def train(self, datasetdscr, data, acts):
self.gacts = self.groupize(datasetdscr, acts)
self.acts = acts
self.strategies = {}
self.acts_name = {}
train_results = {}
self.train_quality = {}
intree = IntervalTree()
# intree = IntervalTree()
for indx, tacts in enumerate(self.gacts):
logger.info("=======================working on activties " +
tacts.__str__() + "=========")
Tdata = self.justifySet(tacts, data, False)
self.acts_name[indx] = datasetdscr.activities[tacts]
self.strategies[indx] = ml_strategy.Simple.SimpleStrategy()
self.strategies[indx].train(datasetdscr, Tdata,
list(range(len(tacts))))
if ('result' in self.strategies[indx].bestOpt.result):
result = self.strategies[indx].bestOpt.result['result']
else:
result = self.strategies[indx].test(Tdata)
utils.saveState(self.strategies[indx].get_info(), 'groupact',
str(indx))
train_results[indx] = result
utils.saveState(
[self.strategies[indx].get_info() for indx in self.strategies],
'groupact', 'all')
return self.fusion(train_results, data.a_events, True)
def train(self, datasetdscr, data, acts):
self.gacts = self.groupize(datasetdscr, acts)
self.acts = acts
self.strategies = {}
self.acts_name = {}
train_results = {}
self.train_quality = {}
intree = IntervalTree()
# intree = IntervalTree()
for indx, tacts in enumerate(self.gacts):
logger.info("=======================working on activties " +
tacts.__str__() + "=========")
weight = np.ones(len(acts))
for a in tacts:
weight[a] = self.alpha
datasetdscr.indx = indx
self.strategies[indx] = ml_strategy.Simple.SimpleStrategy()
self.strategies[indx].train(datasetdscr, data, acts, weight)
if ('result' in self.strategies[indx].bestOpt.result):
result = self.strategies[indx].bestOpt.result['result']
else:
result = self.strategies[indx].test(data)
utils.saveState(self.strategies[indx].get_info(), 'wgroupact',
'n-%d' % (indx))
train_results[indx] = result
utils.saveState(
[self.strategies[indx].get_info() for indx in self.strategies],
'wgroupact', 'n-all')
return self.fusion(train_results, data.a_events, True)
def run(args):
logger = logging.getLogger(__file__)
logger.debug(f'args={args}')
if(args.dataset<0):
logger.error('Invalid dataset argument')
return
if(args.mlstrategy<0):
logger.error('Invalid mlstrategy argument')
return
if(args.evaluation<0):
logger.error('Invalid evaluation argument')
return
datasetdscr = methods.dataset[args.dataset]['method']().load()
strategy = methods.mlstrategy[args.mlstrategy]['method']()
evaluation=methods.evaluation[args.evaluation]['method']()
if(args.feature_extraction>=0): methods.feature_extraction=[methods.feature_extraction[args.feature_extraction]]
if(args.segmentation>=0): methods.segmentation=[methods.segmentation[args.segmentation]]
if(args.classifier>=0): methods.classifier=[methods.classifier[args.classifier]]
evalres = evaluation.evaluate(datasetdscr, strategy)
run_date=datetime.now().strftime('%y%m%d_%H-%M-%S')
run_info={'dataset':datasetdscr.shortname(),'run_date':run_date,'dataset_path':datasetdscr.data_path, 'strategy':strategy.shortname(),'evalution':evaluation.shortname()}
compressdata={'run_info':run_info, 'folds':{k:{'quality':evalres[k]['test'].quality,'runname':evalres[k]['test'].shortrunname} for k in evalres}}
utils.saveState([compressdata],'%s-%s/' % (run_date,datasetdscr.shortname()),'info')
utils.saveState([run_info,datasetdscr, evalres],'%s-%s/' % (run_date,datasetdscr.shortname()))
for i in range(len(evalres)):
logger.debug(f'Evalution quality fold={i} is {evalres[i]["test"].quality}')
logger.debug(f'run finished args={args}')
def load_run_table(file):
runtable=utils.loadState(file,'runtable1',raiseException=False)
if(runtable is None):
res=utils.loadState(file)
if(len(res)!=3):
#raise Error
logger.warn('File %s can not import'%file)
return
[run_info,datasetdscr,evalres]=res
runtable=getRunTable(run_info,datasetdscr,evalres)
utils.saveState(runtable,file,'runtable1')
return runtable
def load_run_info(file):
runinfo=utils.loadState(file,'info',raiseException=False)
if(runinfo is None):
try:
res=utils.loadState(file)
if(len(res)!=3):
#raise Error
logger.warn('File %s can not import'%file)
return
[run_info,datasetdscr,evalres]=res
runinfo=getRunInfo(run_info,datasetdscr,evalres)
utils.saveState([runinfo],file,'info')
return runinfo
except:
logger.warn('File %s can not import'%file)
return
return runinfo[0]
def get(key, valf):
hkey = hashkey(key)
try:
val = utils.loadState(cachefolder, hkey)
logger.debug(f'cached file found {key} {hkey}')
except Exception as e:
if not (os.path.exists(f'save_data/{hkey}')):
logger.debug(f'cached file not found {key} {hkey}')
else:
logger.error(f'error in cached {e}', exc_info=True)
val = valf()
utils.saveState(val, cachefolder, hkey)
with open(f'save_data/{cachefolder}/{hkey}.txt', 'w') as f:
print(key, file=f)
f.close()
return val
def create(real, pred, filename):
evalres = [{}]
evalres[0]['test'] = Data('test res')
evalres[0]['test'].real_events = vs.convert2event(real)
evalres[0]['test'].pred_events = vs.convert2event(pred)
evalres[0]['test'].quality = {}
dataset = Data('MyDataset')
dataset.activities = ['None', 'Act']
dataset.activity_events = evalres[0]['test'].real_events
dataset.activities_map_inverse = {
k: v
for v, k in enumerate(dataset.activities)
}
dataset.activities_map = {v: k for v, k in enumerate(dataset.activities)}
dataset.sensor_events = pd.DataFrame()
runinfo = filename
utils.saveState([runinfo, dataset, evalres], filename)