def initialiseModels(argv, update, initMode='training'):
# argv[1] = dataPath
# argv[2] = modelPath
# argv[3] = driverName
# update = 'update' or 'new'
from SAM.SAM_Core import SAMDriver as Driver
dataPath = argv[0]
modelPath = argv[1]
driverName = argv[2]
logging.info(argv)
stringCommand = 'from SAM.SAM_Drivers import ' + driverName + ' as Driver'
logging.info(stringCommand)
exec stringCommand
mySAMpy = Driver()
mode = update
trainName = dataPath.split('/')[-1]
# participantList is extracted from number of subdirectories of dataPath
participantList = [
f for f in listdir(dataPath) if isdir(join(dataPath, f))
]
off = 17
logging.info('-------------------')
logging.info('Training Settings:')
logging.info('')
logging.info('Init mode: '.ljust(off) + str(initMode))
logging.info('Data Path: '.ljust(off) + str(dataPath))
logging.info('Model Path: '.ljust(off) + str(modelPath))
logging.info('Participants: '.ljust(off) + str(participantList))
logging.info('Model Root Name: '.ljust(off) + str(trainName))
logging.info('Training Mode:'.ljust(off) + str(mode))
logging.info('Driver:'.ljust(off) + str(driverName))
logging.info('-------------------')
logging.info('Loading Parameters...')
logging.info('')
temporalFlag = False
modeConfig = ''
found = ''
try:
parser = SafeConfigParser()
found = parser.read(dataPath + "/config.ini")
if parser.has_option(trainName, 'update_mode'):
modeConfig = parser.get(trainName, 'update_mode')
else:
modeConfig = 'update'
logging.info(modeConfig)
except IOError:
pass
defaultParamsList = [
'experiment_number', 'model_type', 'model_num_inducing',
'model_num_iterations', 'model_init_iterations', 'verbose', 'Quser',
'kernelString', 'ratioData', 'update_mode', 'model_mode',
'temporalModelWindowSize', 'optimiseRecall', 'classificationDict',
'useMaxDistance', 'calibrateUnknown'
]
mySAMpy.experiment_number = None
mySAMpy.model_type = None
mySAMpy.kernelString = None
mySAMpy.fname = None
mySAMpy.ratioData = None
if initMode == 'training' and (mode == 'new' or modeConfig == 'new'
or 'exp' not in modelPath):
logging.info('Loading training parameters from:' + str(dataPath) +
"/config.ini")
try:
default = False
parser = SafeConfigParser()
parser.optionxform = str
found = parser.read(dataPath + "/config.ini")
mySAMpy.experiment_number = 'exp'
# load parameters from config file
# if parser.has_option(trainName, 'experiment_number'):
# mySAMpy.experiment_number = int(parser.get(trainName, 'experiment_number'))
# elif '.pickle' in modelPath:
# mySAMpy.experiment_number = int(modelPath.split('__')[-2].replace('exp', '')) + 1
# else:
if parser.has_option(trainName, 'model_type'):
mySAMpy.model_type = parser.get(trainName, 'model_type')
else:
default = True
mySAMpy.model_type = 'mrd'
if parser.has_option(trainName, 'model_num_inducing'):
mySAMpy.model_num_inducing = int(
parser.get(trainName, 'model_num_inducing'))
else:
default = True
mySAMpy.model_num_inducing = 30
if parser.has_option(trainName, 'model_num_iterations'):
mySAMpy.model_num_iterations = int(
parser.get(trainName, 'model_num_iterations'))
else:
default = True
mySAMpy.model_num_iterations = 700
if parser.has_option(trainName, 'model_init_iterations'):
mySAMpy.model_init_iterations = int(
parser.get(trainName, 'model_init_iterations'))
else:
default = True
mySAMpy.model_init_iterations = 2000
if parser.has_option(trainName, 'verbose'):
mySAMpy.verbose = parser.get(trainName, 'verbose') == 'True'
else:
default = True
mySAMpy.verbose = False
if parser.has_option(trainName, 'optimiseRecall'):
mySAMpy.optimiseRecall = int(
parser.get(trainName, 'optimiseRecall'))
else:
default = True
mySAMpy.optimiseRecall = 200
if parser.has_option(trainName, 'useMaxDistance'):
mySAMpy.useMaxDistance = parser.get(trainName,
'useMaxDistance') == 'True'
else:
mySAMpy.useMaxDistance = False
if parser.has_option(trainName, 'calibrateUnknown'):
mySAMpy.calibrateUnknown = parser.get(
trainName, 'calibrateUnknown') == 'True'
else:
mySAMpy.calibrateUnknown = False
if parser.has_option(trainName, 'model_mode'):
mySAMpy.model_mode = parser.get(trainName, 'model_mode')
if mySAMpy.model_mode == 'temporal' and parser.has_option(
trainName, 'temporalModelWindowSize'):
mySAMpy.temporalWindowSize = int(
parser.get(trainName, 'temporalModelWindowSize'))
else:
temporalFlag = True
else:
default = True
mySAMpy.model_mode = 'single'
if parser.has_option(trainName, 'Quser'):
mySAMpy.Quser = int(parser.get(trainName, 'Quser'))
else:
default = True
mySAMpy.Quser = 2
if parser.has_option(trainName, 'kernelString'):
mySAMpy.kernelString = parser.get(trainName, 'kernelString')
else:
default = True
mySAMpy.kernelString = "GPy.kern.RBF(Q, ARD=False) + GPy.kern.Bias(Q) + GPy.kern.White(Q)"
if parser.has_option(trainName, 'ratioData'):
mySAMpy.ratioData = int(parser.get(trainName, 'ratioData'))
else:
default = True
mySAMpy.ratioData = 50
if default:
logging.info('Default settings applied')
mySAMpy.paramsDict = dict()
mySAMpy.loadParameters(parser, trainName)
except IOError:
logging.warning('IO Exception reading ', found)
pass
else:
logging.info('Loading parameters from: \n \t' + str(modelPath))
try:
parser = SafeConfigParser()
parser.optionxform = str
found = parser.read(dataPath + "/config.ini")
# load parameters from config file
mySAMpy.experiment_number = modelPath.split('__')[-1]
modelPickle = pickle.load(open(modelPath + '.pickle', 'rb'))
mySAMpy.paramsDict = dict()
for j in parser.options(trainName):
if j not in defaultParamsList:
logging.info(str(j))
mySAMpy.paramsDict[j] = modelPickle[j]
mySAMpy.ratioData = modelPickle['ratioData']
mySAMpy.model_type = modelPickle['model_type']
mySAMpy.model_mode = modelPickle['model_mode']
if mySAMpy.model_mode == 'temporal':
mySAMpy.temporalModelWindowSize = modelPickle[
'temporalModelWindowSize']
mySAMpy.model_type = 'mrd'
mySAMpy.model_num_inducing = modelPickle['model_num_inducing']
mySAMpy.model_num_iterations = modelPickle['model_num_iterations']
mySAMpy.model_init_iterations = modelPickle[
'model_init_iterations']
mySAMpy.verbose = modelPickle['verbose']
mySAMpy.Quser = modelPickle['Quser']
mySAMpy.optimiseRecall = modelPickle['optimiseRecall']
mySAMpy.kernelString = modelPickle['kernelString']
mySAMpy.calibrated = modelPickle['calibrated']
# try loading classification parameters for multiple model implementation
try:
