def learn(data):
spn = SPN.LearnStructure(data, featureTypes=featureTypes, row_split_method=Splitting.Gower(), col_split_method=Splitting.RDCTest(threshold=0.3),
domains=domains,
alpha=1,
# spn = SPN.LearnStructure(data, featureNames=["X1"], domains =
# domains, families=families, row_split_method=Splitting.KmeansRows(),
# col_split_method=Splitting.RDCTest(),
min_instances_slice=50)
return spn
def learn(data):
spn = SPN.LearnStructure(data, featureTypes=featureTypes, row_split_method=Splitting.Gower(), col_split_method=Splitting.RDCTest(threshold=0.3),
domains=domains,
alpha=0.1,
families = ['histogram'] * data.shape[1],
# spn = SPN.LearnStructure(data, featureNames=["X1"], domains =
# domains, families=families, row_split_method=Splitting.KmeansRows(),
# col_split_method=Splitting.RDCTest(),
#min_instances_slice=int(data.shape[0]*0.01))
min_instances_slice=200)
return spn
def learn():
spn = SPN.LearnStructure(
data,
featureTypes=["discrete"] * data.shape[1],
row_split_method=Splitting.Gower(),
col_split_method=Splitting.RDCTest(threshold=0.3, linear=True),
# spn = SPN.LearnStructure(data, featureNames=["X1"], domains =
# domains, families=families, row_split_method=Splitting.KmeansRows(),
# col_split_method=Splitting.RDCTest(),
min_instances_slice=200)
return spn
def learn():
spn = SPN.LearnStructure(
traintopics,
featureTypes=featureTypes,
row_split_method=Splitting.Gower(),
col_split_method=Splitting.RDCTest(threshold=0.1, linear=True),
featureNames=featureNames,
domains=domains,
# spn = SPN.LearnStructure(data, featureNames=["X1"], domains =
# domains, families=families, row_split_method=Splitting.KmeansRows(),
# col_split_method=Splitting.RDCTest(),
min_instances_slice=100)
return spn
def estimate_density(self, training_data, validation_data=None):
"""Fit a MSPN on the training data. The variable validation_data is
never used."""
feature_types = []
feature_names = []
families = []
for feat, str_type in training_data.features:
feature_types.append(str_type)
feature_names.append(feat.symbol_name())
if 'leaf' in self.learner_args:
families.append(self.learner_args['leaf'])
else:
families.append(MSPNLearner.SPN_feat_fams[feat.symbol_type()])
if 'row_split' in self.learner_args:
if self.learner_args['row_split'] == 'gower':
row_split_method = Splitting.Gower(n_clusters=2)
elif self.learner_args['row_split'] == 'rdc-kmeans':
row_split_method = Splitting.KmeansRDCRows(n_clusters=2,
k=20,
OHE=1)
else:
raise NotImplementedError()
else:
row_split_method = Splitting.KmeansRDCRows(n_clusters=2,
k=20,
OHE=1)
col_split_method = Splitting.RDCTest(threshold=0.1, OHE=1, linear=1)
rand_seed = self.learner_args['seed']
mspnargs = {
k: v
for k, v in self.learner_args.items()
if k not in ['seed', 'leaf', 'row_split']
}
# let MSPNs sort this out
families = None
self.spn = SPN.LearnStructure(asarray(training_data.data),
feature_types,
families=families,
featureNames=feature_names,
rand_seed=rand_seed,
row_split_method=row_split_method,
col_split_method=col_split_method,
**mspnargs)
# plt.hist(test[:,0], bins=100, histtype='stepfilled', normed=True, color='r', alpha=0.5, label='Uniform')
#
# plt.show()
# print(domains)
print(feature_names)
print(feature_types)
print(train.shape)
# spn = SPN.LearnStructure(train, featureNames=feature_names, domains=domains, featureTypes=feature_types, row_split_method=Splitting.RandomPartitionConditioningRows(), col_split_method=Splitting.RDCTestOHEpy(threshold=0.75),
# spn = SPN.LearnStructure(train, featureNames=feature_names, domains=domains, featureTypes=feature_types, row_split_method=Splitting.DBScanOHE(eps=1.0, min_samples=2), col_split_method=Splitting.RDCTestOHEpy(threshold=0.75),
# spn = SPN.LearnStructure(train, featureNames=feature_names,
# domains=domains, featureTypes=feature_types,
# row_split_method=Splitting.KmeansOHERows(),
# col_split_method=Splitting.RDCTest(threshold=0.75),
spn = SPN.LearnStructure(train, featureNames=feature_names, domains=domains, featureTypes=feature_types, row_split_method=Splitting.Gower(), col_split_method=Splitting.RDCTest(threshold=0.05),
min_instances_slice=20, cluster_first=True)
print(spn)
result.append([dsname, numpy.mean(spn.root.eval(train)), numpy.mean(
spn.root.eval(valid)), numpy.mean(spn.root.eval(test))])
print("train", numpy.mean(spn.root.eval(train)))
print("valid", numpy.mean(spn.root.eval(valid)))
print("test", numpy.mean(spn.root.eval(test)))
print("train", numpy.min(spn.root.eval(train)))
print("valid", numpy.min(spn.root.eval(valid)))
print("test", numpy.min(spn.root.eval(test)))
print(result)
