def test_make_DAG():
edges = [('Cloudy', 'Sprinkler')]
DAG = bn.make_DAG(edges)
# TEST 1
assert 'pgmpy.models.BayesianModel.BayesianModel' in str(type(
DAG['model']))
# TEST 2
cpt_cloudy = TabularCPD(variable='Cloudy',
variable_card=2,
values=[[0.3], [0.7]])
cpt_sprinkler = TabularCPD(variable='Sprinkler',
variable_card=2,
values=[[0.4, 0.9], [0.6, 0.1]],
evidence=['Cloudy'],
evidence_card=[2])
assert bn.make_DAG(DAG, CPD=[cpt_cloudy, cpt_sprinkler], checkmodel=True)
'pop scale', 'label'
]]
print(f"all data size:\t{df_final.size}")
print(f"all data num of successes:\t{df_final['label'].sum()}")
df_train, df_test = train_test_split(df_final, test_size=0.2, random_state=0)
print(f"train size: \t{df_train.size}")
print(f"train num of succes\t{df_train['label'].sum()}")
edges = [('top director', 'budget scale'), ('top director', 'week_num'),
('top director', 'main genre'), ('week_num', 'pop scale'),
('budget scale', 'label'), ('main genre', 'top actor'),
('top actor', 'pop scale'), ('label', 'pop scale')]
# Make the actual Bayesian DAG
DAG = bnlearn.make_DAG(edges)
# DAG is stored in adjacency matrix
print(DAG['adjmat'])
# No CPDs are in the DAG. Lets see what happens if we print it.
bnlearn.print_CPD(DAG)
# # Plot DAG. Note that it can be differently orientated if you re-make the plot.
# print("plotting")
# bnlearn.plot(DAG)
# print("stop plot")
# Parameter learning on the user-defined DAG and input data
DAG = bnlearn.parameter_learning.fit(DAG, df_train)
# %% Inference using custom DAG
import bnlearn as bn
# Load asia DAG
df = bn.import_example('asia')
# from tabulate import tabulate
# print(tabulate(df.head(), tablefmt="grid", headers="keys"))
print(df)
edges = [('smoke', 'lung'), ('smoke', 'bronc'), ('lung', 'xray'),
('bronc', 'xray')]
# edges = [('smoke', 'xray'),
# ('bronc', 'lung')]
# Make the actual Bayesian DAG
DAG = bn.make_DAG(edges)
# Plot the DAG
bn.plot(DAG)
# Print the CPDs
bn.print_CPD(DAG)
# Learn its parameters from data and perform the inference.
DAG = bn.parameter_learning.fit(DAG, df)
# Print the CPDs
bn.print_CPD(DAG)
# Make inference
q1 = bn.inference.fit(DAG, variables=['lung'], evidence={'smoke': 1})
q2 = bn.inference.fit(DAG, variables=['bronc'], evidence={'smoke': 1})
q3 = bn.inference.fit(DAG,
variables=['lung'],