_ARWin::SAMDriver_ARWin

Class developed for the implementation of windowed real time action recognition.

Definition at line 28 of file SAMDriver_ARWin.py.

Inheritance diagram for SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin:

Public Member Functions
def	__init__ (self)
	Initialise class using SAMDriver.__init__ and augment with custom parameters. More...

def	loadParameters (self, parser, trainName)
	Function to load parameters from the model config.ini file. More...

def	saveParameters (self)
	Override SAMDriver.saveParameters. More...

def	testPerformance (self, testModel, Yall, Lall, YtestAll, LtestAll, verbose)
	Custom testPerformance method. More...

def	diskDataToLiveData (self, root_data_dir)
	This method reads in time series data from disk for SAMDriver_ARWin. More...

def	convertToDict (self, rawData, mode, verbose)
	Convert list of strings time series to dictionary with joints and objects as different items of the dictionary and windows of positions for each joint. More...

def	readData (self, root_data_dir, participant_index, args, kw)
	Method which accepts a data directory, reads all the data in and outputs self.Y which is a numpy array with n instances of m length feature vectors and self.L which is a list of text Labels of length n. More...

def	listOfClassificationVectors (self, featureSequence, objectsList, partnerName='partner')
	Constructs a list of classifications to carry out. More...

def	messageChecker (self, dataMessage, mode)
	Method to check validity of incoming messages and split into components if valid. More...

def	processLiveData (self, dataList, thisModel, verbose=False, returnUnknown=False, printClass=True, additionalData=dict())
	Method which receives a list of data frames and outputs a classification if available or 'no_classification' if it is not. More...

Public Member Functions inherited from SAM.SAM_Core.SAMDriver.SAMDriver
def	__init__ (self)
	Initialisation for SAMDriver. More...

def	loadParameters (self, parser, trainName)
	Function to load parameters from the model config.ini file. More...

def	saveParameters (self)
	Method to store variables generated during training which are required during interaction in self.paramsDict. More...

def	testPerformance (self, testModel, Yall, Lall, YtestAll, LtestAll, verbose)
	Method for testing the whole dataset for overall performance. More...

def	training (self, modelNumInducing, modelNumIterations, modelInitIterations, fname, save_model, economy_save, keepIfPresent=True, kernelStr=None)
	Method to train, store and load the learned model. More...

def	prepareData (self, model='mrd', Ntr=50, randSeed=0, normalise=True)
	Method for randomly splitting data and preparing Y dictionary. More...

def	readData (self, root_data_dir, participant_index, args, kw)
	Method which accepts a data directory, reads all the data in and outputs self.Y which is a numpy array with n instances of m length feature vectors and self.L which is a list of text Labels of length n. More...

def	processLiveData (self, dataList, thisModel, verbose=False)
	Method which receives a list of data frames and outputs a classification if available or 'no_classification' if it is not. More...

def	formatGeneratedData (self, instance)
	Method which receives an instance generated from a model via a label and formats the received vector by reshaping it or adding crucial data with it for it to be deciphered at the receiving end. More...

Public Attributes
	data

	numJoints

	dataLogList

	labelsLogList

	itemsPerJoint

	featureSequence

	handsCombined

	data2Labels

	dataVec

	allDataDict

	listOfVectorsToClassify

	seqTestConf

	seqTestPerc

	additionalParametersList

	rawTextData

	Y

	L

Public Attributes inherited from SAM.SAM_Core.SAMDriver.SAMDriver
	SAMObject

	Y

	L

	X

	Ytest

	Ltest

	Ytestn

	Ltestn

	Ymean

	Ystd

	Yn

	Ln

	segTrainConf

	segTrainPerc

	segTestConf

	segTestPerc

	data_labels

	paramsDict

	verbose

	model_mode

	Quser

	listOfModels

	model_type

	modelLabel

	textLabels

	participantList

	varianceThreshold

	fname

	optimiseRecall

	modelLoaded

	parallelOperation

	calibrated

	rawTextData

	rawData

	Yall

	Lall

	YtestAll

	LtestAll

	classifiers

	classif_thresh

	model_num_inducing

	model_num_iterations

	model_init_iterations

	additionalParametersList

Constructor & Destructor Documentation

◆ init()

def SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.__init__ ( self )

Initialise class using SAMDriver.__init__ and augment with custom parameters.

additionalParameterList is a list of extra parameters to preserve between training and interaction.