mySAMpy.useMaxDistance = modelPickle['useMaxDistance']
except:
logging.warning(
'Failed to load useMaxDistace. Possible reasons: '
'Not saved or multiple model implementation')
mySAMpy.calibrateUnknown = modelPickle['calibrateUnknown']
if mySAMpy.calibrateUnknown:
mySAMpy.classificationDict = modelPickle['classificationDict']
# try:
# mySAMpy.listOfModels = modelPickle['listOfModels']
# mySAMpy.classifiers = modelPickle['classifiers']
# mySAMpy.classif_thresh = modelPickle['classif_thresh']
# mulClassLoadFail = False
# logging.info('Successfully loaded multiple model classifiers')
# except:
# mulClassLoadFail = True
# logging.info('Failed to load multiple model classifiers')
# pass
#
# # try loading classification parameters for single model implementation
# try:
# mySAMpy.varianceDirection = modelPickle['varianceDirection']
# mySAMpy.varianceThreshold = modelPickle['varianceThreshold']
# mySAMpy.bestDistanceIDX = modelPickle['bestDistanceIDX']
# logging.info('Successfully loaded single model classifiers')
# singClassLoadFail = False
# except:
# singClassLoadFail = True
# logging.info('Failed to load single model classifiers')
# pass
# if mulClassLoadFail and singClassLoadFail:
# raise ValueError('Failed to load model classifiers')
except IOError:
logging.warning('IO Exception reading ', found)
pass
if 'exp' in modelPath or 'best' in modelPath or 'backup' in modelPath:
fnameProto = '/'.join(modelPath.split('/')[:-1]) + '/' + dataPath.split('/')[-1] + '__' + driverName + \
'__' + mySAMpy.model_type + '__' + str(mySAMpy.experiment_number)
else:
fnameProto = modelPath + dataPath.split('/')[-1] + '__' + driverName + '__' + mySAMpy.model_type + \
'__' + str(mySAMpy.experiment_number)
logging.info('Full model name: ' + str(fnameProto))
logging.info('-------------------')
logging.info('')
mySAMpy.save_model = False
mySAMpy.economy_save = True
mySAMpy.visualise_output = False
# test_mode = True
mySAMpy.readData(dataPath, participantList)
# at this point, all the data that will be eventually used for training is contained in mySAMpy.Y
# and mySAMpy.L contains all labels if any (depending on mrd model or bgplvm model)
# mySAMpy.L is a list of labels while mySAMpy.Y is a numpy array of data
# mySAMpy.Y should have 2 dimensions, length of dimension 0 = number of instances
# length of dimension 1 = length of feature vector
if mySAMpy.model_mode != 'temporal':
# get list of labels
mySAMpy.textLabels = list(set(mySAMpy.L))
# convert L from list of strings to array of indices
mySAMpy.L = np.asarray(
[mySAMpy.textLabels.index(i) for i in mySAMpy.L])[:, None]
mySAMpy.textLabels = mySAMpy.textLabels
else:
mySAMpy.X, mySAMpy.Y = transformTimeSeriesToSeq(
mySAMpy.Y1, mySAMpy.temporalModelWindowSize)
mySAMpy.L, mySAMpy.tmp = transformTimeSeriesToSeq(
mySAMpy.U1, mySAMpy.temporalModelWindowSize)
mm = [mySAMpy]
# mm.append(mySAMpy)
# mm[0] contains root model
# this is the only model in the case of a single model
# or contains all info for the rest of the models in case of multiple models
#
if mySAMpy.model_mode == 'single' or mySAMpy.model_mode == 'temporal':
mm[0].participantList = ['all']
else:
mm[0].participantList = ['root'] + mySAMpy.textLabels
for k in range(len(mm[0].participantList)):
if mm[0].participantList[k] == 'all':
normaliseData = True
minData = len(mm[k].L)
mm[0].fname = fnameProto
mm[0].model_type = mySAMpy.model_type
Ntr = int(mySAMpy.ratioData * minData / 100)
else:
if k > 0:
mm.append(Driver())
# extract subset of data corresponding to this model
inds = [
i for i in range(len(mm[0].Y['L']))
if mm[0].Y['L'][i] == k - 1
]
mm[k].Y = mm[0].Y['Y'][inds]
mm[k].L = mm[0].Y['L'][inds]
mm[k].Quser = mm[0].Quser
mm[k].verbose = mm[0].verbose
logging.info('Object class: ' + str(mm[0].participantList[k]))
minData = len(inds)
mm[k].fname = fnameProto + '__L' + str(k - 1)
mm[0].listOfModels.append(mm[k].fname)
mm[k].model_type = 'bgplvm'
Ntr = int(mySAMpy.ratioData * minData / 100)
normaliseData = True
else:
normaliseData = False
mm[0].listOfModels = []
mm[0].fname = fnameProto
mm[0].SAMObject.kernelString = ''
minData = len(mm[0].L)
Ntr = int(mySAMpy.ratioData * minData / 100)
mm[k].modelLabel = mm[0].participantList[k]
if mm[0].model_mode != 'temporal':
[Yall, Lall, YtestAll,
LtestAll] = mm[k].prepareData(mm[k].model_type,
Ntr,
randSeed=0,
normalise=normaliseData)
mm[k].Yall = Yall
mm[k].Lall = Lall
mm[k].YtestAll = YtestAll
mm[k].LtestAll = LtestAll
elif mm[0].model_mode == 'temporal':
[Xall, Yall, Lall, XtestAll, YtestAll,
LtestAll] = mm[k].prepareData(mm[k].model_type,
Ntr,
randSeed=0,
normalise=normaliseData)
mm[k].Xall = Xall
mm[k].Yall = Yall
mm[k].Lall = Lall
mm[k].XtestAll = XtestAll
mm[k].YtestAll = YtestAll
mm[k].LtestAll = LtestAll
logging.info('minData = ' + str(minData))
logging.info('ratioData = ' + str(mySAMpy.ratioData))
logging.info(
'-------------------------------------------------------------------------------------------------'
)
if initMode == 'training':
samOptimiser.deleteModel(modelPath, 'exp')
for k in range(len(mm[0].participantList)):
# for k = 0 check if multiple model or not
if mm[0].participantList[k] != 'root':
logging.info("Training with " + str(mm[0].model_num_inducing) +
' inducing points for ' +
str(mm[0].model_init_iterations) + '|' +
str(mm[0].model_num_iterations))
logging.info("Fname:" + str(mm[k].fname))
mm[k].training(mm[0].model_num_inducing,
mm[0].model_num_iterations,
mm[0].model_init_iterations,
mm[k].fname,
mm[0].save_model,
mm[0].economy_save,
keepIfPresent=False,
kernelStr=mm[0].kernelString)
if mm[0].visualise_output:
ax = mm[k].SAMObject.visualise()
visualiseInfo = dict()
visualiseInfo['ax'] = ax
else:
visualiseInfo = None
else:
for k in range(len(mm[0].participantList)):
# for k = 0 check if multiple model or not
if mm[0].participantList[k] != 'root':
logging.info("Training with " + str(mm[0].model_num_inducing) +
' inducing points for ' +
str(mm[0].model_init_iterations) + '|' +
str(mm[0].model_num_iterations))
mm[k].training(mm[0].model_num_inducing,
mm[0].model_num_iterations,
mm[0].model_init_iterations,
mm[k].fname,
mm[0].save_model,
mm[0].economy_save,
keepIfPresent=True,
kernelStr=mm[0].kernelString)
return mm
def initialiseModels(argv, update, initMode='training'):
"""Initialise SAM Model data structure, training parameters and user parameters.
