def __init__(self):
print("Starting Tutorial4...")
net = pysmile.Network()
net.read_file("tutorial1.xdsl")
s = net.get_node("Success")
i = self.create_node(net, pysmile.NodeType.DECISION, "Invest",
"Investment decision", ["Invest", "DoNotInvest"],
160, 240)
g = self.create_node(net, pysmile.NodeType.UTILITY, "Gain",
"Financial gain", None, 60, 200)
net.add_arc(i, g)
net.add_arc(s, g)
gain_definition = [
10000, # Utility(Invest=I, Success=S)
-5000, # Utility(Invest=I, Success=F)
500, # Utility(Invest=D, Success=S)
500 # Utility(Invest=D, Success=F)
]
net.set_node_definition(g, gain_definition)
net.write_file("tutorial4.xdsl")
print("Tutorial4 complete:" +
" Influence diagram written to tutorial4.xdsl.")
def __init__(self):
print("Starting Tutorial3...")
net = pysmile.Network()
# load the network created by Tutorial1
net.read_file("tutorial1.xdsl")
for h in net.get_all_nodes():
self.print_node_info(net, h)
print("Tutorial3 complete.")
def __init__(self, width, height):
net = pysmile.Network()
# net.read_file("MineSweeper.xdsl")
self.width = width
self.height = height
self.net = net
self.create_fields(net)
self.create_field_values(net)
def main():
print("vi kjoerer")
feverNet = pysmile.Network()
print("lagde nettverk")
feverNet.read_file("FluModel.xdsl")
feverNet.set_evidence("flu", "True")
feverNet.update_beliefs()
beliefs = feverNet.get_node_value("HighTemp")
for i in range(0, len(beliefs)):
print(feverNet.get_outcome_id("HighTemp", i) + "=" + str(beliefs[i]))
def hello_smile():
net = pysmile.Network()
#Read XDSL file from disk
net.read_file("VentureBN.xdsl")
#Set the evidence on the 'Forecast' node to 'Moderate'
net.set_evidence("Forecast", "Moderate")
#Update the network
net.update_beliefs()
#Get values(Success, Failure) of Success node
beliefs = net.get_node_value("Success")
for i in range(0, len(beliefs)):
print(net.get_outcome_id("Success", i) + "=" + str(beliefs[i]))
def __init__(self):
print("Starting Tutorial5...")
net = pysmile.Network()
net.read_file("tutorial4.xdsl")
print("No evidence set.")
net.update_beliefs()
self.print_financial_gain(net)
print("Setting Forecast=Good.")
self.change_evidence_and_update(net, "Forecast", "Good")
print("Adding Economy=Up")
self.change_evidence_and_update(net, "Economy", "Up")
print("Tutorial5 complete.")
def __init__(self):
net = pysmile.Network()
# load the network created in the class CreatingBN
net.read_file("Network.xdsl")
#Update the probabilities and display them using the method print_all_posteriors() defined below
print("Posteriors with no evidence set:")
net.update_beliefs()
self.print_all_posteriors(net)
#Fix the state of each node using its id
print("Setting Engage_in_Learning_Goals =Learned.")
self.change_evidence_and_update(net, "Engage_in_Learning_Goals", "Learned")
print("MonitorEvaluateProgress=InProgress.")
self.change_evidence_and_update(net, "MonitorEvaluateProgress", "InProgress")
print("Changing MonitorEvaluateProgress to NotLearned, Keeping Engage_in_Learning_Goals=Learned.")
self.change_evidence_and_update(net, "MonitorEvaluateProgress", "NotLearned")
print("Removing evidence from Engage_in_Learning_Goals , keeping MonitorEvaluateProgress=NotLearned.")
self.change_evidence_and_update(net, "Engage_in_Learning_Goals", None)
print("Inferences are successfully done")
def __init__(self):
print("Starting Tutorial2...")
net = pysmile.Network()
# load the network created by Tutorial1
net.read_file("tutorial1.xdsl")
print("Posteriors with no evidence set:")
net.update_beliefs()
self.print_all_posteriors(net)
print("Setting Forecast=Good.")
self.change_evidence_and_update(net, "Forecast", "Good")
print("Adding Economy=Up.")
self.change_evidence_and_update(net, "Economy", "Up")
print("Changing Forecast to Poor, keeping Economy=Up.")
self.change_evidence_and_update(net, "Forecast", "Poor")
print("Removing evidence from Economy, keeping Forecast=Poor.")
