Python p_data_action Examples

Example #1

    def choose_action_phase2(self, stage, prev_data):
        maxratio = 0
        astars = []

        selector = {
            'a': world.possible_actions_phase2a,
            'b': world.possible_actions_phase2b
        }
        possible_actions = selector[stage]()

        for a in possible_actions:
            dt = world.make_forced_action(a, True)
            df = world.make_forced_action(a, False)
            pt = model.p_data_action(dt, a, prev_data)
            pf = model.p_data_action(df, a, prev_data)
            print a, pt, pf, pt / pf
            this_ratio = pt / pf
            if this_ratio > maxratio:
                astars = [a]
                maxratio = this_ratio
            elif this_ratio == maxratio:
                astars.append(a)

        #print astars
        choice = random.choice(astars)
        return choice

Example #2

    def success_probability(self, action, prev_data=[]):

        data_no, data_yes = world.possible_data(action)
        p_yes = model.p_data_action(data_yes, action, prev_data)
        p_no = model.p_data_action(data_no, action, prev_data)

        return p_yes / (p_yes + p_no)

Example #3

File: learners.py Project: fiiiu/active-learning

	def success_probability(self, action, prev_data=[]):

		data_no, data_yes=world.possible_data(action)
		p_yes=model.p_data_action(data_yes, action, prev_data)
		p_no=model.p_data_action(data_no, action, prev_data)
		
		return p_yes/(p_yes+p_no)

Example #4

File: learners.py Project: fiiiu/active-learning

	def choose_action_phase2(self, stage, prev_data):
		maxratio=0
		astars=[]

		selector={'a': world.possible_actions_phase2a, 'b': world.possible_actions_phase2b}
		possible_actions=selector[stage]()

		for a in possible_actions:
			dt=world.make_forced_action(a,True)
			df=world.make_forced_action(a,False)
			pt=model.p_data_action(dt,a,prev_data)
			pf=model.p_data_action(df,a,prev_data)
			print a, pt, pf, pt/pf
			this_ratio=pt/pf
			if this_ratio > maxratio:
				astars=[a]
				maxratio=this_ratio
			elif this_ratio == maxratio:
				astars.append(a)

		#print astars
		choice=random.choice(astars)
		return choice

Example #5

File: run_phyptester.py Project: fiiiu/ActiveLearning

#  	print 't: {0}, p: {1}, ppost: {2}'.format(t, model.p_theory(t),\
#  													model.p_theory_data(t,d0)\
#  													)


d0p=Datapoint.Datapoint((t1,m0), True)
d1=Datapoint.Datapoint((t1,m1), True)
#for h in model.singleh_space:
#print model.p_data_action(d0p, (t1,m0), []), model.p_data_action(d0p, (t1,m0), d0)

action=(t2,m1)
n1=0
n2=0
p1s=[]
p2s=[]

d0[0].display()
print action
for dat in world.possible_data(action):
	p1=model.p_data_action(dat, (t2,m1), [])
	p2=model.p_data_action(dat, (t2,m1), d0)
	
	n1+=p1
	n2+=p2

	p1s.append(p1)
	p2s.append(p2)


print [p/n1 for p in p1s]
print [p/n2 for p in p2s]

Example #6

File: run4.py Project: fiiiu/ActiveLearning

lposc = [0] * 12
hposc = [0] * 12
lposs = [0] * 12
hposs = [0] * 12
lposi = [0] * 12
hposi = [0] * 12

data = Data.Data()
data.read(astext=False)
dind = data.data[data.get_kids()[3]]

[d.display() for d in dind]
# dind[-1].active=False

print low_model.p_data_action(dind[0], world.possible_actions()[3])
print high_model.p_data_action(dind[0], world.possible_actions()[3])

dind[0].active = True

print low_model.p_data_action(dind[0], world.possible_actions()[3])
print high_model.p_data_action(dind[0], world.possible_actions()[3])


norm = True
lostart = time.clock()
for t in range(12):
    lposc[t] = low_model.p_theory_data(t, dcol, normalized=norm)
    lposs[t] = low_model.p_theory_data(t, dsha, normalized=norm)
    lposi[t] = low_model.p_theory_data(t, dind, normalized=norm)

Example #7

File: run4.py Project: fiiiu/ActiveLearning

lposc = [0] * 12
hposc = [0] * 12
lposs = [0] * 12
hposs = [0] * 12
lposi = [0] * 12
hposi = [0] * 12

data = Data.Data()
data.read(astext=False)
dind = data.data[data.get_kids()[3]]

[d.display() for d in dind]
#dind[-1].active=False

print low_model.p_data_action(dind[0], world.possible_actions()[3])
print high_model.p_data_action(dind[0], world.possible_actions()[3])

dind[0].active = True

print low_model.p_data_action(dind[0], world.possible_actions()[3])
print high_model.p_data_action(dind[0], world.possible_actions()[3])

norm = True
lostart = time.clock()
for t in range(12):
    lposc[t] = low_model.p_theory_data(t, dcol, normalized=norm)
    lposs[t] = low_model.p_theory_data(t, dsha, normalized=norm)
    lposi[t] = low_model.p_theory_data(t, dind, normalized=norm)

# l=[]

Example #8

File: run_phyptester.py Project: fiiiu/ActiveLearning

# for t in model.t_space:
#  	print 't: {0}, p: {1}, ppost: {2}'.format(t, model.p_theory(t),\
#  													model.p_theory_data(t,d0)\
#  													)

d0p = Datapoint.Datapoint((t1, m0), True)
d1 = Datapoint.Datapoint((t1, m1), True)
#for h in model.singleh_space:
#print model.p_data_action(d0p, (t1,m0), []), model.p_data_action(d0p, (t1,m0), d0)

action = (t2, m1)
n1 = 0
n2 = 0
p1s = []
p2s = []

d0[0].display()
print action
for dat in world.possible_data(action):
    p1 = model.p_data_action(dat, (t2, m1), [])
    p2 = model.p_data_action(dat, (t2, m1), d0)

    n1 += p1
    n2 += p2

    p1s.append(p1)
    p2s.append(p2)

print[p / n1 for p in p1s]
print[p / n2 for p in p2s]