def make_CPTs(self, nodes, alpha):
for node in nodes:
parents = list(self.bn.parents(node))
if len(parents) != 0:
parValues = list(itertools.product([1, 0],
repeat=len(parents)))
for parVal in parValues:
prnode = "{:.2f}".format(random.uniform(alpha, 1))
complementnode = "{:.2f}".format(1.00 - float(prnode))
change_prob = np.random.random()
if change_prob > 0.50:
newCPT = [float(complementnode), float(prnode)]
else:
newCPT = [float(prnode), float(complementnode)]
self.bn.cpt(node)[{
str(parents[index]): value
for index, value in enumerate(parVal)
}] = newCPT
else:
prnode = "{:.2f}".format(random.uniform(alpha, 1))
complementnode = "{:.2f}".format(1.00 - float(prnode))
change_prob = np.random.random()
if change_prob > 0.50:
newCPT = [float(complementnode), float(prnode)]
else:
newCPT = [float(prnode), float(complementnode)]
self.bn.cpt(node).fillWith(newCPT)
othersnodes = list(self.bn.nodes())
for othernode in othersnodes:
if not othernode in nodes:
self.bn.generateCPT(othernode)
gum.saveBN(self.bn, self.path + self.name + '.bifxml')
def generate_BN_explanations(instance, label_lst, feature_names, class_var,
encoder, scaler, model, path, dataset_name):
# necessary for starting Numpy generated random numbers in an initial state
np.random.seed(515)
# Necessary for starting core Python generated random numbers in a state
rn.seed(515)
indx = instance['index']
prediction_type = instance['prediction_type'].lower() + "s"
prediction_type = prediction_type.replace(" ", "_")
# generate permutations
df = generate_permutations(instance, label_lst, feature_names, class_var,
encoder, scaler, model)
# discretize data
df_discr = discretize_dataframe(df, class_var, num_bins=4)
# save discretised dataframe (for debugging and reproduceability purposes)
path_to_permutations = path + "feature_permutations/" + dataset_name.replace(
".csv", "") + "/" + prediction_type + "/" + str(indx) + ".csv"
df_discr.to_csv(path_to_permutations, index=False)
# normalise dataframe
normalise_dataframe(path_to_permutations)
# learn BN
bn, infoBN, essencGraph = learnBN(
path_to_permutations.replace(".csv", "_norm.csv"))
# perform inference
inference = gnb.getInference(bn,
evs={},
targets=df_discr.columns.to_list(),
size='12')
# show networks
gnb.sideBySide(
*[bn, inference, infoBN],
captions=["Bayesian Network", "Inference", "Information Network"])
# save to file
path_to_explanation = path + "explanations/" + dataset_name.replace(
".csv", "") + "/BN/" + prediction_type + "/"
gum.lib.bn2graph.dotize(bn, path_to_explanation + str(indx) + "_BN")
gum.saveBN(bn, path_to_explanation + str(indx) + "_BN.net")
return [bn, inference, infoBN]
def transform():
bn1 = gum.loadBN("data/test_level_0.o3prm", system="aSys")
print("transform : prm loaded")
gum.saveBN(bn1, "data/test_level_0.bif")
print("transform : bn written")
bn = gum.loadBN("data/test_level_0.bif")
print("transform : bn loaded")
for i in bn.ids():
bn.cpt(i).translate(1e-2).normalizeAsCPT()
print("transform : bn normalized")
gum.saveBN(bn, "data/test_level_0_1.bif")
print("transform : bn written")
def build_save_BN(self, dGraphNodes, dGraphEdges, randomCPTs):
dGraphEdges = [(str(A), str(B)) for (A, B) in dGraphEdges]
bn = gum.BayesNet(self.name)
[
bn.add(gum.LabelizedVariable(str(var), str(var), 2))
for var in dGraphNodes
]
for edge in dGraphEdges:
bn.addArc(edge[0], edge[1])
if randomCPTs:
# For generate all CPTs
bn.generateCPTs()