Definition at line 34 of file SAMDriver_ARWin.py.

Member Function Documentation

◆ convertToDict()

def SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.convertToDict	(	self,
		rawData,
		mode,
		verbose
	)

Convert list of strings time series to dictionary with joints and objects as different items of the dictionary and windows of positions for each joint.

Parameters

rawData	List of strings read in from files.
mode	`'testing'` or `'live'`. `'testing'` will format strings read from file. `'live'` will format strings received via Yarp during interaction.
verbose	Switch logging to stdout on or off.

Returns: Dictionary with the windowed data, list of joints present in dictionary items, list of objects present in dictionary items.

Definition at line 272 of file SAMDriver_ARWin.py.

◆ diskDataToLiveData()

def SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.diskDataToLiveData	(	self,
		root_data_dir
	)

This method reads in time series data from disk for SAMDriver_ARWin.

Returns: list of strings with raw data and list of strings with ground truth classifications.

Definition at line 198 of file SAMDriver_ARWin.py.

◆ listOfClassificationVectors()

def SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.listOfClassificationVectors	(	self,
		featureSequence,
		objectsList,
		partnerName = `'partner'`
	)

Constructs a list of classifications to carry out.

Consider an example where featureSequence consists of `object', 'hand', 'head'. Assuming there are 2 objects in the scene, this method constructs 4 possible vectors to classify.
1) object1, rightHand, head
2) object1, leftHand, head
3) object2, rightHand, head
4) object2, leftHand, head

Parameters

featureSequence	Organisation of features within the feature vector.
objectsList	List of objects currently in the scene.
partnerName	Object name to ignore. This ignores the motion of the interacting agent.

Returns: List of vectors to classify.

Definition at line 763 of file SAMDriver_ARWin.py.

◆ loadParameters()

def SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.loadParameters	(	self,
		parser,
		trainName
	)

Function to load parameters from the model config.ini file.

Method to load parameters from file loaded in parser from within section trainName and store these parameters in self.paramsDict.

Parameters

parser	SafeConfigParser with pre-read config file.
trainName	Section from which parameters are to be read.

Returns: None

Definition at line 65 of file SAMDriver_ARWin.py.

◆ messageChecker()

def SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.messageChecker	(	self,
		dataMessage,
		mode
	)

Method to check validity of incoming messages and split into components if valid.

Parameters

dataMessage	String message to validate.
mode	Mode of validation. Either `'test'` or `'live'`.

Returns: List of strings with split sections and a boolean indicating validity of received string.

Definition at line 800 of file SAMDriver_ARWin.py.

◆ processLiveData()

def SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.processLiveData	(	self,
		dataList,
		thisModel,
		verbose = `False`,
		returnUnknown = `False`,
		printClass = `True`,
		additionalData = `dict()`
	)

Method which receives a list of data frames and outputs a classification if available or 'no_classification' if it is not.

Parameters

dataList	List of dataFrames collected. Length of list is variable.
thisModel	List of models required for testing.
verbose	Boolean turning logging to stdout on or off.
returnUnknown	Boolean to turn on or off the return a sentence if the classification is unknown.
printClass	Boolean to turn on or off logging of classification to stdout.
additionalData	Dictionary containing additional data required for classification to occur.

Returns: String with result of classification, likelihood of the classification, and list of frames with the latest x number of frames popped where x is the window length of the model. Classification result can be string 'None' if the classification is unknown or message is invalid or None if a different error occurs.

Definition at line 851 of file SAMDriver_ARWin.py.

