def test_optimize_modeling(self):
_feature_engineer: FeatureEngineer = FeatureEngineer(
df=DATA_SET,
target_feature='AveragePrice',
temp_dir=DATA_DIR,
auto_typing=False)
_feature_engineer.set_predictors(exclude_original_data=False)
_ga: GeneticAlgorithm = GeneticAlgorithm(
mode='model',
target=_feature_engineer.get_target(),
input_file_path=None,
train_data_file_path=None,
test_data_file_path=None,
valid_data_file_path=None,
df=None,
data_set=None,
features=_feature_engineer.get_predictors(),
re_split_data=False,
re_sample_cases=False,
re_sample_features=False,
re_populate=True,
max_trials=2,
max_features=-1,
labels=None,
models=['cat'],
model_params=None,
burn_in_generations=-1,
warm_start=True,
warm_start_strategy='monotone',
warm_start_constant_hidden_layers=0,
warm_start_constant_category='very_small',
max_generations=2,
pop_size=4,
mutation_rate=0.1,
mutation_prob=0.85,
parents_ratio=0.5,
early_stopping=0,
convergence=True,
convergence_measure='median',
timer_in_seconds=43200,
force_target_type=None,
plot=False,
output_file_path='data',
deep_learning_type='batch',
deep_learning_output_size=None,
log=False,
verbose=False,
checkpoint=True,
feature_engineer=_feature_engineer,
sampling_function=None)
_ga.optimize()
self.assertTrue(expr=_ga.evolution_gradient.get('max')[0] <=
_ga.evolution_gradient.get('max')[-1])
def test_optimize_modeling_text_clustering(self):
_ga: GeneticAlgorithm = GeneticAlgorithm(
mode='model',
target=None,
input_file_path=None,
train_data_file_path=DATA_FILE_PATH_CLUSTER,
test_data_file_path=None,
valid_data_file_path=None,
df=None,
data_set=None,
features=[PREDICTOR_CLUSTER],
re_split_data=False,
re_sample_cases=False,
re_sample_features=False,
re_populate=True,
max_trials=2,
max_features=-1,
labels=None,
models=['gsdmm'
], #[np.random.choice(a=list(CLUSTER_ALGORITHMS.keys()))],
model_params=None,
burn_in_generations=-1,
warm_start=True,
warm_start_strategy='monotone',
warm_start_constant_hidden_layers=0,
warm_start_constant_category='very_small',
max_generations=2,
pop_size=3,
mutation_prob=0.5,
mutation_rate=0.85,
early_stopping=0,
convergence=True,
convergence_measure='median',
timer_in_seconds=43200,
force_target_type=None,
plot=False,
output_file_path='data',
deep_learning_type='batch',
deep_learning_output_size=None,
log=False,
feature_engineer=None,
sampling_function=None,
**dict(sep=',', tokenize=True))
_ga.optimize()
self.assertTrue(expr=_ga.evolution_gradient.get('max')[0] <=
_ga.evolution_gradient.get('max')[-1])
def test_optimize_modeling_text_classification(self):
_ga: GeneticAlgorithm = GeneticAlgorithm(
mode='model',
target=TARGET_TEXT,
input_file_path=None,
train_data_file_path=TRAIN_DATA_PATH_TEXT,
test_data_file_path=TEST_DATA_PATH_TEXT,
valid_data_file_path=VALIDATION_DATA_PATH_TEXT,
df=None,
data_set=None,
features=PREDICTORS_TEXT,
re_split_data=False,
re_sample_cases=False,
re_sample_features=False,
re_populate=True,
max_trials=2,
max_features=-1,
labels=None,
models=['trans'],
model_params=None,
burn_in_generations=-1,
warm_start=True,
warm_start_strategy='monotone',
warm_start_constant_hidden_layers=0,
warm_start_constant_category='very_small',
max_generations=1,
pop_size=4,
mutation_rate=0.5,
mutation_prob=0.85,
early_stopping=0,
convergence=True,
convergence_measure='median',
timer_in_seconds=43200,
force_target_type=None,
plot=False,
output_file_path='data',
deep_learning_type='batch',
deep_learning_output_size=UNIQUE_LABELS,
log=False,
feature_engineer=None,
sampling_function=None,
**dict(sep=','))
_ga.optimize()
self.assertTrue(expr=_ga.evolution_gradient.get('max')[0] <=
_ga.evolution_gradient.get('max')[-1])
def test_save_evolution(self):
_feature_engineer: FeatureEngineer = FeatureEngineer(
df=DATA_SET, target_feature='AveragePrice')
_feature_engineer.set_predictors(exclude_original_data=False)
_ga: GeneticAlgorithm = GeneticAlgorithm(
mode='model',
target=_feature_engineer.get_target(),
input_file_path=None,
train_data_file_path=None,
test_data_file_path=None,
valid_data_file_path=None,
df=None,
data_set=None,
features=_feature_engineer.get_predictors(),
re_split_data=False,
re_sample_cases=False,
re_sample_features=False,
re_populate=True,
max_trials=2,
max_features=-1,
labels=None,
models=['cat'],
model_params=None,
burn_in_generations=-1,
warm_start=True,
warm_start_strategy='monotone',
warm_start_constant_hidden_layers=0,
warm_start_constant_category='very_small',
max_generations=5,
pop_size=64,
mutation_rate=0.1,
mutation_prob=0.15,
parents_ratio=0.5,
