def setUp(self):
nodedata = NodeData.load("unittestlgdict.txt")
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
self.lgb = LGBayesianNetwork(nodedata)
def setUp(self):
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
nodedata = NodeData.load("unittestdict.txt")
self.bn = DiscreteBayesianNetwork(nodedata)
self.fn = TableCPDFactorization(self.bn)
def setUp(self):
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
nodedata = NodeData()
nodedata.load("unittestdict.txt")
self.instance = DiscreteBayesianNetwork(skel, nodedata)
def set_bayesnet(self):
nd = NodeData()
skel = GraphSkeleton()
nd.load(self.file)
skel.load(self.file)
skel.toporder()
self.bn = DiscreteBayesianNetwork(skel, nd)
def setUp(self):
nodedata = NodeData.load("unittestlgdict.txt")
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
self.lgb = LGBayesianNetwork(nodedata)
def setUp(self):
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
nodedata = NodeData.load("unittestdict.txt")
self.bn = DiscreteBayesianNetwork(nodedata)
self.fn = TableCPDFactorization(self.bn)
def setUp(self):
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
nodedata = NodeData()
nodedata.load("unittestdict.txt")
self.instance = DiscreteBayesianNetwork(skel, nodedata)
def buildBN(trainingData, binstyleDict, numbinsDict,
**kwargs): # need to modify to accept skel or skelfile
discretized_training_data, bin_ranges = discretizeTrainingData(
trainingData, binstyleDict, numbinsDict, True)
print 'discret training ', discretized_training_data
if 'skel' in kwargs:
# load file into skeleton
if isinstance(kwargs['skel'], basestring):
skel = GraphSkeleton()
skel.load(kwargs['skel'])
skel.toporder()
else:
skel = kwargs['skel']
# learn bayesian network
learner = PGMLearner()
# baynet = learner.discrete_mle_estimateparams(skel, discretized_training_data)
# baynet = discrete_estimatebn(learner, discretized_training_data, skel, 0.05, 1)
baynet = discrete_mle_estimateparams2(
skel, discretized_training_data
) # using discrete_mle_estimateparams2 written as function in this file, not calling from libpgm
return baynet
def setUp(self):
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
nodedata = NodeData.load("unittestdict.txt")
self.instance = DiscreteBayesianNetwork(nodedata)
self.factor = TableCPDFactor("Grade", self.instance)
self.factor2 = TableCPDFactor("Letter", self.instance)
def setUp(self):
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
nodedata = NodeData.load("unittestdict.txt")
self.instance = DiscreteBayesianNetwork(nodedata)
self.factor = TableCPDFactor("Grade", self.instance)
self.factor2 = TableCPDFactor("Letter", self.instance)
def test_hybn_mte_estimateparams(self):
skel = GraphSkeleton()
skel.load("../tests/bn_skeleton.txt")
skel.toporder()
with open('../tests/dataBR2.json', 'r') as f:
samples = eval(f.read())
result = self.l.hybn_mte_estimateparams(self.skel, self.samplelgseq)
def getTableCPD():
nd = NodeData()
skel = GraphSkeleton()
jsonpath = ""
nd.load(jsonpath)
skel.load(jsonpath)
bn = DiscreteBayesianNetwork(skel, nd)
tablecpd = TableCPDFactorization(bn)
return tablecpd
def getTableCPD():
nd = NodeData()
skel = GraphSkeleton()
jsonpath = "./graph/graph_example.txt"
nd.load(jsonpath)
skel.load(jsonpath)
# load Bayesian network
bn = DiscreteBayesianNetwork(skel, nd)
tablecpd = TableCPDFactorization(bn)
return tablecpd
def getTableCPD(): nd = NodeData() skel = GraphSkeleton() jsonpath = "job_interview.txt" nd.load(jsonpath) skel.load(jsonpath) #load bayesian network bn = DiscreteBayesianNetwork(skel, nd) tablecpd = TableCPDFactorization(bn) return tablecpd
class TestOrderedSkeleton(unittest.TestCase):
def setUp(self):
self.os = OrderedSkeleton()
self.os.load("unittestdict.txt")
self.gs = GraphSkeleton()
self.gs.load("unittestdict.txt")
def test_constructor(self):
self.assertNotEqual(self.os.V, self.gs.V)
self.gs.toporder()
self.assertEqual(self.os.V, self.gs.V)
def load(self, file_name):
#### Load BN
nd = NodeData()
skel = GraphSkeleton()
nd.load(file_name) # any input file
skel.load(file_name)
# topologically order graphskeleton
skel.toporder()
super(DiscreteBayesianNetworkExt, self).__init__(skel, nd)
def test_libpgm(df1):
data = df1.T.to_dict().values()
#pprint(data)
skel = GraphSkeleton()
skel.load("bn_struct.txt")
learner = PGMLearner()
result = learner.discrete_mle_estimateparams(skel, data)
print json.dumps(result.Vdata, indent=2)
def load(self, file_name):
#### Load BN
nd = NodeData()
skel = GraphSkeleton()
nd.load(file_name) # any input file
skel.load(file_name)
# topologically order graphskeleton
skel.toporder()
super(DiscreteBayesianNetworkExt, self).__init__(skel, nd)
##TODO load evidence
def learnBN(fdata_array, bn_file):
bn_path = os.path.join(experiment_dir, 'parameters', bn_file + '.txt')
skel = GraphSkeleton()
skel.load(bn_path)
skel.toporder()
learner = PGMLearner()
bn = learner.discrete_mle_estimateparams(skel, fdata_array)
return bn
class TestOrderedSkeleton(unittest.TestCase):
def setUp(self):
self.os = OrderedSkeleton()
self.os.load("unittestdict.txt")
self.gs = GraphSkeleton()
self.gs.load("unittestdict.txt")
def test_constructor(self):
self.assertNotEqual(self.os.V, self.gs.V)
self.gs.toporder()
self.assertEqual(self.os.V, self.gs.V)
class TestDynDiscBayesianNetwork(unittest.TestCase):
def setUp(self):
self.nd = NodeData.load("unittestdyndict.txt")
self.skel = GraphSkeleton()
self.skel.load("unittestdyndict.txt")
self.skel.toporder()
self.d = DynDiscBayesianNetwork(self.skel, self.nd)
def test_randomsample(self):
sample = self.d.randomsample(10)
for i in range(1, 10):
self.assertEqual(sample[0]['Difficulty'], sample[i]['Difficulty'])
def loadbn(param_file):
"""
This function loads the bn model into the workspace from its associated .txt file.