# To graph and save BN
gumGraph.dotize(bn, self.path + self.name, 'pdf')
gum.saveBN(bn, self.path + self.name + '.bifxml')
self.generator = gum.BNDatabaseGenerator(bn)
self.ie = gum.LazyPropagation(bn)
self.bn = bn
self.structure = [dGraphNodes, dGraphEdges]
def testReadAfterWrite(self):
bn = gum.BayesNet()
bn.add(gum.RangeVariable("1", "", 0, 1))
bn.add(
gum.DiscretizedVariable("2",
"").addTick(0.0).addTick(0.5).addTick(1.0))
bn.add(gum.LabelizedVariable("3", "", 2))
bn.add(gum.LabelizedVariable("4", "", 2))
bn.add(gum.LabelizedVariable("5", "", 3))
bn.addArc("1", "3")
bn.addArc("1", "4")
bn.addArc("3", "5")
bn.addArc("4", "5")
bn.addArc("2", "4")
bn.addArc("2", "5")
bn.cpt("1").fillWith([0.2, 0.8])
bn.cpt("2").fillWith([0.3, 0.7])
bn.cpt("3").fillWith([0.1, 0.9, 0.9, 0.1])
bn.cpt("4").fillWith([0.4, 0.6, 0.5, 0.5, 0.5, 0.5, 1.0, 0.0])
bn.cpt("5").fillWith([
0.3, 0.6, 0.1, 0.5, 0.5, 0.0, 0.5, 0.5, 0.0, 1.0, 0.0, 0.0, 0.4,
0.6, 0.0, 0.5, 0.5, 0.0, 0.5, 0.5, 0.0, 0.0, 0.0, 1.0
])
gum.saveBN(bn, self.agrumSrcDir("o3prm/BNO3PRMIO_file.o3prm"))
bn2 = gum.loadBN(self.agrumSrcDir("o3prm/BNO3PRMIO_file.o3prm"),
system="bayesnet")
self.assertEqual(bn.dim(), bn2.dim())
self.assertEqual(bn.log10DomainSize(), bn2.log10DomainSize())
for n in bn.names():
self.assertEqual(bn.variable(n).name(), bn2.variable(n).name())
self.assertEqual(
bn.variable(n).varType(),
bn2.variable(n).varType())
self.assertEqual(
bn.variable(n).domainSize(),
bn2.variable(n).domainSize())
def learn_bn(learn_algo):
## create and learn BN, and setup inference
dataset_path = 'discr_wps.csv'
bn = inf.learn_bn(learn_algo, dataset_path)
bn_url = "BN.bif"
agrum.saveBN(bn, bn_url)
print("BN saved in " + bn_url)
## BN validation : identify unknown effects
## effect = [goal_value, vector_orient_value]
# unk_aff_vector, nb_aff_dataset, nb_aff_total = check.find_unk_affordances(bn_url)
#
# if nb_aff_total != 0:
# print('\nRESULT:')
## print(nb_aff_total, 'possible affordances in the experiment')
## print(nb_aff_dataset, 'possible affordances in the dataset')
# print(len(unk_aff_vector),'affordances not learned yet')
# else :
# print('\nNOT VALID DATASET. Only',nb_aff_dataset,'lines read')
return bn
def bayesNet(evs):
# Creating BayesNet with 4 variables
bayesNets = gum.BayesNet('Quality Prediction')
# Adding nodes the long way
commitNumber = bayesNets.add(
gum.LabelizedVariable(
'Commit Number', 'cloudy ?',
0).addLabel("Low").addLabel("Medium").addLabel("High"))
numberOfDevloper = bayesNets.add(
gum.LabelizedVariable(
"Number Of Developer", "Devs",
0).addLabel("Low").addLabel("Medium").addLabel("High"))
buildFailures = bayesNets.add(
gum.LabelizedVariable(
'Build Failures', 'cloudy ?',
0).addLabel("Low").addLabel("Medium").addLabel("High"))
numberOfFixedBug = bayesNets.add(
gum.LabelizedVariable('Number Of Fixed Bug', 'cloudy ?', 2))
nbFunctionalEvolution = bayesNets.add(
gum.LabelizedVariable(
"Number Of Functional Evolution", "Evol",
0).addLabel("Low").addLabel("Medium").addLabel("High"))
categoryOfIncident = bayesNets.add(
gum.LabelizedVariable("Incident Category", "Devs", 0).addLabel(
"Tertiaire").addLabel("Secondaire").addLabel("Prmaire"))
# creation of the links between nodes
for link in [(commitNumber, buildFailures),
(numberOfDevloper, buildFailures),
(nbFunctionalEvolution, numberOfFixedBug),
(buildFailures, numberOfFixedBug),
(buildFailures, categoryOfIncident),
(numberOfFixedBug, categoryOfIncident)]:
bayesNets.addArc(*link)
print(bayesNets)
bayesNets.cpt(commitNumber)[:] = [0.5, 0.3, 0.2]
bayesNets.cpt(numberOfDevloper)[:] = [0.5, 0.4, 0.5]
bayesNets.cpt(nbFunctionalEvolution)[:] = [0.5, 0.4, 0.5]
print(bayesNets.cpt(numberOfFixedBug).var_names)
bayesNets.cpt(buildFailures).var_names
bayesNets.cpt(numberOfDevloper)
#bayesNets.cpt(numberOfFixedBug)[{'buildFailures': 1, 'Number Of Functional Evolution': "Medium"}]=[0.5,0.4]
#bayesNets.cpt(numberOfFixedBug)[{'buildFailures': 1, 'Number Of Functional Evolution': "High"}]=[0.54,0.46]
#bayesNets.cpt(numberOfFixedBug)[{'buildFailures': 1, 'Number Of Functional Evolution': "Low"}]=[0.54,0.46]
bayesNets.cpt(numberOfFixedBug)[{
'Build Failures': 0,
'Number Of Functional Evolution': "Medium"
}] = [0.5, 0.4]
bayesNets.cpt(numberOfFixedBug)[{
'Build Failures': 0,
'Number Of Functional Evolution': "High"
}] = [0.54, 0.46]
bayesNets.cpt(numberOfFixedBug)[{
'Build Failures': 0,
'Number Of Functional Evolution': "Low"
}] = [0.53, 0.47]
bayesNets.cpt(numberOfFixedBug)
bayesNets.cpt(buildFailures)[{
'Commit Number': "Low",
'Number Of Developer': "Low"
}] = 0.2
bayesNets.cpt(buildFailures)[{
'Commit Number': "Low",
'Number Of Developer': "High"
}] = 0.4
bayesNets.cpt(buildFailures)[{
'Commit Number': "High",
'Number Of Developer': "Low"
}] = 0.2
bayesNets.cpt(buildFailures)[{
'Commit Number': "High",
'Number Of Developer': "High"
}] = 0.9
bayesNets.cpt(buildFailures)[{
'Commit Number': "Low",
'Number Of Developer': "Medium"
}] = 1
bayesNets.cpt(buildFailures)[{
'Commit Number': "Low",
'Number Of Developer': "Medium"
}] = 0.9
bayesNets.cpt(buildFailures)[{
'Commit Number': "High",
'Number Of Developer': "Medium"
}] = 0.1
bayesNets.cpt(buildFailures)[{
'Commit Number': "Medium",
'Number Of Developer': "Medium"
}] = 0.6
bayesNets.cpt(buildFailures)
bayesNets.cpt(categoryOfIncident)[{
'Build Failures': 0,
'Number Of Fixed Bug': 0
}] = [0.2, 0.3, 0.5]
bayesNets.cpt(categoryOfIncident)[{
'Build Failures': 0,
'Number Of Fixed Bug': 1
}] = [0.5, 0.3, 0.2]
bayesNets.cpt(categoryOfIncident)
ie = gum.LazyPropagation(bayesNets)
gum.saveBN(bayesNets, "QualtiyPrediction.bifxml")
bn = gum.loadBN("QualtiyPrediction.bifxml")
bn
output_parameters_labels = ['Incident Cateogry']
ie = gum.LazyPropagation(bayesNet)
ie.setEvidence(evs)
ie.makeInference()
resultCSV = []
resultCSV.append('Parameter, Low, Medium, High')
for output_parameter_label in output_parameters_labels:
results = ie.posterior(output_parameter_label).tolist()
resultCSV.append(output_parameter_label + ', ' +
str(round(results[0], 3)) + ', ' +
str(round(results[1], 3)) + ', ' +
str(round(results[2])))
#gnb.showInference(bn,evs={})
resultBytes = BNinference2dot(bn, evs=evs).create(format='png')
resultBytesStr = base64.b64encode(resultBytes)
return resultBytesStr, resultCSV
learner = gum.BNLearner("WholeLog.csv")
#learner.learnParameters(bn)
print(learner.names())
learner.useScoreAIC()
learner.setSliceOrder([[0, 1, 2, 3, 4, 5, 6, 7, 8], [9, 10, 11, 12]])
learner.useAprioriSmoothing(10e-2)
learner.useGreedyHillClimbing()
#learner.useLocalSearchWithTabuList()
#learner.useK2([0,1,2,3,4,5,6,7,8, 9, 10, 11, 12])
bn = learner.learnBN()
gum.saveBN(bn, "Many.bif")
generator = CSharpGenerator()
#generator = phpGenerator.PhpGenerator()
filename = "Many.cs"
import pyAgrum as gum
import metaGenBayes.compiler as Compiler
targets = ['move?', 'turn?', 'shell?', "shield?"]
