def pipeline(self,func,data,train):
import os
os.system("taskset -p 0xff %d" % os.getpid())
func.acts=self.acts
logger.debug('Starting .... %s' % (func.shortrunname))
Tdata=func.preprocessor.process(self.datasetdscr, data)
logger.debug('Preprocessing Finished %s' % (func.preprocessor.shortname()))
Sdata=prepare_segment2(func,Tdata,self.datasetdscr)
logger.debug('Segmentation Finished %d segment created %s' % (len(Sdata.set_window), func.segmentor.shortname()))
Sdata.set=featureExtraction(func.featureExtractor,self.datasetdscr,Sdata,True)
logger.debug('FeatureExtraction Finished shape %s , %s' % (str(Sdata.set.shape), func.featureExtractor.shortname()))
if(train):
func.classifier.createmodel(Sdata.set[0].shape,len(self.acts))
func.classifier.setWeight(self.weight)
logger.debug('Classifier model created %s' % (func.classifier.shortname()))
func.classifier.train(Sdata.set, Sdata.label)
logger.debug('Classifier model trained %s' % (func.classifier.shortname()))
logger.info("Evaluating....")
result=Data('Result')
result.shortrunname=func.shortrunname
result.Sdata=Sdata
result.functions={}
for f in func.__dict__:
obj = func.__dict__[f]
if isinstance(obj, MyTask):
result.functions[f]=(obj.shortname(),obj.params)
result.predicted =func.classifier.predict(Sdata.set)
result.predicted_classes=func.classifier.predict_classes(Sdata.set)
pred_events =func.combiner.combine(Sdata.s_event_list,Sdata.set_window,result.predicted)
logger.debug('events merged %s' % (func.combiner.shortname()))
result.pred_events =pred_events
result.real_events =data.a_events
result.event_cm =event_confusion_matrix(data.a_events,pred_events,self.acts)
result.quality =CMbasedMetric(result.event_cm,'macro',self.weight)
#eventeval=EventBasedMetric(Sdata.a_events,pred_events,self.acts)
logger.debug('Evalution quality is %s'%result.quality)
return result
def fusion(self, results, real_events, isTrain):
intree = IntervalTree()
logger.info("\n=======================fusion activties ========")
# intree = IntervalTree()
# Segmentaion ###########################
for indx, tacts in enumerate(self.gacts):
result = results[indx]
for i in range(0, len(result.Sdata.set_window)):
idx = result.Sdata.set_window[i]
start = result.Sdata.s_event_list[idx[0], 1]
end = result.Sdata.s_event_list[idx[-1], 1]
rcls = result.Sdata.label[i]
pcls = result.predicted_classes[i]
fullprob = result.predicted[i]
if (end == start):
continue
d = Data(str(i))
d.real = rcls
d.pred = pcls
d.pred_prob = fullprob
if (isTrain):
self.train_quality[indx] = result.quality
d.gindx = indx
# {'real':rcls,'pred':pcls,'pred_prob':fullprob,'train_q':result.quality}
intree[start:end] = d
intree.split_overlaps()
segments = defaultdict(dict)
for item in intree.items():
segments[item.begin.value << 64
| item.end.value]['begin'] = item.begin
segments[item.begin.value << 64 | item.end.value]['end'] = item.end
segments[item.begin.value << 64
| item.end.value][item.data.gindx] = item.data
# Feature Extraction ###########################
f = np.zeros((len(segments), len(self.gacts) * len(self.acts)))
label = np.zeros(len(segments))
times = []
iseg = 0
for timeseg in segments:
seg = segments[timeseg]
b = seg['begin']
e = seg['end']
times.append({'begin': b, 'end': e})
for indx in range(len(self.gacts)):
if (indx in seg):
label[iseg] = seg[indx].real
start = indx * len(self.acts)
end = (indx + 1) * len(self.acts)
if (self.train_quality[indx]['f1'] < 0.1):
continue
f[iseg, start:end] = seg[indx].pred_prob
iseg += 1
#TRAIN #######################
if (isTrain):
inputsize = (len(f[0]), )
outputsize = len(self.acts)
self.fusion_model = tf.keras.models.Sequential([
tf.keras.layers.Dense(128, input_shape=inputsize),
tf.keras.layers.Dense(512, activation=tf.nn.relu),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(outputsize, activation=tf.nn.softmax)
],
name='fusion')
if (np.max(label) == 0):
# self.trained=False
cw = np.ones(len(self.acts))
else:
cw = compute_class_weight("balanced", self.acts, label)
self.fusion_model.summary()
self.fusion_model.compile(
optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=[
tf.keras.metrics.SparseCategoricalAccuracy(name='acc')
])
self.fusion_model.fit(f, label, epochs=10, class_weight=cw)
#EVALUATE #######################
result = Data('result')
result.results = results
result.predicted = self.fusion_model.predict(f)
result.predicted_classes = self.fusion_model.predict_classes(f)
# predicted = np.argmax(model.predict(f), axis=1)
pred_events = []
ptree = {}
epsilon = pd.to_timedelta('1s')
for i in range(len(f)):