This method starts by initialising the required Driver from the driver name in argv[3] if it exists
in SAM_Drivers folder. The standard model parameters and the specific user parameters are then initialised
and the data is read in by the SAMDriver.readData method to complete the model data structure. This method
then replicates the model data structure for training with multiple models if it is required in the config
file loaded by the Driver.
Args:
argv_0: dataPath containing the data that is to be trained on.
argv_1: modelPath containing the path of where the model is to be stored.
argv_2: driverName containing the name of the driver class that is to be loaded from SAM_Drivers folder.
update: String having either a value of 'update' or 'new'. 'new' will load the parameters as set in the
config file of the driver being loaded present in the dataPath directory. This is used to train a
new model from scratch. 'update' will check for an existing model in the modelPath directory and
load the parameters from this model if it exists. This is used for retraining a model when new
data becomes available.
initMode: String having either a value of 'training' or 'interaction'. 'training' takes into consideration
the value of update in loading the parameters. (Used by trainSAMModel.py) 'interaction' loads
the parameters directly from the model if the model exists. (Used by interactionSAMModel.py)
Returns:
The output is a list of SAMDriver models. The list is of length 1 when the config file requests a single
model or a list of length n+1 for a config file requesting multiple models where n is the number of
requested models. The number of models either depends on the number of directories present in the dataPath
or from the length of textLabels returned from the SAMDriver.readData method.
"""
from SAM.SAM_Core import SAMDriver as Driver
dataPath = argv[0]
modelPath = argv[1]
driverName = argv[2]
logging.info(argv)
stringCommand = 'from SAM.SAM_Drivers import ' + driverName + ' as Driver'
logging.info(stringCommand)
exec stringCommand
mySAMpy = Driver()
mode = update
trainName = dataPath.split('/')[-1]
# participantList is extracted from number of subdirectories of dataPath
participantList = [
f for f in listdir(dataPath) if isdir(join(dataPath, f))
]
off = 17
logging.info('-------------------')
logging.info('Training Settings:')
logging.info('')
logging.info('Init mode: '.ljust(off) + str(initMode))
logging.info('Data Path: '.ljust(off) + str(dataPath))
logging.info('Model Path: '.ljust(off) + str(modelPath))
logging.info('Participants: '.ljust(off) + str(participantList))
logging.info('Model Root Name: '.ljust(off) + str(trainName))
logging.info('Training Mode:'.ljust(off) + str(mode))
logging.info('Driver:'.ljust(off) + str(driverName))
logging.info('-------------------')
logging.info('Loading Parameters...')
logging.info('')
modeConfig = ''
found = ''
try:
parser = SafeConfigParser()
found = parser.read(dataPath + "/config.ini")
if parser.has_option(trainName, 'update_mode'):
modeConfig = parser.get(trainName, 'update_mode')
else:
modeConfig = 'update'
logging.info(modeConfig)
except IOError:
pass
defaultParamsList = [
'experiment_number', 'model_type', 'model_num_inducing',
'model_num_iterations', 'model_init_iterations', 'verbose', 'Quser',
'kernelString', 'ratioData', 'update_mode', 'model_mode',
'temporalModelWindowSize', 'optimiseRecall', 'classificationDict',
'useMaxDistance', 'calibrateUnknown'
]
mySAMpy.experiment_number = None
mySAMpy.model_type = None
mySAMpy.kernelString = None
mySAMpy.fname = None
mySAMpy.ratioData = None
if initMode == 'training' and (mode == 'new' or modeConfig == 'new'
or 'exp' not in modelPath):
logging.info('Loading training parameters from:' + str(dataPath) +
"/config.ini")
try:
default = False
parser = SafeConfigParser()
parser.optionxform = str
found = parser.read(dataPath + "/config.ini")
mySAMpy.experiment_number = 'exp'
if parser.has_option(trainName, 'model_type'):
mySAMpy.model_type = parser.get(trainName, 'model_type')
else:
default = True
mySAMpy.model_type = 'mrd'
if parser.has_option(trainName, 'model_num_inducing'):
mySAMpy.model_num_inducing = int(
parser.get(trainName, 'model_num_inducing'))
else:
default = True
mySAMpy.model_num_inducing = 30
if parser.has_option(trainName, 'model_num_iterations'):
mySAMpy.model_num_iterations = int(
parser.get(trainName, 'model_num_iterations'))
else:
default = True
mySAMpy.model_num_iterations = 700
if parser.has_option(trainName, 'model_init_iterations'):
mySAMpy.model_init_iterations = int(
parser.get(trainName, 'model_init_iterations'))
else:
default = True
mySAMpy.model_init_iterations = 2000
if parser.has_option(trainName, 'verbose'):
mySAMpy.verbose = parser.get(trainName, 'verbose') == 'True'
else:
default = True
mySAMpy.verbose = False
if parser.has_option(trainName, 'optimiseRecall'):
mySAMpy.optimiseRecall = int(
parser.get(trainName, 'optimiseRecall'))
else:
default = True
mySAMpy.optimiseRecall = 200
if parser.has_option(trainName, 'useMaxDistance'):
mySAMpy.useMaxDistance = parser.get(trainName,
'useMaxDistance') == 'True'
else:
mySAMpy.useMaxDistance = False
if parser.has_option(trainName, 'calibrateUnknown'):
mySAMpy.calibrateUnknown = parser.get(
trainName, 'calibrateUnknown') == 'True'
else:
mySAMpy.calibrateUnknown = False
if parser.has_option(trainName, 'model_mode'):
mySAMpy.model_mode = parser.get(trainName, 'model_mode')
if mySAMpy.model_mode == 'temporal' and parser.has_option(
trainName, 'temporalModelWindowSize'):
mySAMpy.temporalWindowSize = int(
parser.get(trainName, 'temporalModelWindowSize'))
else:
temporalFlag = True
else:
default = True
mySAMpy.model_mode = 'single'
if parser.has_option(trainName, 'Quser'):
mySAMpy.Quser = int(parser.get(trainName, 'Quser'))
else:
default = True
mySAMpy.Quser = 2
if parser.has_option(trainName, 'kernelString'):
mySAMpy.kernelString = parser.get(trainName, 'kernelString')
else:
default = True
mySAMpy.kernelString = "GPy.kern.RBF(Q, ARD=False) + GPy.kern.Bias(Q) + GPy.kern.White(Q)"
if parser.has_option(trainName, 'ratioData'):
mySAMpy.ratioData = int(parser.get(trainName, 'ratioData'))
else:
default = True
mySAMpy.ratioData = 50
if default:
logging.info('Default settings applied')
mySAMpy.paramsDict = dict()
mySAMpy.loadParameters(parser, trainName)
except IOError:
logging.warning('IO Exception reading ', found)
pass
else:
logging.info('Loading parameters from: \n \t' + str(modelPath))
try:
parser = SafeConfigParser()
parser.optionxform = str
found = parser.read(dataPath + "/config.ini")
# load parameters from config file
mySAMpy.experiment_number = modelPath.split('__')[-1]
modelPickle = pickle.load(open(modelPath + '.pickle', 'rb'))
mySAMpy.paramsDict = dict()
for j in parser.options(trainName):
if j not in defaultParamsList:
logging.info(str(j))
mySAMpy.paramsDict[j] = modelPickle[j]
mySAMpy.ratioData = modelPickle['ratioData']
mySAMpy.model_type = modelPickle['model_type']
mySAMpy.model_mode = modelPickle['model_mode']
if mySAMpy.model_mode == 'temporal':
mySAMpy.temporalModelWindowSize = modelPickle[
'temporalModelWindowSize']
mySAMpy.model_type = 'mrd'
mySAMpy.model_num_inducing = modelPickle['model_num_inducing']
mySAMpy.model_num_iterations = modelPickle['model_num_iterations']
mySAMpy.model_init_iterations = modelPickle[
'model_init_iterations']
mySAMpy.verbose = modelPickle['verbose']
mySAMpy.Quser = modelPickle['Quser']
mySAMpy.optimiseRecall = modelPickle['optimiseRecall']
mySAMpy.kernelString = modelPickle['kernelString']
mySAMpy.calibrated = modelPickle['calibrated']
# try loading classification parameters for multiple model implementation
try:
mySAMpy.useMaxDistance = modelPickle['useMaxDistance']
except:
logging.warning(
'Failed to load useMaxDistace. Possible reasons: '
'Not saved or multiple model implementation')
mySAMpy.calibrateUnknown = modelPickle['calibrateUnknown']
if mySAMpy.calibrateUnknown:
mySAMpy.classificationDict = modelPickle['classificationDict']
except IOError:
logging.warning('IO Exception reading ', found)
pass
if 'exp' in modelPath or 'best' in modelPath or 'backup' in modelPath:
fnameProto = '/'.join(modelPath.split('/')[:-1]) + '/' + dataPath.split('/')[-1] + '__' + driverName + \
'__' + mySAMpy.model_type + '__' + str(mySAMpy.experiment_number)
else:
fnameProto = modelPath + dataPath.split('/')[-1] + '__' + driverName + '__' + mySAMpy.model_type + \
'__' + str(mySAMpy.experiment_number)
logging.info('Full model name: ' + str(fnameProto))
logging.info('-------------------')
logging.info('')
mySAMpy.save_model = False
mySAMpy.economy_save = True
mySAMpy.visualise_output = False
# test_mode = True
mySAMpy.readData(dataPath, participantList)
if mySAMpy.model_mode != 'temporal':
# get list of labels
mySAMpy.textLabels = list(set(mySAMpy.L))
# convert L from list of strings to array of indices
mySAMpy.L = np.asarray(
[mySAMpy.textLabels.index(i) for i in mySAMpy.L])[:, None]
mySAMpy.textLabels = mySAMpy.textLabels
else:
mySAMpy.X, mySAMpy.Y = transformTimeSeriesToSeq(
mySAMpy.Y1, mySAMpy.temporalModelWindowSize)
mySAMpy.L, mySAMpy.tmp = transformTimeSeriesToSeq(
mySAMpy.U1, mySAMpy.temporalModelWindowSize)
mm = [mySAMpy]
# mm.append(mySAMpy)
# mm[0] contains root model
# this is the only model in the case of a single model
# or contains all info for the rest of the models in case of multiple models
#
if mySAMpy.model_mode == 'single' or mySAMpy.model_mode == 'temporal':
mm[0].participantList = ['all']
else:
mm[0].participantList = ['root'] + mySAMpy.textLabels
for k in range(len(mm[0].participantList)):
if mm[0].participantList[k] == 'all':
normaliseData = True
minData = len(mm[k].L)
mm[0].fname = fnameProto
mm[0].model_type = mySAMpy.model_type
Ntr = int(mySAMpy.ratioData * minData / 100)
else:
if k > 0:
mm.append(Driver())
# extract subset of data corresponding to this model
inds = [
i for i in range(len(mm[0].Y['L']))
if mm[0].Y['L'][i] == k - 1
]
mm[k].Y = mm[0].Y['Y'][inds]
mm[k].L = mm[0].Y['L'][inds]
mm[k].Quser = mm[0].Quser
mm[k].verbose = mm[0].verbose
logging.info('Object class: ' + str(mm[0].participantList[k]))
minData = len(inds)
mm[k].fname = fnameProto + '__L' + str(k - 1)
mm[0].listOfModels.append(mm[k].fname)
mm[k].model_type = 'bgplvm'
Ntr = int(mySAMpy.ratioData * minData / 100)
normaliseData = True
else:
normaliseData = False
mm[0].listOfModels = []
mm[0].fname = fnameProto
mm[0].SAMObject.kernelString = ''
minData = len(mm[0].L)
Ntr = int(mySAMpy.ratioData * minData / 100)
mm[k].modelLabel = mm[0].participantList[k]
if mm[0].model_mode != 'temporal':
[Yall, Lall, YtestAll,
LtestAll] = mm[k].prepareData(mm[k].model_type,
Ntr,
randSeed=0,
normalise=normaliseData)
mm[k].Yall = Yall
mm[k].Lall = Lall
mm[k].YtestAll = YtestAll
mm[k].LtestAll = LtestAll
elif mm[0].model_mode == 'temporal':
[Xall, Yall, Lall, XtestAll, YtestAll,
LtestAll] = mm[k].prepareData(mm[k].model_type,
Ntr,
randSeed=0,
normalise=normaliseData)
mm[k].Xall = Xall
mm[k].Yall = Yall
mm[k].Lall = Lall
mm[k].XtestAll = XtestAll
mm[k].YtestAll = YtestAll
mm[k].LtestAll = LtestAll
logging.info('minData = ' + str(minData))
logging.info('ratioData = ' + str(mySAMpy.ratioData))
logging.info(
'-------------------------------------------------------------------------------------------------'
)
if initMode == 'training':
samOptimiser.deleteModel(modelPath, 'exp')
for k in range(len(mm[0].participantList)):
# for k = 0 check if multiple model or not
if mm[0].participantList[k] != 'root':
logging.info("Training with " + str(mm[0].model_num_inducing) +
' inducing points for ' +
str(mm[0].model_init_iterations) + '|' +
str(mm[0].model_num_iterations))
logging.info("Fname:" + str(mm[k].fname))