self.change_evidence_and_update(net, "Economy", None)
print("Tutorial2 complete.")
def __init__(self):
net = pysmile.Network()
e = self.create_cpt_node(net,
"Economy", "State of the economy",
["Up","Flat","Down"],
160, 40)
s = self.create_cpt_node(net,
"Success", "Success of the venture",
["Success","Failure"],
60, 40)
f = self.create_cpt_node(net,
"Forecast", "Expert forecast",
["Good","Moderate","Poor"],
110, 140)
#Add arcs linking the nodes (two-way)
#1. using node variable
#2. using node id
net.add_arc(e, s); #e->s
net.add_arc(s, f); #s->f
net.add_arc("Economy", "Forecast"); #e->f
#Initialize the conditional probability tables of the node
economyDef = [
0.2, # P(Economy=U)
0.7, # P(Economy=F)
0.1 # P(Economy=D)
]
net.set_node_definition(e, economyDef);
successDef =[
0.3, # P(Success=S|Economy=U)
0.7, # P(Success=F|Economy=U)
0.2, # P(Success=S|Economy=F)
0.8, # P(Success=F|Economy=F)
0.1, # P(Success=S|Economy=D)
0.9 # P(Success=F|Economy=D)
]
net.set_node_definition(s, successDef);
forecastDef = [
0.70, # P(Forecast=G|Success=S,Economy=U)
0.29, # P(Forecast=M|Success=S,Economy=U)
0.01, # P(Forecast=P|Success=S,Economy=U)
0.65, # P(Forecast=G|Success=S,Economy=F)
0.30, # P(Forecast=M|Success=S,Economy=F)
0.05, # P(Forecast=P|Success=S,Economy=F)
0.60, # P(Forecast=G|Success=S,Economy=D)
0.30, # P(Forecast=M|Success=S,Economy=D)
0.10, # P(Forecast=P|Success=S,Economy=D)
0.15, # P(Forecast=G|Success=F,Economy=U)
0.30, # P(Forecast=M|Success=F,Economy=U)
0.55, # P(Forecast=P|Success=F,Economy=U)
0.10, # P(Forecast=G|Success=F,Economy=F)
0.30, # P(Forecast=M|Success=F,Economy=F)
0.60, # P(Forecast=P|Success=F,Economy=F)
0.05, # P(Forecast=G|Success=F,Economy=D)
0.25, # P(Forecast=G|Success=F,Economy=D)
0.70 # P(Forecast=G|Success=F,Economy=D)
]
net.set_node_definition(f, forecastDef);
#Write network to the XDSL file
net.write_file("tutorial1.xdsl");
print("Tutorial1 complete: Network written to tutorial1.xdsl")
def __init__(self):
# Iniziamo dichiarando la variabile Network. I nodi nel network sono creati
# in sequenza chiamando l'helper method create_cpt_node
net = pysmile.Network()
a = self.create_cpt_node(net, "asia", "Asia", ["Yes", "No"], 60, 40)
t = self.create_cpt_node(net, "tub", "Tuberculosis", ["Yes", "No"],
110, 140)
e = self.create_cpt_node(net, "either", "Either", ["Yes", "No"], 160,
240)
x = self.create_cpt_node(net, "xray", "XRay", ["Yes", "No"], 110, 340)
l = self.create_cpt_node(net, "lung", "LungCancer", ["Yes", "No"], 210,
140)
s = self.create_cpt_node(net, "smoke", "Smoke", ["Yes", "No"], 260, 40)
b = self.create_cpt_node(net, "bronc", "Bronchitis", ["Yes", "No"],
260, 140)
d = self.create_cpt_node(net, "dysp", "Dyspnea", ["Yes", "No"], 260,
240)
#possiamo ora aggiungere gli archi che collegano i nodi
net.add_arc(a, t)
net.add_arc(s, l)
net.add_arc(s, b)
net.add_arc(l, e)
net.add_arc(t, e)
net.add_arc(b, d)
net.add_arc(e, x)
net.add_arc(e, d)
asiaDef = [
0.01, # P(asia=Y)
0.99 # P(asia=N)
]
# il prossimo step e' la creazione delle tabelle di probabilita' condizionata. Per ogni nodo chiamiamo
# net.set_node_definition e in questo modo settiamo le probabilita'
net.set_node_definition(a, asiaDef)
