def test_cache_historical_state_using(data_setup):
cache = OperationsCache()
train, _ = data_setup
chain = chain_first()
# chain fitted, model goes to cache
chain.fit(input_data=train)
cache.save_chain(chain)
new_node = SecondaryNode(operation_type='logit')
old_node = chain.root_node.nodes_from[0]
# change child node to new one
chain.update_node(old_node=old_node, new_node=new_node)
# cache is not actual
assert not cache.get(chain.root_node)
# fit modified chain
chain.fit(input_data=train)
cache.save_chain(chain)
# cache is actual now
assert cache.get(chain.root_node)
# change node back
chain.update_node(old_node=chain.root_node.nodes_from[0],
new_node=old_node)
# cache is actual without new fitting,
# because the cached model was saved after first fit
assert cache.get(chain.root_node)
def test_cache_actuality_after_model_change(data_setup):
"""The non-affected nodes has actual cache after changing the model"""
cache = OperationsCache()
chain = chain_first()
train, _ = data_setup
chain.fit(input_data=train)
cache.save_chain(chain)
new_node = SecondaryNode(operation_type='logit')
chain.update_node(old_node=chain.root_node.nodes_from[0],
new_node=new_node)
root_parent_first = chain.root_node.nodes_from[0]
nodes_with_non_actual_cache = [chain.root_node, root_parent_first]
nodes_with_actual_cache = [
node for node in chain.nodes if node not in nodes_with_non_actual_cache
]
# non-affected nodes are actual
assert all(
[cache.get(node) is not None for node in nodes_with_actual_cache])
# affected nodes and their childs has no any actual cache
assert all(
[cache.get(node) is None for node in nodes_with_non_actual_cache])
def fit_from_cache(self, cache: OperationsCache):
for node in self.nodes:
cached_state = cache.get(node)
if cached_state:
node.fitted_operation = cached_state.operation
else:
node.fitted_operation = None
def test_multi_chain_caching_with_cache(data_setup):
train, _ = data_setup
cache = OperationsCache()
main_chain = chain_second()
other_chain = chain_first()
# fit other_chain that contains the parts identical to main_chain
other_chain.fit(input_data=train)
cache.save_chain(other_chain)
nodes_with_non_actual_cache = [main_chain.root_node, main_chain.root_node.nodes_from[0]] + \
[_ for _ in main_chain.root_node.nodes_from[0].nodes_from]
nodes_with_actual_cache = [
node for node in main_chain.nodes
if node not in nodes_with_non_actual_cache
]
# check that using of other_chain make identical of the main_chain fitted,
# despite the main_chain.fit() was not called
assert all([cache.get(node) for node in nodes_with_actual_cache])
# the non-identical parts are still not fitted
assert not any([cache.get(node) for node in nodes_with_non_actual_cache])
# check the same case with another chains
cache = OperationsCache()
main_chain = chain_fourth()
prev_chain_first = chain_third()
prev_chain_second = chain_fifth()
prev_chain_first.fit(input_data=train)
cache.save_chain(prev_chain_first)
prev_chain_second.fit(input_data=train)
cache.save_chain(prev_chain_second)
nodes_with_non_actual_cache = [
main_chain.root_node, main_chain.root_node.nodes_from[1]
]
nodes_with_actual_cache = [
child for child in main_chain.root_node.nodes_from[0].nodes_from
]
assert not any([cache.get(node) for node in nodes_with_non_actual_cache])
assert all([cache.get(node) for node in nodes_with_actual_cache])
def test_cache_actuality_after_subtree_change_to_identical(data_setup):
"""The non-affected nodes has actual cache after changing the subtree to other pre-fitted subtree"""
cache = OperationsCache()
train, _ = data_setup
pipeline = pipeline_first()
other_pipeline = pipeline_second()
pipeline.fit(input_data=train)
cache.save_pipeline(pipeline)
other_pipeline.fit(input_data=train)
cache.save_pipeline(Pipeline(other_pipeline.root_node.nodes_from[0]))
pipeline.update_subtree(pipeline.root_node.nodes_from[0],
other_pipeline.root_node.nodes_from[0])
nodes_with_actual_cache = [node for node in pipeline.nodes if node not in [pipeline.root_node]]
# non-affected nodes of initial pipeline and fitted nodes of new subtree are actual
assert all([cache.get(node) is not None for node in nodes_with_actual_cache])
# affected root node has no any actual cache
assert cache.get(pipeline.root_node) is None
def test_cache_actuality_after_primary_node_changed_to_subtree(data_setup):
""" The non-affected nodes has actual cache after changing the primary node to pre-fitted subtree"""
cache = OperationsCache()
train, _ = data_setup
pipeline = pipeline_first()
other_pipeline = pipeline_second()
pipeline.fit(input_data=train)
cache.save_pipeline(pipeline)
other_pipeline.fit(input_data=train)
pipeline.update_subtree(pipeline.root_node.nodes_from[0].nodes_from[0],
other_pipeline.root_node.nodes_from[0])
cache.save_pipeline(Pipeline(other_pipeline.root_node.nodes_from[0]))
root_parent_first = pipeline.root_node.nodes_from[0]
nodes_with_non_actual_cache = [pipeline.root_node, root_parent_first]
nodes_with_actual_cache = [node for node in pipeline.nodes if node not in nodes_with_non_actual_cache]
# non-affected nodes of initial pipeline and fitted nodes of new subtree are actual
assert all([cache.get(node) for node in nodes_with_actual_cache])
# affected root nodes and their childs has no any actual cache
assert not any([cache.get(node) for node in nodes_with_non_actual_cache])