mm[k].training(mm[0].model_num_inducing,
mm[0].model_num_iterations,
mm[0].model_init_iterations,
mm[k].fname,
mm[0].save_model,
mm[0].economy_save,
keepIfPresent=False,
kernelStr=mm[0].kernelString)
if mm[0].visualise_output:
ax = mm[k].SAMObject.visualise()
visualiseInfo = dict()
visualiseInfo['ax'] = ax
else:
visualiseInfo = None
else:
for k in range(len(mm[0].participantList)):
# for k = 0 check if multiple model or not
if mm[0].participantList[k] != 'root':
logging.info("Training with " + str(mm[0].model_num_inducing) +
' inducing points for ' +
str(mm[0].model_init_iterations) + '|' +
str(mm[0].model_num_iterations))
mm[k].training(mm[0].model_num_inducing,
mm[0].model_num_iterations,
mm[0].model_init_iterations,
mm[k].fname,
mm[0].save_model,
mm[0].economy_save,
keepIfPresent=True,
kernelStr=mm[0].kernelString)
return mm
def initialiseModels(argv, update, initMode='training'):
# argv[1] = dataPath
# argv[2] = modelPath
# argv[3] = driverName
# update = 'update' or 'new'
from SAM.SAM_Core import SAMDriver as Driver
dataPath = argv[0]
modelPath = argv[1]
driverName = argv[2]
logging.info(argv)
stringCommand = 'from SAM.SAM_Drivers import ' + driverName + ' as Driver'
logging.info(stringCommand)
exec stringCommand
mySAMpy = Driver()
mode = update
trainName = dataPath.split('/')[-1]
# participantList is extracted from number of subdirectories of dataPath
participantList = [f for f in listdir(dataPath) if isdir(join(dataPath, f))]
off = 17
logging.info('-------------------')
logging.info('Training Settings:')
logging.info('')
logging.info('Init mode: '.ljust(off) + str(initMode))
logging.info('Data Path: '.ljust(off) + str(dataPath))
logging.info('Model Path: '.ljust(off) + str(modelPath))
logging.info('Participants: '.ljust(off) + str(participantList))
logging.info('Model Root Name: '.ljust(off) + str(trainName))
logging.info('Training Mode:'.ljust(off) + str(mode))
logging.info('Driver:'.ljust(off) + str(driverName))
logging.info('-------------------')
logging.info('Loading Parameters...')
logging.info('')
temporalFlag = False
modeConfig = ''
found = ''
try:
parser = SafeConfigParser()
found = parser.read(dataPath + "/config.ini")
if parser.has_option(trainName, 'update_mode'):
modeConfig = parser.get(trainName, 'update_mode')
else:
modeConfig = 'update'
logging.info(modeConfig)
except IOError:
pass
defaultParamsList = ['experiment_number', 'model_type', 'model_num_inducing',
'model_num_iterations', 'model_init_iterations', 'verbose',
'Quser', 'kernelString', 'ratioData', 'update_mode', 'model_mode',
'temporalModelWindowSize', 'optimiseRecall', 'classificationDict',
'useMaxDistance', 'calibrateUnknown']
mySAMpy.experiment_number = None
mySAMpy.model_type = None
mySAMpy.kernelString = None
mySAMpy.fname = None
mySAMpy.ratioData = None
if initMode == 'training' and (mode == 'new' or modeConfig == 'new' or 'exp' not in modelPath):
logging.info('Loading training parameters from:' + str(dataPath) + "/config.ini")
try:
default = False
parser = SafeConfigParser()
parser.optionxform = str
found = parser.read(dataPath + "/config.ini")
mySAMpy.experiment_number = 'exp'
# load parameters from config file
# if parser.has_option(trainName, 'experiment_number'):
# mySAMpy.experiment_number = int(parser.get(trainName, 'experiment_number'))
# elif '.pickle' in modelPath:
# mySAMpy.experiment_number = int(modelPath.split('__')[-2].replace('exp', '')) + 1
# else:
if parser.has_option(trainName, 'model_type'):
mySAMpy.model_type = parser.get(trainName, 'model_type')
else:
default = True
mySAMpy.model_type = 'mrd'
if parser.has_option(trainName, 'model_num_inducing'):
mySAMpy.model_num_inducing = int(parser.get(trainName, 'model_num_inducing'))
else:
default = True
mySAMpy.model_num_inducing = 30
if parser.has_option(trainName, 'model_num_iterations'):
mySAMpy.model_num_iterations = int(parser.get(trainName, 'model_num_iterations'))
else:
default = True
mySAMpy.model_num_iterations = 700
if parser.has_option(trainName, 'model_init_iterations'):
mySAMpy.model_init_iterations = int(parser.get(trainName, 'model_init_iterations'))
else:
default = True
mySAMpy.model_init_iterations = 2000
if parser.has_option(trainName, 'verbose'):
mySAMpy.verbose = parser.get(trainName, 'verbose') == 'True'
else:
default = True
mySAMpy.verbose = False
if parser.has_option(trainName, 'optimiseRecall'):
mySAMpy.optimiseRecall = int(parser.get(trainName, 'optimiseRecall'))
else:
default = True
mySAMpy.optimiseRecall = 200
if parser.has_option(trainName, 'useMaxDistance'):
mySAMpy.useMaxDistance = parser.get(trainName, 'useMaxDistance') == 'True'
else:
mySAMpy.useMaxDistance = False
if parser.has_option(trainName, 'calibrateUnknown'):
mySAMpy.calibrateUnknown = parser.get(trainName, 'calibrateUnknown') == 'True'
else:
mySAMpy.calibrateUnknown = False
if parser.has_option(trainName, 'model_mode'):
mySAMpy.model_mode = parser.get(trainName, 'model_mode')
if mySAMpy.model_mode == 'temporal' and parser.has_option(trainName, 'temporalModelWindowSize'):
mySAMpy.temporalWindowSize = int(parser.get(trainName, 'temporalModelWindowSize'))
else:
temporalFlag = True
else:
default = True
mySAMpy.model_mode = 'single'
if parser.has_option(trainName, 'Quser'):
mySAMpy.Quser = int(parser.get(trainName, 'Quser'))
else:
default = True
mySAMpy.Quser = 2
if parser.has_option(trainName, 'kernelString'):
mySAMpy.kernelString = parser.get(trainName, 'kernelString')
else:
default = True
mySAMpy.kernelString = "GPy.kern.RBF(Q, ARD=False) + GPy.kern.Bias(Q) + GPy.kern.White(Q)"
if parser.has_option(trainName, 'ratioData'):
mySAMpy.ratioData = int(parser.get(trainName, 'ratioData'))
else:
default = True
mySAMpy.ratioData = 50
if default:
logging.info('Default settings applied')
mySAMpy.paramsDict = dict()
mySAMpy.loadParameters(parser, trainName)
except IOError:
