def processData():
#takes data from database and process it to produce analysisInfo with features that can be used for machine learning
children=parse.parseData()
analysis = extract(children)
startT=findStartDate(analysis)
endT=findEndDate(analysis)
print "date diff", dateDiff(startT, endT)
extend(children, analysis, startT, endT)
addSleepChart(children, analysis)
computeRateNtTr(analysis)
compBigImprov(analysis)
computeCompleteDevRate(analysis)
userReport(analysis)
#searchMissingUsers(analysis)
addFeatureForML(children, analysis)
computeCorrCoef(analysis)
return children, analysis, startT, endT
def dataForInitialAnalysis(children, analysis):
#generates data for machine learning with "initial" data (prior history on sleep disorder) provided from the users
index=analysis.keys()
random.shuffle(index)
#print "Does shuffle work", index
#collect data in machine learning format
X=[]
Y=[]
for i in index:
init=children[i].initial
if analysis[i].start_date:
s_date=dateDiff(start, analysis[i].start_date)
#print i, s_date, analysis[i].start_date
X.append([init.month_count, init.night_count, s_date])
Y.append(len(analysis[i].use))
X=numpy.array(X)
Y=numpy.array(Y)
print 'mean', numpy.mean(X[:,0])
print 'sdt', numpy.std(X[:,0])
print 'sample X', X[:10]
plotInitData(X,Y)
return index, X, Y
def extend(children, analysis, start, end):
#adds additional fields to analysisInfo()
#such as time_for_bed (vector), event1_time (vector), dist_event, values for dev
for ch in children.values():
cid=ch.child_id
for date, d in sorted(ch.dates.items()):
t_bed=d.time_for_bed
t_asleep=d.event1_time
if len(t_bed)>0 or len(t_asleep)>0:
if len(t_bed)>0:
analysis[cid].use.append(dateDiff(start, t_bed[0]))
else:
analysis[cid].use.append(dateDiff(start, t_asleep[0]))
#print "gg", analysis[cid].use
dst_event=d.dev_time_cu
num_tr=len(dst_event)
if num_tr>0:
if len(t_bed)>0:
analysis[cid].dist_event.append([dateDiff(start, t_bed[0]), num_tr])
elif len(t_asleep)>0:
analysis[cid].dist_event.append([dateDiff(start, t_asleep[0]), num_tr])
else:
dev_d=dtToStr((strToDT(dst_event[0])-datetime.timedelta(hours=8)))
#print '???', dst_event
analysis[cid].dist_event.append([dateDiff(start, dev_d), num_tr])
#print 'device info:', d.device
if d.device is not None:
for r in d.device.react:
device_times=d.device.device_start_stop
#print device_times
num=len(device_times)
if num>0:
for times in device_times:
#print times
if len(t_bed)>0:
analysis[cid].dev[r].append([dateDiff(start, t_bed[0]),num ])
elif len(t_asleep)>0:
analysis[cid].dev[r].append([dateDiff(start, t_asleep[0]),num ])
else:
t_device=dtToStr((strToDT(device_times[0][0])-datetime.timedelta(hours=8)))
analysis[cid].dev[r].append([dateDiff(start, t_device),num ])
if len(d.device.react)==0:
device_times=d.device.device_start_stop
if len(device_times)>0:
r='no react'
analysis[cid].dev[r]=[]
#print 'device no react', device_times
num=len(device_times)
if num>0:
for times in device_times:
#print times
if len(t_bed)>0:
analysis[cid].dev[r].append([dateDiff(start, t_bed[0]),num ])
elif len(t_asleep)>0:
analysis[cid].dev[r].append([dateDiff(start, t_asleep[0]),num ])
else:
t_device=dtToStr((strToDT(device_times[0][0])-datetime.timedelta(hours=8)))
analysis[cid].dev[r].append([dateDiff(start, t_device),num ])
