def sample(self, start_state=None, size=1):
"""
Sample from the Markov Chain.
Parameters:
-----------
start_state: dict or array-like iterable
Representing the starting states of the variables. If None is passed, a random start_state is chosen.
size: int
Number of samples to be generated.
Return Type:
------------
pandas.DataFrame
Examples:
---------
>>> from pgmpy.models import MarkovChain as MC
>>> from pgmpy.factors.discrete import State
>>> model = MC(['intel', 'diff'], [2, 3])
>>> model.set_start_state([State('intel', 0), State('diff', 2)])
>>> intel_tm = {0: {0: 0.25, 1: 0.75}, 1: {0: 0.5, 1: 0.5}}
>>> model.add_transition_model('intel', intel_tm)
>>> diff_tm = {0: {0: 0.1, 1: 0.5, 2: 0.4}, 1: {0: 0.2, 1: 0.2, 2: 0.6 }, 2: {0: 0.7, 1: 0.15, 2: 0.15}}
>>> model.add_transition_model('diff', diff_tm)
>>> model.sample(size=5)
intel diff
0 0 2
1 1 0
2 0 1
3 1 0
4 0 2
"""
if start_state is None:
if self.state is None:
self.state = self.random_state()
# else use previously-set state
else:
self.set_start_state(start_state)
sampled = DataFrame(index=range(size), columns=self.variables)
sampled.loc[0] = [st for var, st in self.state]
var_states = defaultdict(dict)
var_values = defaultdict(dict)
samples = defaultdict(dict)
for var in self.transition_models.keys():
for st in self.transition_models[var]:
var_states[var][st] = list(self.transition_models[var][st].keys())
var_values[var][st] = list(self.transition_models[var][st].values())
samples[var][st] = sample_discrete(var_states[var][st], var_values[var][st], size=size)
for i in range(size - 1):
for j, (var, st) in enumerate(self.state):
next_st = samples[var][st][i]
self.state[j] = State(var, next_st)
sampled.loc[i + 1] = [st for var, st in self.state]
return sampled
def generate_sample(self, start_state=None, size=1):
"""
Generator version of self.sample
Returns
-------
List of State namedtuples, representing the assignment to all variables of the model.
Examples
--------
>>> from pgmpy.models.MarkovChain import MarkovChain
>>> from pgmpy.factors.discrete import State
>>> model = MarkovChain()
>>> model.add_variables_from(['intel', 'diff'], [3, 2])
>>> intel_tm = {0: {0: 0.2, 1: 0.4, 2:0.4}, 1: {0: 0, 1: 0.5, 2: 0.5}, 2: {0: 0.3, 1: 0.3, 2: 0.4}}
>>> model.add_transition_model('intel', intel_tm)
>>> diff_tm = {0: {0: 0.5, 1: 0.5}, 1: {0: 0.25, 1:0.75}}
>>> model.add_transition_model('diff', diff_tm)
>>> gen = model.generate_sample([State('intel', 0), State('diff', 0)], 2)
>>> [sample for sample in gen]
[[State(var='intel', state=2), State(var='diff', state=1)],
[State(var='intel', state=2), State(var='diff', state=0)]]
"""
if start_state is None:
if self.state is None:
self.state = self.random_state()
# else use previously-set state
else:
self.set_start_state(start_state)
# sampled.loc[0] = [self.state[var] for var in self.variables]
for i in range(size):
for j, (var, st) in enumerate(self.state):
next_st = sample_discrete(
list(self.transition_models[var][st].keys()),
list(self.transition_models[var][st].values()),
)[0]
self.state[j] = State(var, next_st)
yield self.state[:]
def generate_sample(self, start_state=None, size=1):
"""
Generator version of self.sample
Return Type:
------------
List of State namedtuples, representing the assignment to all variables of the model.
Examples:
---------
>>> from pgmpy.models.MarkovChain import MarkovChain
>>> from pgmpy.factors.discrete import State
>>> model = MarkovChain()
>>> model.add_variables_from(['intel', 'diff'], [3, 2])
>>> intel_tm = {0: {0: 0.2, 1: 0.4, 2:0.4}, 1: {0: 0, 1: 0.5, 2: 0.5}, 2: {0: 0.3, 1: 0.3, 2: 0.4}}
>>> model.add_transition_model('intel', intel_tm)
>>> diff_tm = {0: {0: 0.5, 1: 0.5}, 1: {0: 0.25, 1:0.75}}
>>> model.add_transition_model('diff', diff_tm)
>>> gen = model.generate_sample([State('intel', 0), State('diff', 0)], 2)
>>> [sample for sample in gen]
[[State(var='intel', state=2), State(var='diff', state=1)],
[State(var='intel', state=2), State(var='diff', state=0)]]
"""
if start_state is None:
if self.state is None:
self.state = self.random_state()
# else use previously-set state
else:
self.set_start_state(start_state)
# sampled.loc[0] = [self.state[var] for var in self.variables]
for i in range(size):
for j, (var, st) in enumerate(self.state):
next_st = sample_discrete(list(self.transition_models[var][st].keys()),
list(self.transition_models[var][st].values()))[0]
self.state[j] = State(var, next_st)
yield self.state[:]