◆ readData()

def SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.readData	(	self,
		root_data_dir,
		participant_index,
		args,
		kw
	)

Method which accepts a data directory, reads all the data in and outputs self.Y which is a numpy array with n instances of m length feature vectors and self.L which is a list of text Labels of length n.

This method reads data<number>.log files and the corresponding labels<number>.log files present in the root_data_dir and formats the time series data into normalised and smoothed windows. Subsequently depending on the list of joints chosen by the user and other parameters set in the config file present in the root_data_dir, the information of the different joints and objects are appended into a single feature vector. Number of feature vectors is equal to the number of windows extracted from the time series data.

Parameters

root_data_dir	Data directory.
participant_index	List of subfolders to consider. Can be left as an empty list.

Returns: None

Definition at line 417 of file SAMDriver_ARWin.py.

◆ saveParameters()

def SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.saveParameters ( self )

Override SAMDriver.saveParameters.

This function adds items of additionalParametersList to paramsDict to be saved.

Definition at line 153 of file SAMDriver_ARWin.py.

◆ testPerformance()

def SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.testPerformance	(	self,
		testModel,
		Yall,
		Lall,
		YtestAll,
		LtestAll,
		verbose
	)

Custom testPerformance method.

This augments the standard testPerformance method by including testing of known and unknown together with testing on known training points and known testing points.

Parameters

testModel	SAMObject Model to be tested.
Yall	Numpy array with training data vectors to be tested.
Lall	List with corresponding training data labels.
YtestAll	Numpy array with testing data vectors to be tested.
LtestAll	List with corresponding testing data labels.
verbose	Boolean turning logging to stdout on or off.

Returns: Square numpy array confusion matrix.

Definition at line 176 of file SAMDriver_ARWin.py.

Member Data Documentation

◆ additionalParametersList

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.additionalParametersList

Definition at line 49 of file SAMDriver_ARWin.py.

◆ allDataDict

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.allDataDict

Definition at line 45 of file SAMDriver_ARWin.py.

◆ data

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.data

Definition at line 36 of file SAMDriver_ARWin.py.

◆ data2Labels

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.data2Labels

Definition at line 43 of file SAMDriver_ARWin.py.

◆ dataLogList

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.dataLogList

Definition at line 38 of file SAMDriver_ARWin.py.

◆ dataVec

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.dataVec

Definition at line 44 of file SAMDriver_ARWin.py.

◆ featureSequence

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.featureSequence

Definition at line 41 of file SAMDriver_ARWin.py.

◆ handsCombined

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.handsCombined

Definition at line 42 of file SAMDriver_ARWin.py.

◆ itemsPerJoint

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.itemsPerJoint

Definition at line 40 of file SAMDriver_ARWin.py.

◆ L

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.L

Definition at line 740 of file SAMDriver_ARWin.py.

◆ labelsLogList

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.labelsLogList

Definition at line 39 of file SAMDriver_ARWin.py.

◆ listOfVectorsToClassify

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.listOfVectorsToClassify

Definition at line 46 of file SAMDriver_ARWin.py.

◆ numJoints

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.numJoints

Definition at line 37 of file SAMDriver_ARWin.py.

◆ rawTextData

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.rawTextData

Definition at line 208 of file SAMDriver_ARWin.py.

◆ seqTestConf

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.seqTestConf

Definition at line 47 of file SAMDriver_ARWin.py.

◆ seqTestPerc

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.seqTestPerc

Definition at line 48 of file SAMDriver_ARWin.py.

◆ Y

SAM.SAM_Drivers.SAMDriver_ARWin.SAMDriver_ARWin.Y

Definition at line 739 of file SAMDriver_ARWin.py.

◆ SAM::SAM_Drivers::SAMDriver_interaction::SAMDriver_interaction

class SAM::SAM_Drivers::SAMDriver_interaction::SAMDriver_interaction

Class developed for the implementation of face recognition.

Definition at line 26 of file SAMDriver_interaction.py.