"""
file_path = os.path.join(experiment_dir, 'parameters', param_file + '.txt')
nd = NodeData()
skel = GraphSkeleton()
nd.load(file_path)
skel.load(file_path)
skel.toporder()
bn = DiscreteBayesianNetwork(skel, nd)
return bn
class TestDynDiscBayesianNetwork(unittest.TestCase):
def setUp(self):
self.nd = NodeData.load("unittestdyndict.txt")
self.skel = GraphSkeleton()
self.skel.load("unittestdyndict.txt")
self.skel.toporder()
self.d = DynDiscBayesianNetwork(self.skel, self.nd)
def test_randomsample(self):
sample = self.d.randomsample(10)
for i in range(1, 10):
self.assertEqual(sample[0]['Difficulty'], sample[i]['Difficulty'])
class TestHyBayesianNetwork(unittest.TestCase):
def setUp(self):
self.nd = HybridNodeData.load("unittesthdict.txt")
self.nd.entriestoinstances()
self.skel = GraphSkeleton()
self.skel.load("unittestdict.txt")
self.skel.toporder()
self.hybn = HyBayesianNetwork(self.skel, self.nd)
def test_randomsample(self):
sample = self.hybn.randomsample(1)[0]
self.assertTrue(isinstance(sample['Grade'], float))
self.assertTrue(isinstance(sample['Intelligence'], str))
self.assertEqual(sample["SAT"][-12:], 'blueberries!')
def setUp(self):
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
nodedata = NodeData.load("unittestdict.txt")
self.bn = DiscreteBayesianNetwork(nodedata)
agg = SampleAggregator()
agg.aggregate(self.bn.randomsample(50))
self.rseq = agg.seq
self.ravg = agg.avg
self.fn = TableCPDFactorization(self.bn)
evidence = dict(Letter='weak')
agg.aggregate(self.fn.gibbssample(evidence, 51))
self.gseq = agg.seq
self.gavg = agg.avg
class TestHyBayesianNetwork(unittest.TestCase):
def setUp(self):
self.nd = HybridNodeData.load("unittesthdict.txt")
self.nd.entriestoinstances()
self.skel = GraphSkeleton()
self.skel.load("unittestdict.txt")
self.skel.toporder()
self.hybn = HyBayesianNetwork(self.skel, self.nd)
def test_randomsample(self):
sample = self.hybn.randomsample(1)[0]
self.assertTrue(isinstance(sample['Grade'], float))
self.assertTrue(isinstance(sample['Intelligence'], str))
self.assertEqual(sample["SAT"][-12:], 'blueberries!')