tubDef = [
0.05, # P(tub=Y|asia=Y)
0.95, # P(tub=N|asia=Y)
0.01, # P(tub=Y|asia=N)
0.99 # P(tub=N|asia=N)
]
net.set_node_definition(t, tubDef)
smokeDef = [
0.5, # P(smoke=Y)
0.5 # P(smoke=N)
]
net.set_node_definition(s, smokeDef)
lungDef = [
0.1, # P(lung=Y|smoke=Y)
0.9, # P(lung=N|smoke=Y)
0.01, # P(lung=Y|smoke=N)
0.99 # P(lung=N|smoke=N)
]
net.set_node_definition(l, lungDef)
eitherDef = [
1, # P(either=Y|lung=Y,tub=Y)
0, # P(either=N|lung=Y,tub=Y)
1, # P(either=Y|lung=Y,tub=N)
0, # P(either=N|lung=Y,tub=N)
1, # P(either=Y|lung=N,tub=Y)
0, # P(either=N|lung=N,tub=Y)
0, # P(either=Y|lung=N,tub=N)
1 # P(either=N|lung=N,tub=N)
]
net.set_node_definition(e, eitherDef)
xrayDef = [
0.98, # P(xray=Y|either=Y)
0.02, # P(xray=N|either=Y)
0.05, # P(xray=Y|either=N)
0.95 # P(xray=N|either=N)
]
net.set_node_definition(x, xrayDef)
broncDef = [
0.6, # P(bronc=Y|smoke=Y)
0.4, # P(bronc=N|smoke=Y)
0.3, # P(bronc=Y|smoke=N)
0.7 # P(bronc=N|smoke=N)
]
net.set_node_definition(b, broncDef)
dyspDef = [
0.9, # P(dysp=Y|bronc=Y,either=Y)
0.1, # P(dysp=N|bronc=Y,either=Y)
0.8, # P(dysp=Y|bronc=Y,either=N)
0.2, # P(dysp=N|bronc=Y,either=N)
0.7, # P(dysp=Y|bronc=N,either=Y)
0.3, # P(dysp=N|bronc=N,either=Y)
0.1, # P(dysp=Y|bronc=N,either=N)
0.9 # P(dysp=N|bronc=N,either=N)
]
net.set_node_definition(d, dyspDef)
print("Network created!")
print("")
#Update delle probabilita' e si procede a mostrarle usando l'helper method print_all_posteriors
print("Posteriors with no evidence set:")
net.update_beliefs()
self.print_all_posteriors(net)
print("")
print("Set or change evidences")
print("")
print("Setting Either=Yes, Asia=Yes and Dyspnea=No")
self.change_evidence_and_update(net, "either", "Yes")
self.change_evidence_and_update(net, "asia", "Yes")
self.change_evidence_and_update(net, "dysp", "No")
print(
"Setting Smoke=No, changing Either to No, keeping Asia=Yes and Dyspnea=No"
)
self.change_evidence_and_update(net, "smoke", "No")
self.change_evidence_and_update(net, "either", "No")
print(
"Removing evidence from Asia and Dyspnea, setting Bronchitis=Yes, keeping Either=No and Smoke=No"
)
self.change_evidence_and_update(net, "asia", None)
self.change_evidence_and_update(net, "dysp", None)
self.change_evidence_and_update(net, "bronc", "Yes")
print("Nodes information")
print("")
for h in net.get_all_nodes():
self.print_node_info(net, h)
def initialize_network():
network = pysmile.Network()
network.read_file(gv.file_string)
return update_cases(network)
def __init__(self, numMines, size, fileName="Minesweeper.xdsl"):
self.net = pysmile.Network()
self.fileName = fileName
self.numMines = numMines
self.generate_network(size)
def __init__(self, model_path, threshold=0.95):
self.net = pysmile.Network()
self.net.read_file(model_path)
self.threshold = threshold
def net_setup():
net = pysmile.Network()
net.read_file("mma.xdsl")
return net
def __init__(self):
net = pysmile.Network()
#Defining of nodes
lof = self.create_cpt_node(net,"Level_of_SelfRegulation", "Level of Self-regulation",["Bad","Intermediate","Good"],200, 40)
eng = self.create_fcpt_node(net,"Engage_in_Learning_Goals", "Engage in Learning Goals",["NotLearned","InProgress","Learned"],160, 48)