Inheritance diagram for SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction:

Public Member Functions
def	__init__ (self)
	Initialise class using SAMDriver.__init__ and augment with custom parameters. More...

def	loadParameters (self, parser, trainName)
	Function to load parameters from the model config.ini file. More...

def	saveParameters (self)
	Executes SAMDriver.saveParameters to save default parameters. More...

def	readData (self, root_data_dir, participant_index, args, kw)
	Method which accepts a data directory, reads all the data in and outputs self.Y which is a numpy array with n instances of m length feature vectors and self.L which is a list of text Labels of length n. More...

def	processLiveData (self, dataList, thisModel, verbose, additionalData=dict())
	Method which receives a list of data frames and outputs a classification if available or 'no_classification' if it is not. More...

def	formatGeneratedData (self, instance)
	Method to transform a generated instance from the model into a Yarp formatted output. More...

Public Member Functions inherited from SAM.SAM_Core.SAMDriver.SAMDriver
def	__init__ (self)
	Initialisation for SAMDriver. More...

def	loadParameters (self, parser, trainName)
	Function to load parameters from the model config.ini file. More...

def	saveParameters (self)
	Method to store variables generated during training which are required during interaction in self.paramsDict. More...

def	testPerformance (self, testModel, Yall, Lall, YtestAll, LtestAll, verbose)
	Method for testing the whole dataset for overall performance. More...

def	training (self, modelNumInducing, modelNumIterations, modelInitIterations, fname, save_model, economy_save, keepIfPresent=True, kernelStr=None)
	Method to train, store and load the learned model. More...

def	prepareData (self, model='mrd', Ntr=50, randSeed=0, normalise=True)
	Method for randomly splitting data and preparing Y dictionary. More...

def	readData (self, root_data_dir, participant_index, args, kw)
	Method which accepts a data directory, reads all the data in and outputs self.Y which is a numpy array with n instances of m length feature vectors and self.L which is a list of text Labels of length n. More...

def	processLiveData (self, dataList, thisModel, verbose=False)
	Method which receives a list of data frames and outputs a classification if available or 'no_classification' if it is not. More...

def	formatGeneratedData (self, instance)
	Method which receives an instance generated from a model via a label and formats the received vector by reshaping it or adding crucial data with it for it to be deciphered at the receiving end. More...

Public Attributes
	additionalParametersList

	Y

	L

Public Attributes inherited from SAM.SAM_Core.SAMDriver.SAMDriver
	SAMObject

	Y

	L

	X

	Ytest

	Ltest

	Ytestn

	Ltestn

	Ymean

	Ystd

	Yn

	Ln

	segTrainConf

	segTrainPerc

	segTestConf

	segTestPerc

	data_labels

	paramsDict

	verbose

	model_mode

	Quser

	listOfModels

	model_type

	modelLabel

	textLabels

	participantList

	varianceThreshold

	fname

	optimiseRecall

	modelLoaded

	parallelOperation

	calibrated

	rawTextData

	rawData

	Yall

	Lall

	YtestAll

	LtestAll

	classifiers

	classif_thresh

	model_num_inducing

	model_num_iterations

	model_init_iterations

	additionalParametersList

Constructor & Destructor Documentation

◆ init()

def SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction.__init__ ( self )

Initialise class using SAMDriver.__init__ and augment with custom parameters.

additionalParameterList is a list of extra parameters to preserve between training and interaction.

Definition at line 32 of file SAMDriver_interaction.py.

Member Function Documentation

◆ formatGeneratedData()

def SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction.formatGeneratedData	(	self,
		instance
	)

Method to transform a generated instance from the model into a Yarp formatted output.

Parameters

instance Feature vector returned during generation of a label.

Returns: Yarp formatted output for instance.

Definition at line 264 of file SAMDriver_interaction.py.

◆ loadParameters()

def SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction.loadParameters	(	self,
		parser,
		trainName
	)

Function to load parameters from the model config.ini file.

Method to load parameters from file loaded in parser from within section trainName and store these parameters in self.paramsDict.

