def get_default_config(cls):
d = super(IqrSearch, cls).get_default_config()
# Remove parent_app slot for later explicit specification.
del d['parent_app']
# fill in plugin configs
d['data_set'] = plugin.make_config(get_data_set_impls())
d['descr_generator'] = \
plugin.make_config(get_descriptor_generator_impls())
d['nn_index'] = plugin.make_config(get_nn_index_impls())
ri_config = plugin.make_config(get_relevancy_index_impls())
if d['rel_index_config']:
ri_config.update(d['rel_index_config'])
d['rel_index_config'] = ri_config
df_config = DescriptorElementFactory.get_default_config()
if d['descriptor_factory']:
df_config.update(d['descriptor_factory'].get_config())
d['descriptor_factory'] = df_config
return d
def get_default_config(cls):
d = super(IqrSearch, cls).get_default_config()
# Remove parent_app slot for later explicit specification.
del d['parent_app']
# fill in plugin configs
d['data_set'] = plugin.make_config(get_data_set_impls())
d['descr_generator'] = \
plugin.make_config(get_descriptor_generator_impls())
d['nn_index'] = plugin.make_config(get_nn_index_impls())
ri_config = plugin.make_config(get_relevancy_index_impls())
if d['rel_index_config']:
ri_config.update(d['rel_index_config'])
d['rel_index_config'] = ri_config
df_config = DescriptorElementFactory.get_default_config()
if d['descriptor_factory']:
df_config.update(d['descriptor_factory'].get_config())
d['descriptor_factory'] = df_config
return d
def test_get_impls(self):
ntools.assert_equal(
set(get_relevancy_index_impls().keys()),
{
'LibSvmHikRelevancyIndex',
}
)
def update_working_index(self, nn_index):
"""
Initialize or update our current working index using the given
:class:`.NearestNeighborsIndex` instance given our current positively
labeled descriptor elements.
We only query from the index for new positive elements since the last
update or reset.
:param nn_index: :class:`.NearestNeighborsIndex` to query from.
:type nn_index: smqtk.algorithms.NearestNeighborsIndex
:raises RuntimeError: There are no positive example descriptors in this
session to use as a basis for querying.
"""
pos_examples = (self.external_positive_descriptors |
self.positive_descriptors)
if len(pos_examples) == 0:
raise RuntimeError("No positive descriptors to query the neighbor "
"index with.")
# Not clearing working index because this step is intended to be
# additive.
updated = False
# adding to working index
self._log.info("Building working index using %d positive examples "
"(%d external, %d adjudicated)",
len(pos_examples),
len(self.external_positive_descriptors),
len(self.positive_descriptors))
# TODO: parallel_map and reduce with merge-dict
for p in pos_examples:
if p.uuid() not in self._wi_seeds_used:
self._log.debug("Querying neighbors to: %s", p)
self.working_index.add_many_descriptors(
nn_index.nn(p, n=self.pos_seed_neighbors)[0]
)
self._wi_seeds_used.add(p.uuid())
updated = True
# Make new relevancy index
if updated:
self._log.info("Creating new relevancy index over working index.")
#: :type: smqtk.algorithms.relevancy_index.RelevancyIndex
self.rel_index = plugin.from_plugin_config(
self.rel_index_config, get_relevancy_index_impls()
)
self.rel_index.build_index(self.working_index.iterdescriptors())
def update_working_index(self, nn_index):
"""
Initialize or update our current working index using the given
:class:`.NearestNeighborsIndex` instance given our current positively
labeled descriptor elements.
We only query from the index for new positive elements since the last
update or reset.
:param nn_index: :class:`.NearestNeighborsIndex` to query from.
:type nn_index: smqtk.algorithms.NearestNeighborsIndex
:raises RuntimeError: There are no positive example descriptors in this
session to use as a basis for querying.
"""
pos_examples = (self.external_positive_descriptors
| self.positive_descriptors)
if len(pos_examples) == 0:
raise RuntimeError("No positive descriptors to query the neighbor "
"index with.")
# Not clearing working index because this step is intended to be
# additive.
updated = False
# adding to working index
self._log.info(
"Building working index using %d positive examples "
"(%d external, %d adjudicated)", len(pos_examples),
len(self.external_positive_descriptors),
len(self.positive_descriptors))
# TODO: parallel_map and reduce with merge-dict
for p in pos_examples:
if p.uuid() not in self._wi_seeds_used:
self._log.debug("Querying neighbors to: %s", p)
self.working_index.add_many_descriptors(
nn_index.nn(p, n=self.pos_seed_neighbors)[0])
self._wi_seeds_used.add(p.uuid())
updated = True
# Make new relevancy index
if updated:
self._log.info("Creating new relevancy index over working index.")
#: :type: smqtk.algorithms.relevancy_index.RelevancyIndex
self.rel_index = plugin.from_plugin_config(
self.rel_index_config, get_relevancy_index_impls())
self.rel_index.build_index(self.working_index.iterdescriptors())
def test_get_impls(self):
ntools.assert_equal(set(get_relevancy_index_impls().keys()), {
'LibSvmHikRelevancyIndex',
})