def set_structure(self, edge_dict, value_dict=None):
"""
Set the structure of a BayesNet object. This
function is mostly used to instantiate a BN
skeleton after structure learning algorithms.
See "structure_learn" folder & algorithms
Arguments
---------
*edge_dict* : a dictionary,
where key = rv,
value = list of rv's children
NOTE: THIS MUST BE DIRECTED ALREADY!
*value_dict* : a dictionary,
where key = rv,
value = list of rv's possible values
Returns
-------
None
Effects
-------
- sets self.V in topsort order from edge_dict
- sets self.E
- creates self.F structure and sets the parents
Notes
-----
"""
self.V = topsort(edge_dict)
self.E = edge_dict
self.F = dict([(rv, {}) for rv in self.nodes()])
for rv in self.nodes():
self.F[rv] = {
'parents': [p for p in self.nodes() if rv in self.children(p)],
'cpt': [],
'values': []
}
if value_dict is not None:
self.F[rv]['values'] = value_dict[rv]
def set_structure(self, edge_dict, value_dict=None):
"""
Set the structure of a BayesNet object. This
function is mostly used to instantiate a BN
skeleton after structure learning algorithms.
See "structure_learn" folder & algorithms
Arguments
---------
*edge_dict* : a dictionary,
where key = rv,
value = list of rv's children
NOTE: THIS MUST BE DIRECTED ALREADY!
*value_dict* : a dictionary,
where key = rv,
value = list of rv's possible values
Returns
-------
None
Effects
-------
- sets self.V in topsort order from edge_dict
- sets self.E
- creates self.F structure and sets the parents
Notes
-----
"""
self.V = topsort(edge_dict)
self.E = edge_dict
self.F = dict([(rv,{}) for rv in self.nodes()])
for rv in self.nodes():
self.F[rv] = {
'parents':[p for p in self.nodes() if rv in self.children(p)],
'cpt': [],
'values': []
}
if value_dict is not None:
self.F[rv]['values'] = value_dict[rv]
def read_bif(path):
"""
This function reads a .bif file into a
BayesNet object. It's probably not the
fastest or prettiest but it gets the job
done.
Arguments
---------
*path* : a string
The path
Returns
-------
*bn* : a BayesNet object
Effects
-------
None
Notes
-----
*V* : a list of strings
*E* : a dict, where key = vertex, val = list of its children
*F* : a dict, where key = rv, val = another dict with
keys = 'parents', 'values', cpt'
"""
_parents = {} # key = vertex, value = list of vertices in the scope (includind itself)
_cpt = {} # key = vertex, value = list (then numpy array)
_vals = {} # key=vertex, val=list of its possible values
with open(path, 'r') as f:
while True:
line = f.readline()
if 'variable' in line:
new_vertex = line.split()[1]
_parents[new_vertex] = []
_cpt[new_vertex] = []
#_vals[new_vertex] = []
new_line = f.readline()
new_vals = new_line.replace(',', ' ').split()[6:-1] # list of vals
_vals[new_vertex] = new_vals
num_outcomes = len(new_vals)
elif 'probability' in line:
line = line.replace(',', ' ')
child_rv = line.split()[2]
parent_rvs = line.split()[4:-2]
if len(parent_rvs) == 0: # prior
new_line = f.readline().replace(';', ' ').replace(',',' ').split()
prob_values = new_line[1:]
_cpt[child_rv].append(map(float,prob_values))
#_cpt[child_rv] = map(float,prob_values)
else: # not a prior
_parents[child_rv].extend(list(parent_rvs))
while True:
new_line = f.readline()
if '}' in new_line:
break
new_line = new_line.replace(',',' ').replace(';',' ').replace('(', ' ').replace(')', ' ').split()
prob_values = new_line[-(len(_vals[new_vertex])):]
prob_values = map(float,prob_values)
_cpt[child_rv].append(prob_values)
if line == '':
break
# CREATE FACTORS
_F = {}
_E = {}
for rv in _vals.keys():
_E[rv] = [c for c in _vals.keys() if rv in _parents[c]]
f = {
'parents' : _parents[rv],
'values' : _vals[rv],
'cpt' : [item for sublist in _cpt[rv] for item in sublist]
}
_F[rv] = f
bn = BayesNet()
bn.F = _F
bn.E = _E
bn.V = list(topsort(_E))
return bn
def read_json(path):
"""
Read a BayesNet object from the json format. This
format has the ".bn" extension and is completely
unique to pyBN.