Parameters

parser	SafeConfigParser with pre-read config file.
trainName	Section from which parameters are to be read.

Returns: None

Definition at line 49 of file SAMDriver_interaction.py.

◆ processLiveData()

def SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction.processLiveData	(	self,
		dataList,
		thisModel,
		verbose,
		additionalData = `dict()`
	)

Method which receives a list of data frames and outputs a classification if available or 'no_classification' if it is not.

Parameters

dataList	List of dataFrames collected. Length of list is variable.
thisModel	List of models required for testing.
verbose	Boolean turning logging to stdout on or off.
additionalData	Dictionary containing additional data required for classification to occur.

Returns: String with result of classification, likelihood of the classification, and list of frames with the latest x number of frames popped where x is the window length of the model. Classification result can be string 'None' if the classification is unknown or message is invalid or None if a different error occurs.

Definition at line 213 of file SAMDriver_interaction.py.

◆ readData()

def SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction.readData	(	self,
		root_data_dir,
		participant_index,
		args,
		kw
	)

Method which accepts a data directory, reads all the data in and outputs self.Y which is a numpy array with n instances of m length feature vectors and self.L which is a list of text Labels of length n.

This method reads .ppm images from disk, converts the images to grayscale and serialises the data into a feature vector.

Parameters

root_data_dir	Data directory.
participant_index	List of subfolders to consider. Can be left as an empty list.

Returns

Definition at line 104 of file SAMDriver_interaction.py.

◆ saveParameters()

def SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction.saveParameters ( self )

Executes SAMDriver.saveParameters to save default parameters.

Definition at line 88 of file SAMDriver_interaction.py.

Member Data Documentation

◆ additionalParametersList

SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction.additionalParametersList

Definition at line 34 of file SAMDriver_interaction.py.

◆ L

SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction.L

Definition at line 199 of file SAMDriver_interaction.py.

◆ Y

SAM.SAM_Drivers.SAMDriver_interaction.SAMDriver_interaction.Y

Definition at line 198 of file SAMDriver_interaction.py.

Function Documentation

◆ init()

def SAM.SAM_Core.SAMDriver.SAMDriver.__init__ ( self )

Initialisation for SAMDriver.

Definition at line 40 of file SAMDriver.py.

◆ formatGeneratedData()

def SAM.SAM_Core.SAMDriver.SAMDriver.formatGeneratedData	(	self,
		instance
	)

Method which receives an instance generated from a model via a label and formats the received vector by reshaping it or adding crucial data with it for it to be deciphered at the receiving end.

Parameters

instance A vector of generated data.

Returns: NotImplementedError if not implemented by the inheriting child. Otherwise returns a Yarp Bottle or Yarp Image with the formatted generated data.

Definition at line 373 of file SAMDriver.py.

◆ loadParameters()

def SAM.SAM_Core.SAMDriver.SAMDriver.loadParameters	(	self,
		parser,
		trainName
	)

Function to load parameters from the model config.ini file.

Method to load parameters from file loaded in parser from within section trainName and store these parameters in self.paramsDict,

Parameters

parser	SafeConfigParser with pre-read config file.
trainName	Section from which parameters are to be read.

Returns: NotImplementedError if this function is not implemented by the inheriting child.

Definition at line 105 of file SAMDriver.py.

◆ prepareData()

def SAM.SAM_Core.SAMDriver.SAMDriver.prepareData	(	self,
		model = `'mrd'`,
		Ntr = `50`,
		randSeed = `0`,
		normalise = `True`
	)

Method for randomly splitting data and preparing Y dictionary.

This method splits the data in the model randomly between training and testing. Currently does not take equal number of samples from different classes.

Parameters

model	String with type of model to be trained. Accepted values are `'mrd'` and `'bgplvm'`.
Ntr	Float percentage for the training/testing division of data.
randSeed	Integer random seed.
normalise	Boolean turning normalisation of data on or off.

Returns: None

Definition at line 271 of file SAMDriver.py.