eval = self.create_cpt_node(net,"MonitorEvaluateProgress", "Evaluate and Monitor the progress",["NotLearned","InProgress","Learned"],110, 140)
under = self.create_cpt_node(net,"Understand_and_describe_Goals_Plan", "Understand and describe Goals ( Plan )",["NotLearned","InProgress","Learned"],111, 160)
mang = self.create_cpt_node(net,"Manage_the_obstacles_Challenges", "Manage the obstacles/Challenges",["NotLearned","InProgress","Learned"],98, 170)
res = self.create_cpt_node(net,"ResourceManagement", "Manage the Resources",["NotLearned","InProgress","Learned"],141, 180)
htd = self.create_cpt_node(net,"HowToDo", "Execute Tasks (How To Do)",["NotLearned","InProgress","Learned"],181, 98)
task = self.create_cpt_node(net,"Identify_and_Descibe_tasks", "Identify and Descibe tasks",["NotLearned","InProgress","Learned"],171, 150)
react = self.create_cpt_node(net,"React_to_different_situations_Adaptability", "React to different situations / Adaptability",["NotLearned","InProgress","Learned"],45, 180)
#Defining of arcs
net.add_arc(eng, lof)
net.add_arc(eval, lof)
net.add_arc(under, eng)
net.add_arc(eng, task)
net.add_arc(react, task)
net.add_arc(task, res)
net.add_arc(res, htd)
net.add_arc(htd, mang)
net.add_arc(mang, eval)
#Defining of Conditional Probability Table (CPT) for each node
underCPT = [
0.091856061, # P(under=N)
0.38162879, # P(under=I)
0.52651515 # P(under=L)
]
net.set_node_definition(under, underCPT)
reactCPT = [
0.1174242424242424, # P(react=N)
0.4839015151515152, # P(react=I)
0.3986742424242424 # P(react=L)
]
net.set_node_definition(react, reactCPT)
evalCPT = [
#--------State=NotLearned
0.27693333, # P(eval=N|mang=N)
0.229771138561716, # P(eval=N|mang=I)
0.1561223732085839, # P(eval=N|mang=L)
#--------State=InProgress
0.4649333333333333, # P(eval=I|mang=N)
0.5256631236234798, # P(eval=I|mang=I)
0.6753916982252913, # P(eval=I|mang=L)
#--------State=Learned
0.2581333333333333, # P(eval=L|mang=N)
0.2445657378148041, # P(eval=L|mang=I)
0.1684859285661246 # P(eval=L|mang=L)
]
net.set_node_definition(eval, evalCPT)
engCPT = [
#--------State=NotLearned
0.3482304422842233, # P(eng=N|under=N)
0.324035516777932, # P(eng=N|under=I)
0.2131292517006803, # P(eng=N|under=L)
#--------State=InProgress
0.3258847788578882, # P(eng=I|under=N)
0.4216625906096459, # P(eng=I|under=I)
0.4341496598639455, # P(eng=I|under=L)
#--------State=Learned
0.3258847788578882, # P(eng=L|under=N)
0.2543018926124221, # P(eng=L|under=I)
0.3527210884353741 # P(eng=L|under=L)
]
net.set_node_definition(eng, engCPT)
mangCPT = [
#--------State=NotLearned
0.2606293333333333, # P(mang=N|htd=N)
0.2230315643426986, # P(mang=N|htd=I)
0.2613190058755145, # P(mang=N|htd=L)
#--------State=InProgress
0.3424213333333334, # P(mang=I|htd=N)
0.3057578910856746, # P(mang=I|htd=I)
0.3693404970622428, # P(mang=I|htd=L)
#--------State=Learned
0.3969493333333333, # P(mang=L|htd=N)
0.4712105445716268, # P(mang=L|htd=I)
0.3693404970622428 # P(mang=L|htd=L)
]
net.set_node_definition(mang, mangCPT)
htdCPT = [
#--------State=NotLearned
0.2606293333333333, # P(htd=N|res=N)
0.2230315643426986, # P(htd=N|res=I)
0.2613190058755145, # P(htd=N|res=L)