def setUp(self):
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
nodedata = NodeData.load("unittestdict.txt")
self.bn = DiscreteBayesianNetwork(nodedata)
agg = SampleAggregator()
agg.aggregate(self.bn.randomsample(50))
self.rseq = agg.seq
self.ravg = agg.avg
self.fn = TableCPDFactorization(self.bn)
evidence = dict(Letter='weak')
agg.aggregate(self.fn.gibbssample(evidence, 51))
self.gseq = agg.seq
self.gavg = agg.avg
def createData(): nd = NodeData() skel = GraphSkeleton() fpath = "job_interview.txt" nd.load(fpath) skel.load(fpath) skel.toporder() bn = DiscreteBayesianNetwork(skel, nd) learner = PGMLearner() data = bn.randomsample(1000) X, Y = 'Grades', 'Offer' c,p,w=learner.discrete_condind(data, X, Y, ['Interview']) print "independence between X and Y: ", c, " p-value ", p, " witness node: ", w result = learner.discrete_constraint_estimatestruct(data) print result.E
def net2():
nd = NodeData()
skel = GraphSkeleton()
nd.load("net.txt") # an input file
skel.load("net.txt")
# topologically order graphskeleton
skel.toporder()
# load bayesian network
lgbn = LGBayesianNetwork(skel, nd)
in_data = read_data.getdata2()
learner = PGMLearner()
bn = learner.lg_mle_estimateparams(skel, in_data)
p = cal_prob(in_data[300:500], bn)
print p
return 0
def net2():
nd = NodeData()
skel = GraphSkeleton()
nd.load("net.txt") # an input file
skel.load("net.txt")
# topologically order graphskeleton
skel.toporder()
# load bayesian network
lgbn = LGBayesianNetwork(skel, nd)
in_data=read_data.getdata2()
learner = PGMLearner()
bn=learner.lg_mle_estimateparams(skel,in_data)
p=cal_prob(in_data[300:500],bn)
print p
return 0
def setUp(self):
# instantiate learner
self.l = PGMLearner()
# generate graph skeleton
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
# generate sample sequence to try to learn from - discrete
nd = NodeData.load("unittestdict.txt")
self.samplediscbn = DiscreteBayesianNetwork(nd)
self.samplediscseq = self.samplediscbn.randomsample(5000)
# generate sample sequence to try to learn from - discrete
nda = NodeData.load("unittestlgdict.txt")
self.samplelgbn = LGBayesianNetwork(nda)
self.samplelgseq = self.samplelgbn.randomsample(10000)
self.skel = skel
def test_structure_estimation(self):
req = DiscreteStructureEstimationRequest()
skel = GraphSkeleton()
skel.load(self.data_path)
skel.toporder()
teacher_nd = NodeData()
teacher_nd.load(self.teacher_data_path)
bn = DiscreteBayesianNetwork(skel, teacher_nd)
data = bn.randomsample(8000)
for v in data:
gs = DiscreteGraphState()
for k_s, v_s in v.items():
gs.node_states.append(DiscreteNodeState(node=k_s, state=v_s))
req.states.append(gs)
res = self.struct_estimate(req)
self.assertIsNotNone(res.graph)
self.assertEqual(len(res.graph.nodes), 5)
self.assertGreater(len(res.graph.edges), 0)
def test_structure_estimation(self):
req = DiscreteStructureEstimationRequest()
skel = GraphSkeleton()
skel.load(self.data_path)
skel.toporder()
teacher_nd = NodeData()
teacher_nd.load(self.teacher_data_path)
bn = DiscreteBayesianNetwork(skel, teacher_nd)
data = bn.randomsample(8000)
for v in data:
gs = DiscreteGraphState()
for k_s, v_s in v.items():
gs.node_states.append(DiscreteNodeState(node=k_s, state=v_s))
req.states.append(gs)
res = self.struct_estimate(req)
self.assertIsNotNone(res.graph)
self.assertEqual(len(res.graph.nodes), 5)
self.assertGreater(len(res.graph.edges), 0)
def setUp(self):
# instantiate learner
self.l = PGMLearner()
# generate graph skeleton
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
# generate sample sequence to try to learn from - discrete
nd = NodeData.load("unittestdict.txt")
self.samplediscbn = DiscreteBayesianNetwork(nd)
self.samplediscseq = self.samplediscbn.randomsample(5000)
# generate sample sequence to try to learn from - discrete
nda = NodeData.load("unittestlgdict.txt")
self.samplelgbn = LGBayesianNetwork(nda)
self.samplelgseq = self.samplelgbn.randomsample(10000)
self.skel = skel
def main():
in_data = read_data.getdata()
f_data = format_data(in_data)
nd = NodeData()
nd.load("net4.txt") # an input file
skel = GraphSkeleton()
skel.load("net4.txt")
skel.toporder()
bn = DiscreteBayesianNetwork(skel, nd)
#training dataset:70%
bn2 = em(f_data[1:6000], bn, skel)
pr_training = precision(f_data[1:6000], bn2)
print "Prediction accuracy for training data:", pr_training[1]
#testing dataset:30%
pr = precision(f_data[6700:6800], bn2)
print "Prediction accuracy for test data:", pr[1]
def test_param_estimation(self):
req = DiscreteParameterEstimationRequest()
# load graph structure
skel = GraphSkeleton()
skel.load(self.data_path)
req.graph.nodes = skel.V
req.graph.edges = [GraphEdge(k, v) for k, v in skel.E]
skel.toporder()
# generate trial data
teacher_nd = NodeData()
teacher_nd.load(self.teacher_data_path)
bn = DiscreteBayesianNetwork(skel, teacher_nd)