◆ processLiveData()

def SAM.SAM_Core.SAMDriver.SAMDriver.processLiveData	(	self,
		dataList,
		thisModel,
		verbose = `False`
	)

Method which receives a list of data frames and outputs a classification if available or 'no_classification' if it is not.

Parameters

dataList	List of dataFrames collected. Length of list is variable.
thisModel	List of models required for testing.
verbose	Boolean turning logging to stdout on or off.

Returns: NotImplementedError if not implemented by the inheriting child. Otherwise returns a string classification label.

Definition at line 361 of file SAMDriver.py.

◆ readData()

def SAM.SAM_Core.SAMDriver.SAMDriver.readData	(	self,
		root_data_dir,
		participant_index,
		args,
		kw
	)

Method which accepts a data directory, reads all the data in and outputs self.Y which is a numpy array with n instances of m length feature vectors and self.L which is a list of text Labels of length n.

Parameters

root_data_dir	Data directory.
participant_index	List of subfolders to consider. Can be left as an empty list.

Returns: NotImplementedError if not implemented by the inheriting child. Otherwise returns self.Y and self.L which contain the formatted data and labels read from the data directory.

Definition at line 347 of file SAMDriver.py.

◆ saveParameters()

def SAM.SAM_Core.SAMDriver.SAMDriver.saveParameters ( self )

Method to store variables generated during training which are required during interaction in self.paramsDict.

Parameters

None

Returns: None

Definition at line 117 of file SAMDriver.py.

◆ testPerformance()

def SAM.SAM_Core.SAMDriver.SAMDriver.testPerformance	(	self,
		testModel,
		Yall,
		Lall,
		YtestAll,
		LtestAll,
		verbose
	)

Method for testing the whole dataset for overall performance.

Returns a confusion matrix.

   This implementation is a standard performance testing method that can be overridden by an inheriting child.

Parameters

testModel	SAMObject Model to be tested.
Yall	Numpy array with training data vectors to be tested.
Lall	List with corresponding training data labels.
YtestAll	Numpy array with testing data vectors to be tested.
LtestAll	List with corresponding testing data labels.
verbose	Boolean turning logging to stdout on or off.

Returns: Square numpy array confusion matrix.

Definition at line 142 of file SAMDriver.py.

◆ training()

def SAM.SAM_Core.SAMDriver.SAMDriver.training	(	self,
		modelNumInducing,
		modelNumIterations,
		modelInitIterations,
		fname,
		save_model,
		economy_save,
		keepIfPresent = `True`,
		kernelStr = `None`
	)

Method to train, store and load the learned model.

This method tries reloading the model in fname. If unsuccessful or loaded model has mismatching parameters, trains a new model from scratch.

Parameters

modelNumInducing	Integer number of inducing parameters.
modelNumIterations	Integer number of training iterations.
modelInitIterations	Integer number of initialisation iterations.
fname	Filename to save model to.
save_model	Boolean to turn saving of the model on or off.
economy_save	Boolean to turn economy saving on or off. Economy save saves smaller models by not storing data inside the model but keeping it stored in the data path.
keepIfPresent	Boolean to enable or disable loading of a model when one is available.
kernelStr	Kernel string with the requested kernel. If `None` the default kernel is used.

Returns: None

Definition at line 172 of file SAMDriver.py.

Variable Documentation

◆ additionalParametersList

SAM.SAM_Core.SAMDriver.SAMDriver.additionalParametersList

Definition at line 90 of file SAMDriver.py.

◆ calibrated

SAM.SAM_Core.SAMDriver.SAMDriver.calibrated

Definition at line 74 of file SAMDriver.py.

◆ classif_thresh

SAM.SAM_Core.SAMDriver.SAMDriver.classif_thresh

Definition at line 84 of file SAMDriver.py.

◆ classifiers

SAM.SAM_Core.SAMDriver.SAMDriver.classifiers

Definition at line 83 of file SAMDriver.py.