#--------State=InProgress
0.3424213333333334, # P(htd=I|res=N)
0.3057578910856746, # P(htd=I|res=I)
0.3693404970622428, # P(htd=I|res=L)
#--------State=Learned
0.3969493333333333, # P(htd=L|res=N)
0.4712105445716268, # P(htd=L|res=I)
0.3693404970622428 # P(htd=L|res=L)
]
net.set_node_definition(htd, htdCPT)
taskCPT = [
#--------State=NotLearned
0.3333333333333333, # P(task=N|eng=N|react=N)
0.3062973222530009, # P(task=N|eng=N|react=I)
0.3145333333333334, # P(task=N|eng=N|react=L)
0.3406584362139918, # P(task=N|eng=I|react=N)
0.4130527210884354, # P(task=N|eng=I|react=I)
0.2988014714607808, # P(task=N|eng=I|react=L)
0.3626337448559671, # P(task=N|eng=L|react=N)
0.4161735700197238, # P(task=N|eng=L|react=I)
0.3265743305632502, # P(task=N|eng=L|react=L)
#--------State=InProgress
0.3333333333333333, # P(task=I|eng=N|react=N)
0.3468513388734995, # P(task=I|eng=N|react=I)
0.3145333333333334, # P(task=I|eng=N|react=L)
0.3406584362139918, # P(task=I|eng=I|react=N)
0.3333333333333333, # P(task=I|eng=I|react=I)
0.4196629880147146, # P(task=I|eng=I|react=L)
0.3186831275720165, # P(task=I|eng=L|react=N)
0.3274161735700197, # P(task=I|eng=L|react=I)
0.3468513388734996, # P(task=I|eng=L|react=L)
#--------State=Learned
0.3333333333333333, # P(task=L|eng=N|react=N)
0.3468513388734995, # P(task=L|eng=N|react=I)
0.3709333333333333, # P(task=L|eng=N|react=L)
0.3186831275720165, # P(task=L|eng=I|react=N)
0.2536139455782313, # P(task=L|eng=I|react=I)
0.2815355405245045, # P(task=L|eng=I|react=L)
0.3186831275720165, # P(task=L|eng=L|react=N)
0.2564102564102564, # P(task=L|eng=L|react=I)
0.3265743305632502 # P(task=L|eng=L|react=L)
]
net.set_node_definition(task, taskCPT)
resCPT = [
#--------State=NotLearned
0.4023970570784384, # P(res=N|task=N)
0.4053476607911521, # P(res=N|task=I)
0.3549490802238055, # P(res=N|task=L)
#--------State=InProgress
0.3505992642696095, # P(res=I|task=N)
0.351336915197788, # P(res=I|task=I)
0.3117175864428612, # P(res=I|task=L)
#--------State=Learned
0.2470036786519521, # P(res=L|task=N)
0.2433154240110598, # P(res=L|task=I)
0.3333333333333334, # P(res=L|task=L)
]
net.set_node_definition(res, resCPT)
lofCPT = [
#--------State=Bad
0.1, # P(lof=B|eval=N|eng=N)
0.3, # P(lof=B|eval=N|eng=I)
0.0, # P(lof=B|eval=N|eng=L)
0.1, # P(lof=B|eval=I|eng=N)
0.1, # P(lof=B|eval=I|eng=I)
0.1, # P(lof=B|eval=I|eng=L)
0.1, # P(lof=B|eval=L|eng=N)
0.1, # P(lof=B|eval=L|eng=I)
0.1, # P(lof=B|eval=L|eng=L)
#--------State=Intermediate
0.5, # P(lof=I|eval=N|eng=N)
0.4, # P(lof=I|eval=N|eng=I)
0.6, # P(lof=I|eval=N|eng=L)
0.5, # P(lof=I|eval=I|eng=N)
0.5, # P(lof=I|eval=I|eng=I)
0.6, # P(lof=I|eval=I|eng=L)
0.6, # P(lof=I|eval=L|eng=N)
0.6, # P(lof=I|eval=L|eng=I)
0.6, # P(lof=I|eval=L|eng=L)
#--------State=Good
0.4, # P(lof=G|eval=N|eng=N)
0.3, # P(lof=G|eval=N|eng=I)
0.4, # P(lof=G|eval=N|eng=L)
0.4, # P(lof=G|eval=I|eng=N)
0.4, # P(lof=G|eval=I|eng=I)
0.3, # P(lof=G|eval=I|eng=L)
0.3, # P(lof=G|eval=L|eng=N)
0.3, # P(lof=G|eval=L|eng=I)
0.3 # P(lof=G|eval=L|eng=L)
]
net.set_node_definition(lof, lofCPT)
#save the file "Network.xdsl" in the current directory
net.write_file("Network.xdsl")
print("Network written to Network.xdsl")