data = bn.randomsample(200)
for v in data:
gs = DiscreteGraphState()
for k_s, v_s in v.items():
gs.node_states.append(DiscreteNodeState(node=k_s, state=v_s))
req.states.append(gs)
self.assertEqual(len(self.param_estimate(req).nodes), 5)
def test_param_estimation(self):
req = DiscreteParameterEstimationRequest()
# load graph structure
skel = GraphSkeleton()
skel.load(self.data_path)
req.graph.nodes = skel.V
req.graph.edges = [GraphEdge(k, v) for k,v in skel.E]
skel.toporder()
# generate trial data
teacher_nd = NodeData()
teacher_nd.load(self.teacher_data_path)
bn = DiscreteBayesianNetwork(skel, teacher_nd)
data = bn.randomsample(200)
for v in data:
gs = DiscreteGraphState()
for k_s, v_s in v.items():
gs.node_states.append(DiscreteNodeState(node=k_s, state=v_s))
req.states.append(gs)
self.assertEqual(len(self.param_estimate(req).nodes), 5)
def main():
in_data=read_data.getdata()
f_data=format_data(in_data)
nd = NodeData()
nd.load("net4.txt") # an input file
skel = GraphSkeleton()
skel.load("net4.txt")
skel.toporder()
bn=DiscreteBayesianNetwork(skel,nd)
#training dataset:70%
bn2=em(f_data[1:6000],bn,skel)
pr_training = precision(f_data[1:6000],bn2)
print "Prediction accuracy for training data:" , pr_training[1]
#testing dataset:30%
pr=precision(f_data[6700:6800],bn2)
print "Prediction accuracy for test data:", pr[1]
def bn_learn(attr, cicli, passed_file):
path_to_sentiments = 'sentiment_AFINN'
print "Using AFINN sentiment dictionary"
if attr == 0:
print "Considering tweets' number"
elif attr == 1:
print "Considering averaged number of positive, negative and neutral tweets"
elif attr == 2:
print "Considering averaged value of positive and negative tweets"
elif attr == 3:
print "Considering positive and negative tweets\' increment"
elif attr == 4:
print "Considering bullisment index obtained by number of tweets sentiment"
elif attr == 5:
print "Considering bullisment index obtained by tweets value of sentiment"
print "And considering market trend"
all_data = []
files = [
path_to_sentiments + "/" + file
for file in os.listdir(path_to_sentiments) if file.endswith('.json')
]
for file in files:
with open(file) as sentiment_file:
data = json.load(sentiment_file)
vdata = {}
if attr == 0:
vdata["com"] = data["n_tweets"]
elif attr == 1:
vdata["pos"] = data["n_pos_ave"]
vdata["neg"] = data["n_neg_ave"]
vdata["neu"] = data["n_neu_ave"]
elif attr == 2:
vdata["pos"] = data["pos_val_ave"]
vdata["neg"] = data["neg_val_ave"]
elif attr == 3:
vdata["pos"] = data["pos_inc"]
vdata["neg"] = data["neg_inc"]
elif attr == 4:
vdata["com"] = data["bull_ind"]
elif attr == 5:
vdata["com"] = data["bull_ind_val"]
vdata["market"] = data["market_inc"]
all_data.append(vdata)
skel = GraphSkeleton()
if len(all_data[0]) == 2:
skel.load("network_struct_1_vertex.json")
print "Loading structure with 2 node"
elif len(all_data[0]) == 3:
skel.load("network_struct_2_vertex.json")
print "Loading structure with 3 node"
elif len(all_data[0]) == 4:
skel.load("network_struct_3_vertex.json")
print "Loading structure with 4 node"
skel.toporder()
learner = PGMLearner()
result = learner.lg_mle_estimateparams(skel, all_data)
for key in result.Vdata.keys():
result.Vdata[key]['type'] = 'lg'
prob_pos = prob_neg = prob_neu = 0
for data in all_data:
if data['market'] == 1:
prob_pos += 1
elif data['market'] == 0:
prob_neu += 1
else:
prob_neg += 1
prob_pos = float(prob_pos) / float(len(all_data))
prob_neg = float(prob_neg) / float(len(all_data))
prob_neu = float(prob_neu) / float(len(all_data))
tmp = {}
tmp['numoutcomes'] = len(all_data)
tmp['cprob'] = [prob_pos, prob_neg, prob_neu]
tmp['parents'] = result.Vdata['market']['parents']
tmp['vals'] = ['positive', 'negative', 'neutral']
tmp['type'] = 'discrete'
tmp['children'] = result.Vdata['market']['children']
result.Vdata['market'] = tmp
node = Discrete(result.Vdata["market"])
print "Loading node as Discrete"
estimated, real = mcmc_json(passed_file, attr, cicli, node)
return estimated, real
from libpgm.nodedata import NodeData
from libpgm.graphskeleton import GraphSkeleton
from libpgm.discretebayesiannetwork import DiscreteBayesianNetwork
from inference.exact_inference import ExactInferenceEngine
from inference.approximate_inference import ApproximateInferenceEngine
node_data = NodeData()
network_skeleton = GraphSkeleton()
node_data.load('test_bayesian_networks/network.txt')
network_skeleton.load('test_bayesian_networks/network.txt')
network = DiscreteBayesianNetwork(network_skeleton, node_data)
exact_inference_engine = ExactInferenceEngine(network)
approximate_inference_engine = ApproximateInferenceEngine(network)
query_variable = 'Burglary'
evidence_variables = {'MaryCalls': 'true', 'JohnCalls': 'true'}
resulting_distribution = exact_inference_engine.perform_inference(query_variable, evidence_variables)
print 'P(B|m,j) - enumeration: ', resulting_distribution
resulting_distribution = exact_inference_engine.perform_ve_inference(query_variable, evidence_variables)
print '(B|m,j) - variable elimination: ', resulting_distribution
resulting_distribution = approximate_inference_engine.perform_rs_inference(query_variable, evidence_variables, 100000)
print 'P(B|m,j) - approximate - rejection sampling: ', resulting_distribution
resulting_distribution = approximate_inference_engine.perform_lw_inference(query_variable, evidence_variables, 100000)
print 'P(B|m,j) - approximate - likelihood weighting: ', resulting_distribution
resulting_distribution = approximate_inference_engine.perform_gibbs_inference(query_variable, evidence_variables, 100000)
print 'P(B|m,j) - approximate - Gibbs: ', resulting_distribution
print
query_variable = 'JohnCalls'
if __name__ == '__main__':
rospy.init_node("pgm_learner_sample_discrete")
param_estimate = rospy.ServiceProxy(
"pgm_learner/discrete/parameter_estimation",
DiscreteParameterEstimation)
req = DiscreteParameterEstimationRequest()
dpath = os.path.join(PKG_PATH, "test", "graph-test.txt")
tpath = dpath
# load graph structure
skel = GraphSkeleton()
skel.load(dpath)
req.graph.nodes = skel.V
req.graph.edges = [GraphEdge(k, v) for k, v in skel.E]
skel.toporder()
# generate trial data
teacher_nd = NodeData()
teacher_nd.load(dpath)
bn = DiscreteBayesianNetwork(skel, teacher_nd)
data = bn.randomsample(200)
for v in data:
gs = DiscreteGraphState()
for k_s, v_s in v.items():
gs.node_states.append(DiscreteNodeState(node=k_s, state=v_s))
req.states.append(gs)
import json
from libpgm.nodedata import NodeData
from libpgm.graphskeleton import GraphSkeleton
from libpgm.discretebayesiannetwork import DiscreteBayesianNetwork
from libpgm.pgmlearner import PGMLearner
nd = NodeData()
nd.load("nodedata.json")
skel = GraphSkeleton()
skel.load("nodedata.json")
skel.toporder()
bn = DiscreteBayesianNetwork(skel,nd)
with open("manipulatedata.json") as fp:
data = json.load(fp)
learner = PGMLearner()
# result = learner.discrete_constraint_estimatestruct(data)
result = learner.discrete_estimatebn(data)
print json.dumps(result.E, indent=2)
print json.dumps(result.Vdata, indent=2)
import string
from libpgm.graphskeleton import GraphSkeleton
from libpgm.tablecpdfactorization import TableCPDFactorization
from libpgm.pgmlearner import PGMLearner
text = open("../unifiedMLData2.json")
data=text.read()
printable = set(string.printable)
asciiData=filter(lambda x: x in printable, data)
listofDicts=json.loads(asciiData)
skel = GraphSkeleton()
skel.load("../skeleton.json")
learner = PGMLearner()
result = learner.discrete_mle_estimateparams(skel, listofDicts)
tcf=TableCPDFactorization(result)
#Rating 1 Given Genre is Drama
myquery = dict(rating=[1])
myevidence = dict(genre='Drama')
result=tcf.specificquery(query=myquery,evidence=myevidence)
print result
tcf.refresh()
#temp.append(min(list)+float(max(list) - min(list))*1/3)
#temp.append(min(list)+float(max(list) - min(list))*2/3)
temp.append(float(max(list))/3)
temp.append(float(max(list))/3*2)
return temp
EachLikeThreshold = Threshold(EachLike)
EachLikedThreshold = Threshold(EachLiked)
print EachLikeThreshold
print EachLikedThreshold
BulliedPro = []
nd = NodeData()
skel = GraphSkeleton()
nd.load('unittestdict.txt')
skel.load('unittestdict.txt')
bn = DiscreteBayesianNetwork(skel, nd)
fn = TableCPDFactorization(bn)
for i in range(len(EachLike)):
evidence = {}
if EachLike[i] <= EachLikeThreshold[0]:
evidence['LikeN'] = 'Small'
elif EachLikeThreshold[0] < EachLike[i] and EachLike[i] <= EachLikeThreshold[1]:
evidence['LikeN'] = 'Mid'
else:
evidence['LikeN'] = 'Big'
if EachLiked[i] <= EachLikedThreshold[0]:
evidence['LikedN'] = 'Small'
elif EachLikedThreshold[0] < EachLiked[i] and EachLiked[i] <= EachLikedThreshold[1]:
evidence['LikedN'] = 'Mid'
def learn(self):
print "ds: ", len(self.dataset)
#print self.dataset
data = []
rw = []
bestreward = -100
for seq in self.dataset:
for state_, action_, reward_ in seq:
if reward_[0] > bestreward:
bestreward = reward_[0]
# find limit for theta
print "bestrw", bestreward
nds = []
lt=[]
ls = []
ltv =[]
lsv=[]
i = 0
for seq in self.dataset:
for state_, action_, reward_ in seq:
# if reward_[0] == 0:
# print state_, action_, reward_
#print state_, reward_
if reward_[0] == bestreward:
ns = (state_, action_[0], reward_[0])
nds.append(ns)
# print state_[0], state_[2], reward_[0], bestreward
t = state_[0]
tv= state_[1]
s = state_[2]
sv = state_[3]
if t > 0.05:
print "hmmm,", i, t
#raise Exception(i)
i += 1
lt.append(t)
ls.append(s)
ltv.append(tv)
lsv.append(sv)
limits = dict(theta=[min(lt),max(lt)],s=[min(ls),max(ls)],thetaV=[min(ltv),max(ltv)],sV=[min(lsv),max(lsv)])
print "limits: ", limits
# print "all good things:", nds
#convert ds
for seq in self.dataset:
for state_, action_, reward_ in seq:
# sample = dict(theta=state_[0],thetaPrime=state_[1],s=state_[2],sPrime=state_[3],Action=action_[0],Reward=reward_[0])
#
#
# dtpo = min( abs(sample["thetaPrime"] - limits["theta"][0]), abs(sample["thetaPrime"] - limits["theta"][1]))
# dto = min( abs(sample["theta"] - limits["theta"][0]), abs(sample["theta"] - limits["theta"][1]))
# dspo = min( abs(sample["sPrime"] - limits["s"][0]), abs(sample["sPrime"] - limits["s"][1]))
# dso = min( abs(sample["s"] - limits["s"][0]), abs(sample["s"] - limits["s"][1]))
#
# #print dspo, dso
#
# netsample = dict(theta=sample["theta"],s=sample["s"],Action=sample["Action"],Reward=sample["Reward"])
# # did this action improve theta or s??
# if dtpo <= dto or dspo <= dso: #yes it did
## data.append(netsample)
# rw.append(sample["Reward"])
sample = dict(theta=state_[0],thetaV=state_[1],s=state_[2],sV=state_[3],Action=action_[0],Reward=reward_[0])
#print state_, action_, reward_
#print sample
if sample["Reward"] != 990:
data.append(sample)
if numpy.random.random() >= 9.1:
continue
import matplotlib.pyplot as plt
import pandas as pd
df = pd.DataFrame(rw)
# print df
# plt.figure()
# df[0].diff().hist()
# instantiate my learner
learner = PGMLearner()
# estimate parameters
rbn = []
for i in range(0,1):
result = learner.lg_constraint_estimatestruct(data,bins=10, pvalparam=0.05)
rbn.append(result)
print len(result.E), result.E
result = rbn[0]
# output - toggle comment to see
print json.dumps(result.V, indent=2)
print len(result.E), "Edges", result.E
import pydot
# this time, in graph_type we specify we want a DIrected GRAPH
graph = pydot.Dot(graph_type='digraph')
nd = {}
for n in result.V:
nd[n] = pydot.Node(n)
graph.add_node(nd[n])
for e in result.E:
graph.add_edge(pydot.Edge(nd[e[0]], nd[e[1]]))
graph.write_png('eg.png')
from IPython.display import Image
Image('eg.png')
f = open('workfile', 'w')
f.write("{\n \"V\":")
f.write(json.dumps(result.V))
f.write(",\n \"E\":")
f.write(json.dumps(result.E))
f.write("}")
f.close()
skel = GraphSkeleton()
skel.load("workfile")
# topologically order graphskeleton
skel.toporder()
return
import json
from libpgm.nodedata import NodeData
from libpgm.graphskeleton import GraphSkeleton
from libpgm.discretebayesiannetwork import DiscreteBayesianNetwork
from libpgm.pgmlearner import PGMLearner
# generate some data to use
nd = NodeData()
nd.load("grades.txt") # an input file
skel = GraphSkeleton()
skel.load("grades.txt")
skel.toporder()
bn = DiscreteBayesianNetwork(skel, nd)
data = bn.randomsample(80000)
# instantiate my learner
learner = PGMLearner()
# estimate structure
result = learner.discrete_constraint_estimatestruct(data)
# output
print json.dumps(result.E, indent=2)
import string
from libpgm.graphskeleton import GraphSkeleton
from libpgm.tablecpdfactorization import TableCPDFactorization
from libpgm.pgmlearner import PGMLearner
text = open("../unifiedMLData2.json")
data = text.read()
printable = set(string.printable)
asciiData = filter(lambda x: x in printable, data)
#listofDicts=json.dumps(data)
listofDicts = json.loads(asciiData)
skel = GraphSkeleton()
skel.load("../skeleton.json")
learner = PGMLearner()
result = learner.discrete_mle_estimateparams(skel, listofDicts)
tcf = TableCPDFactorization(result)
#Rating 1 Given Occupation is student
myquery = dict(rating=[1])
myevidence = dict(occupation='student')
result = tcf.specificquery(query=myquery, evidence=myevidence)
print result
tcf.refresh()
def train(self):
"""Train the associated module for one epoch."""
assert len(self.ds) > 0, "Dataset cannot be empty."
