def infer_distribution(self):
if self.is_categorical:
distribution = self.data_dropna.value_counts()
for value in set(self.distribution_bins) - set(distribution.index):
distribution[value] = 0
distribution.sort_index(inplace=True)
self.distribution_probabilities = normalize_given_distribution(distribution)
self.distribution_bins = np.array(distribution.index)
else:
distribution = np.histogram(self.data_dropna_len, bins=self.histogram_size)
self.distribution_bins = distribution[1][:-1]
self.distribution_probabilities = normalize_given_distribution(distribution[0])
def infer_distribution(self):
if self.is_categorical:
histogram = self.data_dropna.value_counts()
for value in set(self.distribution_bins) - set(histogram.index):
histogram[value] = 0
histogram = histogram[self.distribution_bins]
self.distribution_probabilities = normalize_given_distribution(
histogram)
else:
histogram, _ = np.histogram(self.data_dropna,
bins=self.distribution_bins)
self.distribution_probabilities = normalize_given_distribution(
histogram)
def _construct_conditional_probabilities(self, bayesian_network,
encoded_dataset):
k = len(bayesian_network[-1][1])
conditional_distributions = {}
# first k+1 attributes
root = bayesian_network[0][1][0]
kplus1_attributes = [root]
for child, _ in bayesian_network[:k]:
kplus1_attributes.append(child)
freqs_of_kplus1_attributes = self._get_attribute_frequency_counts(
kplus1_attributes, encoded_dataset)
# get distribution of root attribute
root_marginal_freqs = freqs_of_kplus1_attributes.loc[:, [
root, 'count'
]].groupby(root).sum()['count']
conditional_distributions[root] = normalize_given_distribution(
root_marginal_freqs).tolist()
for idx, (child, parents) in enumerate(bayesian_network):
conditional_distributions[child] = {}
if idx < k:
stats = freqs_of_kplus1_attributes.copy().loc[:, parents +
[child, 'count']]
else:
stats = self._get_attribute_frequency_counts(
parents + [child], encoded_dataset)
stats = DataFrame(
stats.loc[:, parents +
[child, 'count']].groupby(parents + [child]).sum())
if len(parents) == 1:
for parent_instance in stats.index.levels[0]:
dist = normalize_given_distribution(
stats.loc[parent_instance]['count']).tolist()
conditional_distributions[child][str([parent_instance
])] = dist
else:
for parents_instance in product(*stats.index.levels[:-1]):
dist = normalize_given_distribution(
stats.loc[parents_instance]['count']).tolist()
conditional_distributions[child][str(
list(parents_instance))] = dist
return conditional_distributions
def infer_distribution(self):
histogram = self.data_dropna.value_counts()
for attr_cat in set(self.distribution_bins) - set(histogram.index):
histogram[attr_cat] = 0
histogram = histogram[self.distribution_bins]
self.distribution_probabilities = normalize_given_distribution(
histogram)
def infer_distribution(self):
frequency_counts, _ = histogram(self.data_dropna,
bins=self.distribution_bins)
self.distribution_probabilities = normalize_given_distribution(
frequency_counts)