un_sur_neuf = [1.0 / 9.0] * 9
evs = {
'distance?': [0.25, 0.25, 0.25, 0.25],
"direction?": [
1.0 / 9.0, 1.0 / 9.0, 1.0 / 9.0, 1.0 / 9.0, 1.0 / 9.0, 1.0 / 9.0,
1.0 / 9.0, 1.0 / 9.0, 1.0 / 9.0
learner=gum.BNLearner("WholeLog.csv")
#learner.learnParameters(bn)
print(learner.names())
learner.useScoreAIC()
learner.setSliceOrder([[0,1,2,3,4,5,6,7,8], [9, 10, 11, 12]])
learner.useAprioriSmoothing(10e-2)
learner.useGreedyHillClimbing()
#learner.useLocalSearchWithTabuList()
#learner.useK2([0,1,2,3,4,5,6,7,8, 9, 10, 11, 12])
bn = learner.learnBN()
gum.saveBN(bn, "Many.bif")
generator = CSharpGenerator()
#generator = phpGenerator.PhpGenerator()
filename="Many.cs"
import pyAgrum as gum
import metaGenBayes.compiler as Compiler
targets = ['move?', 'turn?', 'shell?', "shield?"]
un_sur_neuf = [1.0/9.0]*9
evs = {'distance?':[0.25, 0.25, 0.25, 0.25],
"direction?":[1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0],
'dist_coll_1?':[1.0/3.0, 1.0/3.0, 1.0/3.0],
'dir_coll_1?':[1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0, 1.0/9.0],
import pyAgrum as gum
from gumLib.pyAgrum_header import pyAgrum_header
pyAgrum_header(2011)
bn = gum.BayesNet('exo1')
# sexe = 0(H)/1(F)
# daltonisme = 0(D) / 1 (nonD)
sexe, daltonisme = [
bn.add(gum.LabelizedVar(nom, '', 2)) for nom in 'sexe daltonisme'.split()
]
bn.insertArc(sexe, daltonisme)
bn.cpt(sexe)[:] = [0.5, 0.5]
bn.cpt(daltonisme)[0, :] = [0.08, 0.92]
bn.cpt(daltonisme)[1, :] = [0.005, 0.995]
bn.saveBIF("exo1.bif")
for line in open("exo1.bif"):
print line,
print("for gum.loadBN or gum.saveBN, possible files ext are =" +
gum.availableBNExts())
gum.saveBN(bn, "exo1.dsl")
for line in open("exo1.dsl"):
print line,
def save_bn(bn, bn_url):
agrum.saveBN(bn, bn_url)
print("BN saved in " + bn_url)
while (len(bn.parents(CLASSE)) < NBRPARENTSMIN):
nvparent = int(gum.randomProba() * bn.size())
try:
bn.addArc(nvparent, CLASSE)
except gum.Exception:
print(f" Failed in {bn.parents(0)} with {nvparent}")
print("(*) re-generating CPTs")
bn.generateCPTs()
fileid = "{0}-{1}-{2}-{3}".format(
datetime.datetime.now().strftime("%Y%m%d-%H%M%S"), NBRNOEUDS, NBRARCS,
MODMAX)
print("(*) saving bif file {0}".format(fileid))
gum.saveBN(bn, "BN{0}.bif".format(fileid))
print("(*) saving learning csv file {0}".format(fileid))
print
LLlearn = bn2csv.generateCSV(bn, "BN{0}-{1}.csv".format(fileid, NBCASELEARN),
NBCASELEARN, True)
print("(*) saving test csv file {0}".format(fileid))
print
LLtest = bn2csv.generateCSV(bn, "BN{0}-{1}.csv".format(fileid, NBCASETEST),
NBCASETEST, True)
print("classe : {0}".format(CLASSE))
print("Modalités : {0}".format(bn.variable(CLASSE)))
print("parents :{0}".format(str(bn.parents(CLASSE))))
print("log-likelihood (learning): {0}".format(LLlearn))