gbds = []
ds2 = []
for seq in self.ds:
for state_, action_, reward_ in seq:
#sample = dict(theta=state_[0],thetaV=state_[1],s=state_[2],sV=state_[3],Action=action_[0],Reward=reward_[0])
sample = dict(StateA=state_[0],StateB=state_[2],StateC=state_[1],StateD=state_[3],Action=action_[0],Reward=reward_[0])
#print state_, action_, reward_
# sample = dict(StateA=state_[0],StateB=state_[2],StateC=state_[1],StateD=state_[3],Action=action_[0],Reward=reward_[0])
#sample = dict(theta=state_[0],thetaPrime=state_[2],s=state_[1],sPrime=state_[3],Action=action_[0],Reward=reward_[0])
if sample["Reward"] >= 0:
gbds.append(sample)
if sample["Reward"] == -1:
ds2.append(sample)
#print sample["Reward"]
# sort samples for highest reward
# bdss = sorted(gbds, key=lambda tup: tup["Reward"],reverse=True)
#
#print "BDS: "
#print json.dumps(gbds, indent=2)
# print "BDSS: "
# print json.dumps(bdss, indent=2)
#tokeep = bdss[:max(2,len(bdss)/2)]
#print bds
# estimate parameters
# print "data size: ", len(bds), len(gbds)
N = 200
if len(gbds) < N:
l = N - len(gbds)
n = len(ds2)
t = len(ds2[n-l:])
gbds.extend(ds2[n-l:])
print "ds:, ", len(gbds), len(ds2)
if len(gbds) < 100:
# print "burn"
self.module.burn = True
return
else:
self.module.burn = False
if len(gbds) < 5: #there was no rewarding action, so nothing to learn
self.module.burn = True
return
N = 200
if len(gbds) > N:
#only take the newest N samples
l = len(gbds)
gbds = gbds[l-N:]
# print "new effective set", len(gbds)
skel = GraphSkeleton()
#load network topology
skel.load("net2.txt")
# skel.load("workfile")
skel.toporder()
# estimate parameters
self.module.net = self.learner.lg_mle_estimateparams(skel, gbds)
if __name__ == "__main__":
rospy.init_node("pgm_learner_sample_linear_gaussian")
param_estimate = rospy.ServiceProxy(
"pgm_learner/linear_gaussian/parameter_estimation", LinearGaussianParameterEstimation
)
req = LinearGaussianParameterEstimationRequest()
dpath = os.path.join(PKG_PATH, "test", "graph-test.txt")
tpath = os.path.join(PKG_PATH, "test", "graph-lg-test.txt")
# load graph structure
skel = GraphSkeleton()
skel.load(dpath)
req.graph.nodes = skel.V
req.graph.edges = [GraphEdge(k, v) for k, v in skel.E]
skel.toporder()
# generate trial data
teacher_nd = NodeData()
teacher_nd.load(tpath)
bn = LGBayesianNetwork(skel, teacher_nd)
data = bn.randomsample(200)
for v in data:
gs = LinearGaussianGraphState()
for k_s, v_s in v.items():
gs.node_states.append(LinearGaussianNodeState(node=k_s, state=v_s))
req.states.append(gs)
import json
from libpgm.nodedata import NodeData
from libpgm.graphskeleton import GraphSkeleton
from libpgm.lgbayesiannetwork import LGBayesianNetwork
from libpgm.pgmlearner import PGMLearner
# generate some data to use
nd = NodeData()
nd.load("gaussGrades.txt") # an input file
skel = GraphSkeleton()
skel.load("gaussGrades.txt")
skel.toporder()
lgbn = LGBayesianNetwork(skel, nd)
data = lgbn.randomsample(8000)
print data
# instantiate my learner
learner = PGMLearner()
# estimate structure
result = learner.lg_constraint_estimatestruct(data)
# output
print json.dumps(result.E, indent=2)
import json
from libpgm.nodedata import NodeData
from libpgm.graphskeleton import GraphSkeleton
from libpgm.discretebayesiannetwork import DiscreteBayesianNetwork
from libpgm.tablecpdfactorization import TableCPDFactorization
# load nodedata and graphskeleton
nd = NodeData()
skel = GraphSkeleton()
nd.load("tests/net1.json") # any input file
skel.load("tests/net1.json")
# topologically order graphskeleton
skel.toporder()
# load bayesian network
bn = DiscreteBayesianNetwork(skel, nd)
fn = TableCPDFactorization(bn)
# sample
result = fn.specificquery(dict(C='T'), dict(B='F'))
# output
print json.dumps(result, indent=2)
# result.append(dict(great = row.great, good = row.good, nice = row.nice, clean = row.clean, helpful = row.helpful, comfortable = row.comfortable,
# beautiful = row.beautiful, wonderful = row.wonderful, friendly = row.friendly, fantastic = row.fantastic, bad = row.bad,
# Cleanliness= row.Cleanliness, Location=row.Location ,Businessservice=row.Businessservice,
# Checkin=row.Checkin, Service=row.Service, Rooms=row.Rooms, Value=row.Value, Overall=row.Overall ))
return result
#load all preprocessed training data
df = pd.read_csv('features.csv', sep=',')
#format data to let them correctly processed by libpgm functions
node_data = format_data(df)
skel = GraphSkeleton()
#load structure of our net
skel.load("./skel-learned2.txt")
#setting the topologic order
skel.toporder()
#learner which will estimate parameters e if needed net structure
learner = PGMLearner()
#estismting parameters for our own model
res = learner.discrete_mle_estimateparams(skel, node_data)
"""
#estimating net structure given training data and paramenters this is an alternative to create a new model on our data
net = learner.discrete_estimatebn(node_data)
with open("reteTestMeta.csv", "a") as gv:
gv.write(json.dumps(net.V, indent=2))
gv.write(json.dumps(net.E, indent=2))
