In [1]:

    

import pgmpy


    

In [2]:

    

from pgmpy.models import BayesianModel


    

In [8]:

    

model = BayesianModel([('a','b'),('c','b'),('c','d'),('b','e')])


    

In [10]:

    

model.check_model()


    

    
Out[10]:





True

In [15]:

    

model.get_independencies()


    

    
Out[15]:





b _|_ e, d, b, c | a
c _|_ d, a, c | b
c _|_ e, b, c | d
e _|_ e | b
b _|_ e, a, b, c | d
b _|_ e, a, b | c
e _|_ e, a, b, c | d
e _|_ e, a, b | c
d _|_ d, a, b, c | e
d _|_ e, d, b, c | a
a _|_ a, d, b, c | e
a _|_ a, d, c | b
d _|_ d, a, c | b
d _|_ d | c
a _|_ e, a, b | d
a _|_ e, a, b | c
c _|_ d, a, b, c | e
c _|_ e, d, b, c | a
e _|_ e, d, b, c | a
b _|_ d, a, b, c | e

In [16]:

    

import numpy as np
import numpy.random as npr
import pandas as pd
values = pd.DataFrame(np.random.randint(low=0, high=2, size=(1000, 5)),
                      columns=['a', 'b', 'c', 'd', 'e'])


    

In [20]:

    

train,test=values[:800],values[800:]


    

In [21]:

    

model.fit(train)


    

In [19]:

    

model.predict(


    

In [ ]: