def results_visualization(history, composed_chains):
visualiser = ChainVisualiser()
visualiser.visualise_history(history)
visualiser.pareto_gif_create(history.archive_history, history.chains)
visualiser.boxplots_gif_create(history.chains)
for chain_evo_composed in composed_chains:
visualiser.visualise(chain_evo_composed)
def run_chain_ang_history_visualisation(generations=2,
pop_size=10,
with_chain_visualisation=True):
""" Function run visualisation of composing history and chain """
# Generate chain and history
chain = chain_first()
history = generate_history(generations, pop_size)
visualiser = ChainVisualiser()
visualiser.visualise_history(history)
if with_chain_visualisation:
visualiser.visualise(chain)
def run_credit_scoring_problem(
train_file_path,
test_file_path,
max_lead_time: datetime.timedelta = datetime.timedelta(minutes=5),
is_visualise=False,
with_tuning=False):
task = Task(TaskTypesEnum.classification)
dataset_to_compose = InputData.from_csv(train_file_path, task=task)
dataset_to_validate = InputData.from_csv(test_file_path, task=task)
# the search of the models provided by the framework that can be used as nodes in a chain for the selected task
available_model_types, _ = ModelTypesRepository().suitable_model(
task_type=task.task_type)
# the choice of the metric for the chain quality assessment during composition
metric_function = MetricsRepository().metric_by_id(
ClassificationMetricsEnum.ROCAUC_penalty)
# the choice and initialisation of the GP search
composer_requirements = GPComposerRequirements(
primary=available_model_types,
secondary=available_model_types,
max_arity=3,
max_depth=3,
pop_size=20,
num_of_generations=20,
crossover_prob=0.8,
mutation_prob=0.8,
max_lead_time=max_lead_time)
# GP optimiser parameters choice
scheme_type = GeneticSchemeTypesEnum.steady_state
optimiser_parameters = GPChainOptimiserParameters(
genetic_scheme_type=scheme_type)
# Create builder for composer and set composer params
builder = GPComposerBuilder(
task=task).with_requirements(composer_requirements).with_metrics(
metric_function).with_optimiser_parameters(optimiser_parameters)
# Create GP-based composer
composer = builder.build()
# the optimal chain generation by composition - the most time-consuming task
chain_evo_composed = composer.compose_chain(data=dataset_to_compose,
is_visualise=True)
if with_tuning:
chain_evo_composed.fine_tune_primary_nodes(
input_data=dataset_to_compose, iterations=50, verbose=True)
chain_evo_composed.fit(input_data=dataset_to_compose, verbose=True)
if is_visualise:
visualiser = ChainVisualiser()
composer.log.info('History visualization started')
visualiser.visualise_history(composer.history)
composer.log.info('History visualization finished')
composer.history.write_composer_history_to_csv()
composer.log.info('Best chain visualization started')
visualiser.visualise(chain_evo_composed)
composer.log.info('Best chain visualization finished')
# the quality assessment for the obtained composite models
roc_on_valid_evo_composed = calculate_validation_metric(
chain_evo_composed, dataset_to_validate)
print(f'Composed ROC AUC is {round(roc_on_valid_evo_composed, 3)}')
return roc_on_valid_evo_composed
chain.add_node(root_node_child)
root_of_tree.nodes_from.append(root_node_child)
chain.add_node(root_of_tree)
return chain
def generate_history(generations, pop_size):
history = ComposingHistory()
for gen in range(generations):
new_pop = []
for idx in range(pop_size):
chain = chain_first()
chain.fitness = 1 / (gen * idx + 1)
new_pop.append(chain)
history.add_to_history(new_pop)
return history
if __name__ == '__main__':
generations = 2
pop_size = 10
chain = chain_first()
history = generate_history(generations, pop_size)
visualiser = ChainVisualiser()
visualiser.visualise_history(history)
visualiser.visualise(chain)
def run_credit_scoring_problem(
train_file_path,
test_file_path,
max_lead_time: datetime.timedelta = datetime.timedelta(minutes=5),
is_visualise=False,
with_tuning=False,
cache_path=None):
task = Task(TaskTypesEnum.classification)
dataset_to_compose = InputData.from_csv(train_file_path, task=task)
dataset_to_validate = InputData.from_csv(test_file_path, task=task)
# the search of the models provided by the framework that can be used as nodes in a chain for the selected task
available_model_types = get_operations_for_task(task=task, mode='models')
# the choice of the metric for the chain quality assessment during composition
metric_function = ClassificationMetricsEnum.ROCAUC_penalty
# the choice and initialisation of the GP search
composer_requirements = GPComposerRequirements(
primary=available_model_types,
secondary=available_model_types,
max_arity=3,
max_depth=3,
pop_size=20,
num_of_generations=20,
crossover_prob=0.8,
mutation_prob=0.8,
max_lead_time=max_lead_time)
# GP optimiser parameters choice
scheme_type = GeneticSchemeTypesEnum.parameter_free
optimiser_parameters = GPChainOptimiserParameters(
genetic_scheme_type=scheme_type)
# Create builder for composer and set composer params
logger = default_log('FEDOT logger', verbose_level=4)
builder = GPComposerBuilder(task=task).with_requirements(composer_requirements). \
with_metrics(metric_function).with_optimiser_parameters(optimiser_parameters).with_logger(logger=logger)
if cache_path:
builder = builder.with_cache(cache_path)
# Create GP-based composer
composer = builder.build()
# the optimal chain generation by composition - the most time-consuming task
chain_evo_composed = composer.compose_chain(data=dataset_to_compose,
is_visualise=True)
if with_tuning:
# TODO Add tuning
raise NotImplementedError(f'Tuning is not supported')
chain_evo_composed.fit(input_data=dataset_to_compose)
composer.history.write_composer_history_to_csv()
if is_visualise:
visualiser = ChainVisualiser()
composer.log.debug('History visualization started')
visualiser.visualise_history(composer.history)
composer.log.debug('History visualization finished')
composer.log.debug('Best chain visualization started')
visualiser.visualise(chain_evo_composed)
composer.log.debug('Best chain visualization finished')
# the quality assessment for the obtained composite models
roc_on_valid_evo_composed = calculate_validation_metric(
chain_evo_composed, dataset_to_validate)
print(f'Composed ROC AUC is {round(roc_on_valid_evo_composed, 3)}')
return roc_on_valid_evo_composed