start = times[i]['begin']
end = times[i]['end']
pclass = result.predicted_classes[i]
pred_events.append({
'Activity': pclass,
'StartTime': start,
'EndTime': end
})
pred_events = pd.DataFrame(pred_events)
pred_events = pred_events.sort_values(['StartTime'])
pred_events = pred_events.reset_index()
pred_events = pred_events.drop(['index'], axis=1)
result.shortrunname = "fusion model" + str(
{r: results[r].shortrunname
for r in results})
result.times = times
result.pred_events = pred_events
result.real_events = real_events
result.event_cm = event_confusion_matrix(result.real_events,
result.pred_events, self.acts)
result.quality = CMbasedMetric(result.event_cm, 'macro')
result.functions = {r: results[r].functions for r in results}
logger.debug('Evalution quality is %s' % result.quality)
return result
def fusion(self, results, real_events, isTrain):
intree = IntervalTree()
logger.info("\n=======================fusion activties ========")
# intree = IntervalTree()
# Segmentaion ###########################
for indx, tacts in enumerate(self.gacts):
result = results[indx]
for i in range(0, len(result.Sdata.set_window)):
idx = result.Sdata.set_window[i]
start = result.Sdata.s_event_list[idx[0], 1]
end = result.Sdata.s_event_list[idx[-1], 1]
rcls = result.Sdata.label[i]
pcls = result.predicted_classes[i]
fullprob = result.predicted[i]
if (end == start):
continue
d = Data(str(i))
d.real = rcls
d.pred = pcls
d.pred_prob = fullprob
if (isTrain):
self.train_quality[indx] = result.quality
d.gindx = indx
# {'real':rcls,'pred':pcls,'pred_prob':fullprob,'train_q':result.quality}
intree[start:end] = d
intree.split_overlaps()
segments = defaultdict(dict)
for item in intree.items():
segments[item.begin.value << 64
| item.end.value]['begin'] = item.begin
segments[item.begin.value << 64 | item.end.value]['end'] = item.end
segments[item.begin.value << 64
| item.end.value][item.data.gindx] = item.data
probs = np.zeros((len(segments), len(self.acts)))
# Feature Extraction ###########################
label = np.zeros(len(segments))
times = []
iseg = 0
for timeseg in segments:
seg = segments[timeseg]
b = seg['begin']
e = seg['end']
times.append({'begin': b, 'end': e})
for indx in range(len(self.gacts)):
if (indx in seg):
label[iseg] = seg[indx].real
if (self.mode == 1):
probs[iseg, :] += np.array(
seg[indx].pred_prob
) * self.train_quality[indx]['f1'] / len(self.gacts)
elif self.mode == 2:
p = np.zeros(len(self.acts))
p[np.argmax(seg[indx].pred_prob)] = 1
probs[iseg, :] += p
else:
p = np.zeros(len(self.acts))
p[np.argmax(seg[indx].pred_prob
)] = self.train_quality[indx]['f1']
probs[iseg, :] += p
iseg += 1
plabel = np.argmax(probs, 1)
#EVALUATE #######################
result = Data('result')
result.results = results
result.predicted = probs
result.predicted_classes = plabel
# predicted = np.argmax(model.predict(f), axis=1)
pred_events = []
ptree = {}
epsilon = pd.to_timedelta('1s')
for i in range(len(segments)):
start = times[i]['begin']
end = times[i]['end']
pclass = result.predicted_classes[i]
pred_events.append({
'Activity': pclass,
'StartTime': start,
'EndTime': end
})
pred_events = pd.DataFrame(pred_events)
pred_events = pred_events.sort_values(['StartTime'])
pred_events = pred_events.reset_index()
pred_events = pred_events.drop(['index'], axis=1)
result.shortrunname = "fusion model" + str(
{r: results[r].shortrunname
for r in results})
result.times = times
result.pred_events = pred_events
result.real_events = real_events
result.event_cm = event_confusion_matrix(result.real_events,
result.pred_events, self.acts)
result.quality = CMbasedMetric(result.event_cm, 'macro')
result.functions = {r: results[r].functions for r in results}
logger.debug('Evalution quality is %s' % result.quality)
return result
model.evaluate(f,label)
combiner=EmptyCombiner()
predicted=model.predict_classes(f)
# predicted = np.argmax(model.predict(f), axis=1)
pred_events = []
ptree = {}
epsilon=pd.to_timedelta('1s')
for i in range(len(f)):
start = times[i][0]
end = times[i][1]
pclass = predicted[i]
pred_events.append({'Activity': pclass, 'StartTime': start, 'EndTime': end})
pred_events = pd.DataFrame(pred_events)
pred_events = pred_events.sort_values(['StartTime'])
pred_events = pred_events.reset_index()
pred_events = pred_events.drop(['index'], axis=1)
result=Data('result')
result.pred_events =pred_events
result.real_events =savedata.train_results[11].real_events
result.event_cm =event_confusion_matrix(result.real_events,result.pred_events,savedata.acts)
result.quality =CMbasedMetric(result.event_cm,'macro')
print(result.quality)