logging.warning('IO Exception reading ', found)
pass
else:
logging.info('Loading parameters from: \n \t' + str(modelPath))
try:
parser = SafeConfigParser()
parser.optionxform = str
found = parser.read(dataPath + "/config.ini")
# load parameters from config file
mySAMpy.experiment_number = modelPath.split('__')[-1]
modelPickle = pickle.load(open(modelPath+'.pickle', 'rb'))
mySAMpy.paramsDict = dict()
for j in parser.options(trainName):
if j not in defaultParamsList:
logging.info(str(j))
mySAMpy.paramsDict[j] = modelPickle[j]
mySAMpy.ratioData = modelPickle['ratioData']
mySAMpy.model_type = modelPickle['model_type']
mySAMpy.model_mode = modelPickle['model_mode']
if mySAMpy.model_mode == 'temporal':
mySAMpy.temporalModelWindowSize = modelPickle['temporalModelWindowSize']
mySAMpy.model_type = 'mrd'
mySAMpy.model_num_inducing = modelPickle['model_num_inducing']
mySAMpy.model_num_iterations = modelPickle['model_num_iterations']
mySAMpy.model_init_iterations = modelPickle['model_init_iterations']
mySAMpy.verbose = modelPickle['verbose']
mySAMpy.Quser = modelPickle['Quser']
mySAMpy.optimiseRecall = modelPickle['optimiseRecall']
mySAMpy.kernelString = modelPickle['kernelString']
mySAMpy.calibrated = modelPickle['calibrated']
# try loading classification parameters for multiple model implementation
try:
mySAMpy.useMaxDistance = modelPickle['useMaxDistance']
except:
logging.warning('Failed to load useMaxDistace. Possible reasons: '
'Not saved or multiple model implementation')
mySAMpy.calibrateUnknown = modelPickle['calibrateUnknown']
if mySAMpy.calibrateUnknown:
mySAMpy.classificationDict = modelPickle['classificationDict']
# try:
# mySAMpy.listOfModels = modelPickle['listOfModels']
# mySAMpy.classifiers = modelPickle['classifiers']
# mySAMpy.classif_thresh = modelPickle['classif_thresh']
# mulClassLoadFail = False
# logging.info('Successfully loaded multiple model classifiers')
# except:
# mulClassLoadFail = True
# logging.info('Failed to load multiple model classifiers')
# pass
#
# # try loading classification parameters for single model implementation
# try:
# mySAMpy.varianceDirection = modelPickle['varianceDirection']
# mySAMpy.varianceThreshold = modelPickle['varianceThreshold']
# mySAMpy.bestDistanceIDX = modelPickle['bestDistanceIDX']
# logging.info('Successfully loaded single model classifiers')
# singClassLoadFail = False
# except:
# singClassLoadFail = True
# logging.info('Failed to load single model classifiers')
# pass
# if mulClassLoadFail and singClassLoadFail:
# raise ValueError('Failed to load model classifiers')
except IOError:
logging.warning('IO Exception reading ', found)
pass
if 'exp' in modelPath or 'best' in modelPath or 'backup' in modelPath:
fnameProto = '/'.join(modelPath.split('/')[:-1]) + '/' + dataPath.split('/')[-1] + '__' + driverName + \
'__' + mySAMpy.model_type + '__' + str(mySAMpy.experiment_number)
else:
fnameProto = modelPath + dataPath.split('/')[-1] + '__' + driverName + '__' + mySAMpy.model_type + \
'__' + str(mySAMpy.experiment_number)
logging.info('Full model name: ' + str(fnameProto))
logging.info('-------------------')
logging.info('')
mySAMpy.save_model = False
mySAMpy.economy_save = True
mySAMpy.visualise_output = False
# test_mode = True
mySAMpy.readData(dataPath, participantList)
# at this point, all the data that will be eventually used for training is contained in mySAMpy.Y
# and mySAMpy.L contains all labels if any (depending on mrd model or bgplvm model)
# mySAMpy.L is a list of labels while mySAMpy.Y is a numpy array of data
# mySAMpy.Y should have 2 dimensions, length of dimension 0 = number of instances
# length of dimension 1 = length of feature vector
if mySAMpy.model_mode != 'temporal':
# get list of labels
mySAMpy.textLabels = list(set(mySAMpy.L))
# convert L from list of strings to array of indices
mySAMpy.L = np.asarray([mySAMpy.textLabels.index(i) for i in mySAMpy.L])[:, None]
mySAMpy.textLabels = mySAMpy.textLabels
else:
mySAMpy.X, mySAMpy.Y = transformTimeSeriesToSeq(mySAMpy.Y1, mySAMpy.temporalModelWindowSize)
mySAMpy.L, mySAMpy.tmp = transformTimeSeriesToSeq(mySAMpy.U1, mySAMpy.temporalModelWindowSize)
mm = [mySAMpy]
# mm.append(mySAMpy)
# mm[0] contains root model
# this is the only model in the case of a single model
# or contains all info for the rest of the models in case of multiple models
#
if mySAMpy.model_mode == 'single' or mySAMpy.model_mode == 'temporal':
mm[0].participantList = ['all']
else:
mm[0].participantList = ['root'] + mySAMpy.textLabels
for k in range(len(mm[0].participantList)):
if mm[0].participantList[k] == 'all':
normaliseData = True
minData = len(mm[k].L)
mm[0].fname = fnameProto
mm[0].model_type = mySAMpy.model_type
Ntr = int(mySAMpy.ratioData * minData / 100)
else:
if k > 0:
mm.append(Driver())
# extract subset of data corresponding to this model
inds = [i for i in range(len(mm[0].Y['L'])) if mm[0].Y['L'][i] == k - 1]
mm[k].Y = mm[0].Y['Y'][inds]
mm[k].L = mm[0].Y['L'][inds]
mm[k].Quser = mm[0].Quser
mm[k].verbose = mm[0].verbose
logging.info('Object class: ' + str(mm[0].participantList[k]))
minData = len(inds)
mm[k].fname = fnameProto + '__L' + str(k - 1)
mm[0].listOfModels.append(mm[k].fname)
mm[k].model_type = 'bgplvm'
Ntr = int(mySAMpy.ratioData * minData / 100)
normaliseData = True
else:
normaliseData = False
mm[0].listOfModels = []
mm[0].fname = fnameProto
mm[0].SAMObject.kernelString = ''
minData = len(mm[0].L)
Ntr = int(mySAMpy.ratioData * minData / 100)
mm[k].modelLabel = mm[0].participantList[k]
if mm[0].model_mode != 'temporal':
[Yall, Lall, YtestAll, LtestAll] = mm[k].prepareData(mm[k].model_type, Ntr,
randSeed=0,
normalise=normaliseData)
mm[k].Yall = Yall
mm[k].Lall = Lall
mm[k].YtestAll = YtestAll
mm[k].LtestAll = LtestAll
elif mm[0].model_mode == 'temporal':
[Xall, Yall, Lall, XtestAll, YtestAll, LtestAll] = mm[k].prepareData(mm[k].model_type, Ntr,
