def generate_BN_explanations(instance, label_lst, feature_names, class_var,
encoder, scaler, model, path, dataset_name):
# necessary for starting Numpy generated random numbers in an initial state
np.random.seed(515)
# Necessary for starting core Python generated random numbers in a state
rn.seed(515)
indx = instance['index']
prediction_type = instance['prediction_type'].lower() + "s"
prediction_type = prediction_type.replace(" ", "_")
# generate permutations
df = generate_permutations(instance, label_lst, feature_names, class_var,
encoder, scaler, model)
# discretize data
df_discr = discretize_dataframe(df, class_var, num_bins=4)
# save discretised dataframe (for debugging and reproduceability purposes)
path_to_permutations = path + "feature_permutations/" + dataset_name.replace(
".csv", "") + "/" + prediction_type + "/" + str(indx) + ".csv"
df_discr.to_csv(path_to_permutations, index=False)
# normalise dataframe
normalise_dataframe(path_to_permutations)
# learn BN
bn, infoBN, essencGraph = learnBN(
path_to_permutations.replace(".csv", "_norm.csv"))
# perform inference
inference = gnb.getInference(bn,
evs={},
targets=df_discr.columns.to_list(),
size='12')
# show networks
gnb.sideBySide(
*[bn, inference, infoBN],
captions=["Bayesian Network", "Inference", "Information Network"])
# save to file
path_to_explanation = path + "explanations/" + dataset_name.replace(
".csv", "") + "/BN/" + prediction_type + "/"
gum.lib.bn2graph.dotize(bn, path_to_explanation + str(indx) + "_BN")
gum.saveBN(bn, path_to_explanation + str(indx) + "_BN.net")
return [bn, inference, infoBN]
template.add(gum.LabelizedVariable("occupation", "occupation",['Tech-support', 'Craft-repair', 'Other-service', 'Sales', 'Exec-managerial', 'Prof-specialty', 'Handlers-cleaners', 'Machine-op-inspct', 'Adm-clerical', 'Farming-fishing', 'Transport-moving', 'Priv-house-serv', 'Protective-serv', 'Armed-Forces']))
gnb.showBN(template)
train_df.to_csv(os.path.join('/content/gdrive/My Drive/train_data2.csv'), index=False)
file = os.path.join('res', 'titanic', '/content/gdrive/My Drive/train_data2.csv')
learner = gum.BNLearner(file, template)
bn = learner.learnBN()
bn
gnb.showInformation(bn,{},size="20")
gnb.showInference(bn)
gnb.showPosterior(bn,evs={"sex": "Male", "age_range": '21-30'},target='target')
gnb.sideBySide(bn, gum.MarkovBlanket(bn, 'target'), captions=["Learned Bayesian Network", "Markov blanket of 'target'"])
ie=gum.LazyPropagation(bn)
init_belief(ie)
ie.addTarget('target')
result = testdf.apply(lambda x: is_well_predicted(ie, bn, 0.157935, x), axis=1)
result.value_counts(True)
positives = sum(result.map(lambda x: 1 if x.startswith("True") else 0 ))
total = result.count()
print("{0:.2f}% good predictions".format(positives/total*100))
showROC(bn,file, 'target', "True", True, True)
#
# $\color{red}{\text{TODO: understand these algorithms}}$
#
# **Using:** LocalSearchWithTabuList
# %% codecell
learner = gum.BNLearner(outPath, asiaBN) # using bn as template for variables
# Learn the structure of the BN
learner.useLocalSearchWithTabuList()
asiaBN_learnedStructure_localSearchAlgo = learner.learnBN()
print("Learned in {}ms".format(1000 * learner.currentTime()))
htmlInfo: str = gnb.getInformation(asiaBN_learnedStructure_localSearchAlgo)
gnb.sideBySide(asiaBN_learnedStructure_localSearchAlgo, htmlInfo)
# %% markdown
# Notice how the original .bif BN and parameter-learned BN and structure-learned BN are different:
# %% codecell
asiaBN
# %% codecell
asiaBN_learnedParams
# %% markdown
# [`ExactBNdistance`](https://hyp.is/1OhsSKy4EeqyemuIJO85ew/pyagrum.readthedocs.io/en/0.18.0/BNToolsCompar.html) is a class representing exacte computation of divergence and distance between BNs
# %% codecell
from pyAgrum import ExactBNdistance
exact: ExactBNdistance = gum.ExactBNdistance(asiaBN, asiaBN_learnedStructure_localSearchAlgo)