◆ data_labels

SAM.SAM_Core.SAMDriver.SAMDriver.data_labels

Definition at line 59 of file SAMDriver.py.

◆ fname

SAM.SAM_Core.SAMDriver.SAMDriver.fname

Definition at line 70 of file SAMDriver.py.

◆ L

SAM.SAM_Core.SAMDriver.SAMDriver.L

Definition at line 45 of file SAMDriver.py.

◆ Lall

SAM.SAM_Core.SAMDriver.SAMDriver.Lall

Definition at line 79 of file SAMDriver.py.

◆ listOfModels

SAM.SAM_Core.SAMDriver.SAMDriver.listOfModels

Definition at line 64 of file SAMDriver.py.

◆ Ln

SAM.SAM_Core.SAMDriver.SAMDriver.Ln

Definition at line 54 of file SAMDriver.py.

◆ Ltest

SAM.SAM_Core.SAMDriver.SAMDriver.Ltest

Definition at line 48 of file SAMDriver.py.

◆ LtestAll

SAM.SAM_Core.SAMDriver.SAMDriver.LtestAll

Definition at line 81 of file SAMDriver.py.

◆ Ltestn

SAM.SAM_Core.SAMDriver.SAMDriver.Ltestn

Definition at line 50 of file SAMDriver.py.

◆ model_init_iterations

SAM.SAM_Core.SAMDriver.SAMDriver.model_init_iterations

Definition at line 88 of file SAMDriver.py.

◆ model_mode

SAM.SAM_Core.SAMDriver.SAMDriver.model_mode

Definition at line 62 of file SAMDriver.py.

◆ model_num_inducing

SAM.SAM_Core.SAMDriver.SAMDriver.model_num_inducing

Definition at line 86 of file SAMDriver.py.

◆ model_num_iterations

SAM.SAM_Core.SAMDriver.SAMDriver.model_num_iterations

Definition at line 87 of file SAMDriver.py.

◆ model_type

SAM.SAM_Core.SAMDriver.SAMDriver.model_type

Definition at line 65 of file SAMDriver.py.

◆ modelLabel

SAM.SAM_Core.SAMDriver.SAMDriver.modelLabel

Definition at line 66 of file SAMDriver.py.

◆ modelLoaded

SAM.SAM_Core.SAMDriver.SAMDriver.modelLoaded

Definition at line 72 of file SAMDriver.py.

◆ optimiseRecall

SAM.SAM_Core.SAMDriver.SAMDriver.optimiseRecall

Definition at line 71 of file SAMDriver.py.

◆ parallelOperation

SAM.SAM_Core.SAMDriver.SAMDriver.parallelOperation

Definition at line 73 of file SAMDriver.py.

◆ paramsDict

SAM.SAM_Core.SAMDriver.SAMDriver.paramsDict

Definition at line 60 of file SAMDriver.py.

◆ participantList

SAM.SAM_Core.SAMDriver.SAMDriver.participantList

Definition at line 68 of file SAMDriver.py.

◆ Quser

SAM.SAM_Core.SAMDriver.SAMDriver.Quser

Definition at line 63 of file SAMDriver.py.

◆ rawData

SAM.SAM_Core.SAMDriver.SAMDriver.rawData

Definition at line 76 of file SAMDriver.py.

◆ rawTextData

SAM.SAM_Core.SAMDriver.SAMDriver.rawTextData

Definition at line 75 of file SAMDriver.py.

◆ SAMObject

SAM.SAM_Core.SAMDriver.SAMDriver.SAMObject

Definition at line 42 of file SAMDriver.py.

◆ segTestConf

SAM.SAM_Core.SAMDriver.SAMDriver.segTestConf

Definition at line 57 of file SAMDriver.py.

◆ segTestPerc

SAM.SAM_Core.SAMDriver.SAMDriver.segTestPerc

Definition at line 58 of file SAMDriver.py.

◆ segTrainConf

SAM.SAM_Core.SAMDriver.SAMDriver.segTrainConf

Definition at line 55 of file SAMDriver.py.

◆ segTrainPerc

SAM.SAM_Core.SAMDriver.SAMDriver.segTrainPerc

Definition at line 56 of file SAMDriver.py.

◆ textLabels

SAM.SAM_Core.SAMDriver.SAMDriver.textLabels

Definition at line 67 of file SAMDriver.py.

◆ varianceThreshold

SAM.SAM_Core.SAMDriver.SAMDriver.varianceThreshold

Definition at line 69 of file SAMDriver.py.

◆ verbose

SAM.SAM_Core.SAMDriver.SAMDriver.verbose

Definition at line 61 of file SAMDriver.py.

◆ X

SAM.SAM_Core.SAMDriver.SAMDriver.X

Definition at line 46 of file SAMDriver.py.

◆ Y

SAM.SAM_Core.SAMDriver.SAMDriver.Y

Definition at line 44 of file SAMDriver.py.

◆ Yall

SAM.SAM_Core.SAMDriver.SAMDriver.Yall

Definition at line 78 of file SAMDriver.py.

◆ Ymean

SAM.SAM_Core.SAMDriver.SAMDriver.Ymean

Definition at line 51 of file SAMDriver.py.

◆ Yn

SAM.SAM_Core.SAMDriver.SAMDriver.Yn

Definition at line 53 of file SAMDriver.py.

◆ Ystd

SAM.SAM_Core.SAMDriver.SAMDriver.Ystd

Definition at line 52 of file SAMDriver.py.

◆ Ytest

SAM.SAM_Core.SAMDriver.SAMDriver.Ytest

Definition at line 47 of file SAMDriver.py.

◆ YtestAll

SAM.SAM_Core.SAMDriver.SAMDriver.YtestAll

Definition at line 80 of file SAMDriver.py.

◆ Ytestn

SAM.SAM_Core.SAMDriver.SAMDriver.Ytestn

Definition at line 49 of file SAMDriver.py.

Namespaces

Classes

Functions

Variables

Detailed Description

Class Documentation

◆ SAM::SAM_Core::SAMDriver::SAMDriver

Public Member Functions

Public Attributes

◆ SAM::SAM_Drivers::SAMDriver_ARWin::SAMDriver_ARWin

Public Member Functions

Public Attributes

Constructor & Destructor Documentation

◆ __init__()

Member Function Documentation

◆ convertToDict()

◆ diskDataToLiveData()

◆ listOfClassificationVectors()

◆ loadParameters()

◆ messageChecker()

◆ processLiveData()

◆ readData()

◆ saveParameters()

◆ testPerformance()

Member Data Documentation

◆ additionalParametersList

◆ allDataDict

◆ data

◆ data2Labels

◆ dataLogList

◆ dataVec

◆ featureSequence

◆ handsCombined

◆ itemsPerJoint

◆ L

◆ labelsLogList

◆ listOfVectorsToClassify

◆ numJoints

◆ rawTextData

◆ seqTestConf

◆ seqTestPerc

◆ Y

◆ SAM::SAM_Drivers::SAMDriver_interaction::SAMDriver_interaction

Public Member Functions

Public Attributes

Constructor & Destructor Documentation

◆ __init__()

Member Function Documentation

◆ formatGeneratedData()

◆ loadParameters()

◆ processLiveData()

◆ readData()

◆ saveParameters()

Member Data Documentation

◆ additionalParametersList

◆ L

◆ Y

Function Documentation

◆ __init__()

◆ formatGeneratedData()

◆ loadParameters()

◆ prepareData()

◆ processLiveData()

◆ readData()

◆ saveParameters()

◆ testPerformance()

◆ training()

Variable Documentation

◆ additionalParametersList

◆ calibrated

◆ classif_thresh

◆ classifiers

◆ data_labels

◆ fname

◆ L

◆ Lall

◆ listOfModels

◆ Ln

◆ Ltest

◆ LtestAll

◆ init()

◆ init()

◆ init()