res = learner.discrete_mle_estimateparams(net, node_data)
# learner = PGMLearner()
#
# # estimate parameters
# result = learner.discrete_mle_estimateparams(skel, data)
#
# # output - toggle comment to see
# print json.dumps(result.Vdata, indent=2)
# (5) --------------------------------------------------------------------------
# Compute the probability distribution over a specific node or nodes
# load nodedata and graphskeleton
nd = NodeData()
skel = GraphSkeleton()
nd.load("../tests/unittestdict.txt")
skel.load("../tests/unittestdict.txt")
# toporder graph skeleton
print skel.toporder()
# load evidence
evidence = {"Intelligence": "high"}
query = {"Grade": "A"}
# load bayesian network
bn = DiscreteBayesianNetwork(skel, nd)
# load factorization
fn = TableCPDFactorization(bn)
# # calculate probability distribution
import json
from libpgm.nodedata import NodeData
from libpgm.graphskeleton import GraphSkeleton
from libpgm.lgbayesiannetwork import LGBayesianNetwork
from libpgm.pgmlearner import PGMLearner
# generate some data to use
nd = NodeData()
nd.load("gaussGrades.txt") # an input file
skel = GraphSkeleton()
skel.load("gaussGrades.txt")
skel.toporder()
lgbn = LGBayesianNetwork(skel, nd)
data = lgbn.randomsample(8000)
print data
# instantiate my learner
learner = PGMLearner()
# estimate structure
result = learner.lg_constraint_estimatestruct(data)
# output
print json.dumps(result.E, indent=2)
for line in data_r.readlines():
data_l.append(map(int, line.split()))
truth_l = []
for row in truth_r:
truth_l.append(row[0])
w = csv.writer(open("bayesian_outcome.txt", "wb"))
count = 0
for i in range(104):
nd = NodeData()
skel = GraphSkeleton()
nd.load('bayes_net/'+str(i)+".txt") # any input file
skel.load('bayes_net/'+str(i)+".txt")
# topologically order graphskeleton
skel.toporder()
# load bayesian network
# load bayesian network
bn = DiscreteBayesianNetwork(skel, nd)
dic1 = {}
k = 1
for c in data_l[i]:
dic1[str(k)] = str(c)
k += 2
print dic1
k = 2 * len(data_l[i]) - 2
from libpgm.discretebayesiannetwork import DiscreteBayesianNetwork
from libpgm.lgbayesiannetwork import LGBayesianNetwork
from libpgm.hybayesiannetwork import HyBayesianNetwork
from libpgm.dyndiscbayesiannetwork import DynDiscBayesianNetwork
from libpgm.tablecpdfactorization import TableCPDFactorization
from libpgm.sampleaggregator import SampleAggregator
from libpgm.pgmlearner import PGMLearner
# (1) ---------------------------------------------------------------------
# Generate a sequence of samples from a discrete-CPD Bayesian network
# load nodedata and graphskeleton
nd = NodeData()
skel = GraphSkeleton()
nd.load("../tests/unittestdict.txt")
skel.load("../tests/unittestdict.txt")
# topologically order graphskeleton
skel.toporder()
# load bayesian network
bn = DiscreteBayesianNetwork(skel, nd)
# sample
result = bn.randomsample(10)
# output - toggle comment to see
#print json.dumps(result, indent=2)
# (2) ----------------------------------------------------------------------
# Generate a sequence of samples from a linear Gaussian-CPD Bayesian network
import json
from libpgm.nodedata import NodeData
from libpgm.graphskeleton import GraphSkeleton
from libpgm.discretebayesiannetwork import DiscreteBayesianNetwork
from libpgm.pgmlearner import PGMLearner
# generate some data to use
nd = NodeData()
nd.load("grades.txt") # an input file
skel = GraphSkeleton()
skel.load("grades.txt")
skel.toporder()
bn = DiscreteBayesianNetwork(skel, nd)
data = bn.randomsample(80000)
# instantiate my learner
learner = PGMLearner()
# estimate structure
result = learner.discrete_constraint_estimatestruct(data)
# output
print json.dumps(result.E, indent=2)
activValsList)
# checking if input from user was approppriate
if set(userinput).issubset(dictionary):
# initializing probabilities lists
wkdayProbList = []
hourProbList = []
locatProbList = []
activProbList = []
#INITIALIZING BN 1
# load nodedata and graphskeleton
nd1 = NodeData()
skel1 = GraphSkeleton()
nd1.load(path_bn1)
skel1.load(path_bn1)
skel1.toporder() # toporder graph skeleton
#INITIALIZING BN 2
# load nodedata and graphskeleton
nd2 = NodeData()
skel2 = GraphSkeleton()
nd2.load(path_bn2)
skel2.load(path_bn2)
skel2.toporder() # toporder graph skeleton
# FINDING NEXT ACTIVITY ATTRIBUTES THROUGH INFERENCE ON BN 1
# wkday variable query
evidence1 = dict(wkdayT0=userinput[0])
for i, item in enumerate(wkdayValsList):
# loading bayesian network and factorization - needs to be done at every iteration
__author__ = 'Amir'
import json
from libpgm.graphskeleton import GraphSkeleton
from libpgm.pgmlearner import PGMLearner
with open('data.txt', 'r') as f:
data = eval(f.read())
# generate some data to use
skel = GraphSkeleton()
skel.load("skel.txt")
skel.toporder()
# instantiate my learner
learner = PGMLearner()
# estimate parameters from data and skeleton
result = learner.lg_mle_estimateparams(skel, data)
# output
print json.dumps(result.Vdata, indent=2)