Arguments
---------
*path* : a string
The file path
Returns
-------
None
Effects
-------
- Instantiates and sets a new BayesNet object
Notes
-----
This function reads in a libpgm-style format into a bn object
File Format:
{
"V": ["Letter", "Grade", "Intelligence", "SAT", "Difficulty"],
"E": [["Intelligence", "Grade"],
["Difficulty", "Grade"],
["Intelligence", "SAT"],
["Grade", "Letter"]],
"Vdata": {
"Letter": {
"ord": 4,
"numoutcomes": 2,
"vals": ["weak", "strong"],
"parents": ["Grade"],
"children": None,
"cprob": [[.1, .9],[.4, .6],[.99, .01]]
},
...
}
"""
def byteify(input):
if isinstance(input, dict):
return {byteify(key):byteify(value) for key,value in input.iteritems()}
elif isinstance(input, list):
return [byteify(element) for element in input]
elif isinstance(input, unicode):
return input.encode('utf-8')
else:
return input
bn = BayesNet()
f = open(path,'r')
ftxt = f.read()
success=False
try:
data = byteify(json.loads(ftxt))
bn.V = data['V']
bn.E = data['E']
bn.F = data['F']
success = True
except ValueError:
print "Could not read file - check format"
bn.V = topsort(bn.E)
return bn
def read_bif(path):
"""
This function reads a .bif file into a
BayesNet object. It's probably not the
fastest or prettiest but it gets the job
done.
Arguments
---------
*path* : a string
The path
Returns
-------
*bn* : a BayesNet object
Effects
-------
None
Notes
-----
*V* : a list of strings
*E* : a dict, where key = vertex, val = list of its children
*F* : a dict, where key = rv, val = another dict with
keys = 'parents', 'values', cpt'
"""
_parents = {
} # key = vertex, value = list of vertices in the scope (includind itself)
_cpt = {} # key = vertex, value = list (then numpy array)
_vals = {} # key=vertex, val=list of its possible values
with open(path, 'r') as f:
while True:
line = f.readline()
if 'variable' in line:
new_vertex = line.split()[1]
_parents[new_vertex] = []
_cpt[new_vertex] = []
#_vals[new_vertex] = []
new_line = f.readline()
new_vals = new_line.replace(',',
' ').split()[6:-1] # list of vals
_vals[new_vertex] = new_vals
num_outcomes = len(new_vals)
elif 'probability' in line:
line = line.replace(',', ' ')
child_rv = line.split()[2]
parent_rvs = line.split()[4:-2]
if len(parent_rvs) == 0: # prior
new_line = f.readline().replace(';',
' ').replace(',',
' ').split()
prob_values = new_line[1:]
_cpt[child_rv].append(map(float, prob_values))
#_cpt[child_rv] = map(float,prob_values)
else: # not a prior
_parents[child_rv].extend(list(parent_rvs))
while True:
new_line = f.readline()
if '}' in new_line:
break
new_line = new_line.replace(',', ' ').replace(
';', ' ').replace('(', ' ').replace(')',
' ').split()
prob_values = new_line[-(len(_vals[new_vertex])):]
prob_values = map(float, prob_values)
_cpt[child_rv].append(prob_values)
if line == '':
break
# CREATE FACTORS
_F = {}
_E = {}
for rv in _vals.keys():
_E[rv] = [c for c in _vals.keys() if rv in _parents[c]]
f = {
'parents': _parents[rv],
'values': _vals[rv],
'cpt': [item for sublist in _cpt[rv] for item in sublist]
}
_F[rv] = f
bn = BayesNet()
bn.F = _F
bn.E = _E
bn.V = list(topsort(_E))
return bn
def read_json(path):
"""
Read a BayesNet object from the json format. This
format has the ".bn" extension and is completely
unique to pyBN.
Arguments
---------
*path* : a string
The file path
Returns
-------
None
Effects
-------
- Instantiates and sets a new BayesNet object
Notes
-----
This function reads in a libpgm-style format into a bn object
File Format:
{
"V": ["Letter", "Grade", "Intelligence", "SAT", "Difficulty"],
"E": [["Intelligence", "Grade"],
["Difficulty", "Grade"],
["Intelligence", "SAT"],
["Grade", "Letter"]],
"Vdata": {
"Letter": {
"ord": 4,
"numoutcomes": 2,
"vals": ["weak", "strong"],
"parents": ["Grade"],
"children": None,
"cprob": [[.1, .9],[.4, .6],[.99, .01]]
},
...
}
"""
def byteify(input):
if isinstance(input, dict):
return {
byteify(key): byteify(value)
for key, value in input.iteritems()
}
elif isinstance(input, list):
return [byteify(element) for element in input]
elif isinstance(input, unicode):
return input.encode('utf-8')
else:
return input
bn = BayesNet()
f = open(path, 'r')
ftxt = f.read()
success = False
try:
data = byteify(json.loads(ftxt))
bn.V = data['V']
bn.E = data['E']
bn.F = data['F']
success = True
except ValueError:
print("Could not read file - check format")
bn.V = topsort(bn.E)
return bn