randSeed=0,
normalise=normaliseData)
mm[k].Xall = Xall
mm[k].Yall = Yall
mm[k].Lall = Lall
mm[k].XtestAll = XtestAll
mm[k].YtestAll = YtestAll
mm[k].LtestAll = LtestAll
logging.info('minData = ' + str(minData))
logging.info('ratioData = ' + str(mySAMpy.ratioData))
logging.info('-------------------------------------------------------------------------------------------------')
if initMode == 'training':
samOptimiser.deleteModel(modelPath, 'exp')
for k in range(len(mm[0].participantList)):
# for k = 0 check if multiple model or not
if mm[0].participantList[k] != 'root':
logging.info("Training with " + str(mm[0].model_num_inducing) + ' inducing points for ' +
str(mm[0].model_init_iterations) + '|' + str(mm[0].model_num_iterations))
logging.info("Fname:" + str(mm[k].fname))
mm[k].training(mm[0].model_num_inducing, mm[0].model_num_iterations,
mm[0].model_init_iterations, mm[k].fname, mm[0].save_model,
mm[0].economy_save, keepIfPresent=False, kernelStr=mm[0].kernelString)
if mm[0].visualise_output:
ax = mm[k].SAMObject.visualise()
visualiseInfo = dict()
visualiseInfo['ax'] = ax
else:
visualiseInfo = None
else:
for k in range(len(mm[0].participantList)):
# for k = 0 check if multiple model or not
if mm[0].participantList[k] != 'root':
logging.info("Training with " + str(mm[0].model_num_inducing) + ' inducing points for ' +
str(mm[0].model_init_iterations) + '|' + str(mm[0].model_num_iterations))
mm[k].training(mm[0].model_num_inducing, mm[0].model_num_iterations,
mm[0].model_init_iterations, mm[k].fname, mm[0].save_model,
mm[0].economy_save, keepIfPresent=True, kernelStr=mm[0].kernelString)
return mm
def initialiseModels(argv, update, initMode='training'):
# argv[1] = dataPath
# argv[2] = modelPath
# argv[3] = driverName
# update = 'update' or 'new'
from SAM.SAM_Core import SAMDriver as Driver
dataPath = argv[0]
modelPath = argv[1]
driverName = argv[2]
print argv
stringCommand = 'from SAM.SAM_Drivers import ' + driverName + ' as Driver'
print stringCommand
exec stringCommand
mySAMpy = Driver()
mode = update
trainName = dataPath.split('/')[-1]
# participantList is extracted from number of subdirectories of dataPath
participantList = [
f for f in listdir(dataPath) if isdir(join(dataPath, f))
]
off = 17
print '-------------------'
print 'Training Settings:'
print
print 'Data Path: '.ljust(off), dataPath
print 'Model Path: '.ljust(off), modelPath
print 'Participants: '.ljust(off), participantList
print 'Model Root Name: '.ljust(off), trainName
print 'Training Mode:'.ljust(off), mode
print 'Driver:'.ljust(off), driverName
print '-------------------'
print 'Loading Parameters...'
print
temporalFlag = False
modeConfig = ''
found = ''
try:
parser = SafeConfigParser()
found = parser.read(dataPath + "/config.ini")
if parser.has_option(trainName, 'update_mode'):
modeConfig = parser.get(trainName, 'update_mode')
else:
modeConfig = 'update'
print modeConfig
except IOError:
pass
defaultParamsList = [
'experiment_number', 'model_type', 'model_num_inducing',
'model_num_iterations', 'model_init_iterations', 'verbose', 'Quser',
'kernelString', 'ratioData', 'update_mode', 'model_mode', 'windowSize'
]
mySAMpy.experiment_number = None
mySAMpy.model_type = None
mySAMpy.kernelString = None
mySAMpy.fname = None
mySAMpy.ratioData = None
if initMode == 'training' and (mode == 'new' or modeConfig == 'new'
or 'exp' not in modelPath):
print 'Loading training parameters from: \n ', '\t' + dataPath + "/config.ini"
try:
default = False
parser = SafeConfigParser()
parser.optionxform = str
found = parser.read(dataPath + "/config.ini")
# load parameters from config file
if parser.has_option(trainName, 'experiment_number'):
mySAMpy.experiment_number = int(
parser.get(trainName, 'experiment_number'))
elif '.pickle' in modelPath:
mySAMpy.experiment_number = int(
modelPath.split('__')[-2].replace('exp', '')) + 1
else:
fail = True
print 'No experiment_number found'
if parser.has_option(trainName, 'model_type'):
mySAMpy.model_type = parser.get(trainName, 'model_type')
else:
default = True
mySAMpy.model_type = 'mrd'
if parser.has_option(trainName, 'model_num_inducing'):
mySAMpy.model_num_inducing = int(
parser.get(trainName, 'model_num_inducing'))
else:
default = True
mySAMpy.model_num_inducing = 30
if parser.has_option(trainName, 'model_num_iterations'):
mySAMpy.model_num_iterations = int(
parser.get(trainName, 'model_num_iterations'))
else:
default = True
mySAMpy.model_num_iterations = 700
if parser.has_option(trainName, 'model_init_iterations'):
mySAMpy.model_init_iterations = int(
parser.get(trainName, 'model_init_iterations'))
else:
default = True
mySAMpy.model_init_iterations = 2000
if parser.has_option(trainName, 'verbose'):
mySAMpy.verbose = parser.get(trainName, 'verbose') == 'True'
else:
default = True
mySAMpy.verbose = False
if parser.has_option(trainName, 'model_mode'):
mySAMpy.model_mode = parser.get(trainName, 'model_mode')
if mySAMpy.model_mode == 'temporal' and parser.has_option(
trainName, 'windowSize'):
mySAMpy.windowSize = int(
parser.get(trainName, 'windowSize'))
else:
temporalFlag = True
else:
default = True
mySAMpy.model_mode = 'single'
if parser.has_option(trainName, 'Quser'):
mySAMpy.Quser = int(parser.get(trainName, 'Quser'))
else:
default = True
mySAMpy.Quser = 2
if parser.has_option(trainName, 'kernelString'):
mySAMpy.kernelString = parser.get(trainName, 'kernelString')
else:
default = True
mySAMpy.kernelString = "GPy.kern.RBF(Q, ARD=False) + GPy.kern.Bias(Q) + GPy.kern.White(Q)"
if parser.has_option(trainName, 'ratioData'):
mySAMpy.ratioData = int(parser.get(trainName, 'ratioData'))
else:
default = True
mySAMpy.ratioData = 50
if default:
print 'Default settings applied'
mySAMpy.paramsDict = dict()
mySAMpy.loadParameters(parser, trainName)
except IOError:
print 'IO Exception reading ', found
pass
else:
print 'Loading parameters from: \n ', '\t' + modelPath
try:
parser = SafeConfigParser()
parser.optionxform = str
found = parser.read(dataPath + "/config.ini")
# load parameters from config file
if parser.has_option(trainName, 'experiment_number'):
mySAMpy.experiment_number = int(
parser.get(trainName, 'experiment_number'))
else:
mySAMpy.experiment_number = int(
modelPath.split('__')[-2].replace('exp', ''))
modelPickle = pickle.load(open(modelPath + '.pickle', 'rb'))
mySAMpy.paramsDict = dict()
for j in parser.options(trainName):
if j not in defaultParamsList:
print j
mySAMpy.paramsDict[j] = modelPickle[j]
mySAMpy.ratioData = modelPickle['ratioData']
mySAMpy.model_type = modelPickle['model_type']
mySAMpy.model_mode = modelPickle['model_mode']
if mySAMpy.model_mode == 'temporal':
mySAMpy.windowSize = modelPickle['windowSize']
mySAMpy.model_type = 'mrd'
mySAMpy.model_num_inducing = modelPickle['model_num_inducing']
mySAMpy.model_num_iterations = modelPickle['model_num_iterations']
mySAMpy.model_init_iterations = modelPickle[
'model_init_iterations']
mySAMpy.verbose = modelPickle['verbose']
mySAMpy.Quser = modelPickle['Quser']
mySAMpy.kernelString = modelPickle['kernelString']
try:
mySAMpy.listOfModels = modelPickle['listOfModels']
mySAMpy.classifiers = modelPickle['classifiers']
mySAMpy.classif_thresh = modelPickle['classif_thresh']
except:
pass
except IOError:
print 'IO Exception reading ', found
pass
if 'exp' in modelPath:
fnameProto = '/'.join(modelPath.split('/')[:-1]) + '/' + dataPath.split('/')[-1] + '__' + driverName + \
'__' + mySAMpy.model_type + '__exp' + str(mySAMpy.experiment_number)
else:
fnameProto = modelPath + dataPath.split('/')[-1] + '__' + driverName + '__' + mySAMpy.model_type + \
'__exp' + str(mySAMpy.experiment_number)
print 'Full model name: \n', '\t' + fnameProto
print '-------------------'
print
mySAMpy.save_model = False
mySAMpy.economy_save = True
mySAMpy.visualise_output = False
# test_mode = True
mySAMpy.readData(dataPath, participantList)
# at this point, all the data that will be eventually used for training is contained in mySAMpy.Y
# and mySAMpy.L contains all labels if any (depending on mrd model or bgplvm model)
# mySAMpy.L is a list of labels while mySAMpy.Y is a numpy array of data
# mySAMpy.Y should have 2 dimensions, length of dimension 0 = number of instances
# length of dimension 1 = length of feature vector
if mySAMpy.model_mode != 'temporal':
# get list of labels
mySAMpy.textLabels = list(set(mySAMpy.L))
# convert L from list of strings to array of indices
mySAMpy.L = np.asarray(
[mySAMpy.textLabels.index(i) for i in mySAMpy.L])[:, None]
mySAMpy.textLabels = mySAMpy.textLabels
else:
mySAMpy.X, mySAMpy.Y = transformTimeSeriesToSeq(
mySAMpy.Y1, mySAMpy.windowSize)
mySAMpy.L, mySAMpy.tmp = transformTimeSeriesToSeq(
mySAMpy.U1, mySAMpy.windowSize)
mm = [mySAMpy]
# mm.append(mySAMpy)
# mm[0] contains root model
# this is the only model in the case of a single model
# or contains all info for the rest of the models in case of multiple models
#
if mySAMpy.model_mode == 'single' or mySAMpy.model_mode == 'temporal':
mm[0].participantList = ['all']
else:
mm[0].participantList = ['root'] + mySAMpy.textLabels
for k in range(len(mm[0].participantList)):
if mm[0].participantList[k] == 'all':
minData = len(mm[k].L)
mm[0].fname = fnameProto
mm[0].model_type = mySAMpy.model_type
Ntr = int(mySAMpy.ratioData * minData / 100)
else:
if k > 0:
mm.append(Driver())
# extract subset of data corresponding to this model
inds = [
i for i in range(len(mm[0].Y['L']))
if mm[0].Y['L'][i] == k - 1
]
mm[k].Y = mm[0].Y['Y'][inds]
mm[k].L = mm[0].Y['L'][inds]
mm[k].Quser = mm[0].Quser
mm[k].verbose = mm[0].verbose
print 'Object class: ', mm[0].participantList[k]
minData = len(inds)
mm[k].fname = fnameProto + '__L' + str(k - 1)
mm[0].listOfModels.append(mm[k].fname)
mm[k].model_type = 'bgplvm'
Ntr = int(mySAMpy.ratioData * minData / 100)
else:
mm[0].listOfModels = []
mm[0].fname = fnameProto
mm[0].SAMObject.kernelString = ''
minData = len(mm[0].L)
Ntr = int(mySAMpy.ratioData * minData / 100)
mm[k].modelLabel = mm[0].participantList[k]
if mm[0].model_mode != 'temporal':
[Yall, Lall, YtestAll,
LtestAll] = mm[k].prepareData(mm[k].model_type,
Ntr,
randSeed=mm[0].experiment_number)
mm[k].Yall = Yall
mm[k].Lall = Lall
mm[k].YtestAll = YtestAll
mm[k].LtestAll = LtestAll
elif mm[0].model_mode == 'temporal':
[Xall, Yall, Lall, XtestAll, YtestAll,
LtestAll] = mm[k].prepareData(mm[k].model_type,
Ntr,
randSeed=mm[0].experiment_number)
mm[k].Xall = Xall
mm[k].Yall = Yall
mm[k].Lall = Lall
mm[k].XtestAll = XtestAll
mm[k].YtestAll = YtestAll
mm[k].LtestAll = LtestAll
print 'minData = ' + str(minData)
print 'ratioData = ' + str(mySAMpy.ratioData)
if initMode == 'training':
for k in range(len(mm[0].participantList)):
# for k = 0 check if multiple model or not
if mm[0].participantList[k] != 'root':
print "Training with ", mm[0].model_num_inducing, 'inducing points for ', \
mm[0].model_init_iterations, '|', mm[0].model_num_iterations
mm[k].training(mm[0].model_num_inducing,
mm[0].model_num_iterations,
mm[0].model_init_iterations,
mm[k].fname,
mm[0].save_model,
mm[0].economy_save,
keepIfPresent=False,
kernelStr=mm[0].kernelString)
if mm[0].visualise_output:
ax = mm[k].SAMObject.visualise()
visualiseInfo = dict()
visualiseInfo['ax'] = ax
else:
visualiseInfo = None
else:
for k in range(len(mm[0].participantList)):
# for k = 0 check if multiple model or not
if mm[0].participantList[k] != 'root':
print "Training with ", mm[0].model_num_inducing, 'inducing points for ', \
mm[0].model_init_iterations, '|', mm[0].model_num_iterations
mm[k].training(mm[0].model_num_inducing,
mm[0].model_num_iterations,
mm[0].model_init_iterations,
mm[k].fname,
mm[0].save_model,
mm[0].economy_save,
keepIfPresent=True,
kernelStr=mm[0].kernelString)
return mm