def save_bn(bn, bn_url):
agrum.saveBN(bn, bn_url)
if sim_param.debug:
print("BN saved in " + bn_url)
bn.cpt(s).var_names
bn.cpt(w).var_names # [r, s, w]
bn.cpt(w)[0,0,:] = [1, 0] # when r=0, s=0
bn.cpt(w)[0,1,:] = [0.1, 0.9] # r=0, s=1
bn.cpt(w)[1,0,:] = [0.1, 0.9] # r=1, s=0
bn.cpt(w)[1,1,:] = [0.01, 0.99] # r=1, s=1
# use dictionaries to introduce data!! -- it facilitates and avoids common errors
bn.cpt(r)[{'c': 0}] = [0.8, 0.2]
bn.cpt(r)[{'c': 1}] = [0.2, 0.8]
# use the name (string) of the variable 'c' , do not use the variable itself c (it won't work)
# NOW YOUR BN IS COMPLETE!! #
# ------------------------------------------
# formats that we can save our bayesian network
# print(gum.availableBNExts())
# out: bif|dsl|net|bifxml|o3prm|uai
# Saving the BN in an archive
# gum.saveBN(bn, os.path.join("out","WaterSprinkler.bif"))
gum.saveBN(bn, "WaterSprinkler.bif")
# Loading a BN from an archive
bn2 = gum.loadBN("WaterSprinkler.bif")
print("(*) forcing node {0} to have at least {1} parents".format(CLASSE,NBRPARENTSMIN))
while (len(bn.parents(CLASSE))<NBRPARENTSMIN):
nvparent=int(gum.randomProba()*bn.size())
try:
bn.addArc(nvparent,CLASSE)
except gum.Exception:
print(" Failed in {0} with {1}".format(str(bn.parents(0)),nvparent))
print("(*) re-generating CPTs")
bn.generateCPTs()
fileid="{0}-{1}-{2}-{3}".format(datetime.datetime.now().strftime("%Y%m%d-%H%M%S"),NBRNOEUDS,NBRARCS,MODMAX)
print("(*) saving bif file {0}".format(fileid))
gum.saveBN(bn,"BN{0}.bif".format(fileid))
print("(*) saving learning csv file {0}".format(fileid))
print
LLlearn=bn2csv.generateCSV(bn,"BN{0}-{1}.csv".format(fileid,NBCASELEARN),NBCASELEARN,True)
print("(*) saving test csv file {0}".format(fileid))
print
LLtest=bn2csv.generateCSV(bn,"BN{0}-{1}.csv".format(fileid,NBCASETEST),NBCASETEST,True)
print("classe : {0}".format(CLASSE))
print("Modalités : {0}".format(bn.variable(CLASSE)))
print("parents :{0}".format(str(bn.parents(CLASSE))))
print("log-likelihood (learning): {0}".format(LLlearn))
print("log-likelihood (testing): {0}".format(LLtest))
#OR PERFORMANCE OF THIS SOFTWARE!# -*- coding: utf-8 -*-
import sys
import pyAgrum as gum
from gumLib.pyAgrum_header import pyAgrum_header
pyAgrum_header(2011)
bn=gum.BayesNet('exo1')
# sexe = 0(H)/1(F)
# daltonisme = 0(D) / 1 (nonD)
sexe,daltonisme=[bn.add(gum.LabelizedVar(nom,'',2)) for nom in 'sexe daltonisme'.split()]
bn.insertArc(sexe,daltonisme)
bn.cpt(sexe)[:]=[0.5, 0.5]
bn.cpt(daltonisme)[0,:]=[0.08, 0.92]
bn.cpt(daltonisme)[1,:]=[0.005,0.995]
bn.saveBIF("exo1.bif")
for line in open("exo1.bif"):
print line,
print("for gum.loadBN or gum.saveBN, possible files ext are ="+gum.availableBNExts())
gum.saveBN(bn,"exo1.dsl")
for line in open("exo1.dsl"):
print line,