early_stopping=0,
convergence=True,
convergence_measure='median',
timer_in_seconds=43200,
force_target_type=None,
plot=False,
output_file_path='data',
deep_learning_type='batch',
deep_learning_output_size=None,
log=False,
feature_engineer=_feature_engineer,
sampling_function=None)
_ga.optimize()
_ga.save_evolution(ga=True,
model=True,
evolution_history=True,
generation_history=True,
final_generation=True)
_found_pickles: List[bool] = []
for pickle in [
'model', 'GeneticAlgorithm', 'evolution_history',
'generation_history', 'final_generation'
]:
if os.path.isfile('data/{}.p'.format(pickle)):
_found_pickles.append(True)
else:
_found_pickles.append(False)
self.assertTrue(expr=all(_found_pickles))
def test_visualize_reg(self):
_feature_engineer: FeatureEngineer = FeatureEngineer(
df=DATA_SET, target_feature='AveragePrice')
_feature_engineer.set_predictors(exclude_original_data=False)
_ga: GeneticAlgorithm = GeneticAlgorithm(
mode='model',
target=_feature_engineer.get_target(),
input_file_path=None,
train_data_file_path=None,
test_data_file_path=None,
valid_data_file_path=None,
df=None,
data_set=None,
features=_feature_engineer.get_predictors(),
re_split_data=False,
re_sample_cases=False,
re_sample_features=False,
re_populate=True,
max_trials=2,
max_features=-1,
labels=None,
models=None,
model_params=None,
burn_in_generations=-1,
warm_start=True,
warm_start_strategy='monotone',
warm_start_constant_hidden_layers=0,
warm_start_constant_category='very_small',
max_generations=5,
pop_size=4,
mutation_rate=0.1,
mutation_prob=0.15,
parents_ratio=0.5,
early_stopping=0,
convergence=True,
convergence_measure='median',
timer_in_seconds=43200,
force_target_type=None,
plot=False,
output_file_path='data',
deep_learning_type='batch',
deep_learning_output_size=None,
log=False,
feature_engineer=_feature_engineer,
sampling_function=None)
_ga.optimize()
_ga.visualize(results_table=True,
model_distribution=True,
model_evolution=True,
param_distribution=True,
train_time_distribution=True,
breeding_map=True,
breeding_graph=True,
fitness_distribution=True,
fitness_evolution=True,
fitness_dimensions=True,
per_generation=True,
prediction_of_best_model=True,
epoch_stats=True)
_found_plot: List[bool] = []
for plot in [
'ga_metadata_table',
'ga_model_evolution',
'ga_model_distribution',
#'ga_parameter_treemap',
'ga_training_time_distribution',
#'ga_breeding_heatmap',
#'ga_breeding_graph',
'ga_fitness_score_distribution_per_generation',
'ga_metadata_evolution_coords_actor_only',
'ga_evolution_fitness_score',
'ga_prediction_evaluation_coords',
'ga_prediction_scatter_contour'
]:
if os.path.isfile('data/{}.html'.format(plot)):
_found_plot.append(True)
else:
_found_plot.append(False)
self.assertTrue(expr=all(_found_plot))
def test_ga_clf(self):
_feature_engineer: FeatureEngineer = FeatureEngineer(
df=DATA_SET, target_feature='type')
_feature_engineer.set_predictors(exclude=None,
exclude_original_data=False)
_ga: GeneticAlgorithm = GeneticAlgorithm(
mode='model',
target=_feature_engineer.get_target(),
input_file_path=None,
train_data_file_path=None,
test_data_file_path=None,
valid_data_file_path=None,
df=None,
data_set=None,
features=_feature_engineer.get_predictors(),
re_split_data=False,
re_sample_cases=False,
re_sample_features=False,
re_populate=True,
max_trials=2,
max_features=-1,
labels=None,
models=['cat'],
model_params=None,
burn_in_generations=-1,
warm_start=True,
warm_start_strategy='monotone',
warm_start_constant_hidden_layers=0,
warm_start_constant_category='very_small',
max_generations=10,
pop_size=64,
mutation_rate=0.1,
mutation_prob=0.15,
parents_ratio=0.5,
early_stopping=0,
convergence=True,
convergence_measure='min',
timer_in_seconds=43200,
force_target_type=None,
plot=False,
output_file_path='data',
deep_learning_type='batch',
deep_learning_output_size=None,
log=False,
feature_engineer=_feature_engineer,
sampling_function=None)
_ga.optimize()
_feature_learning: FeatureLearning = FeatureLearning(
feature_engineer=_feature_engineer,
df=None,
file_path=None,
target=_feature_engineer.get_target(),
force_target_type=None,
max_features=-1,
keep_fittest_only=True,
train_categorical_critic=False,
train_continuous_critic=False,
engineer_time_disparity=True,
engineer_categorical=True,
engineer_text=True,
output_path='data')
_feature_learning_engineer = _feature_learning.ga()
_ga_using_new_features: GeneticAlgorithm = GeneticAlgorithm(
mode='model',
target=_feature_learning_engineer.get_target(),
input_file_path=None,
train_data_file_path=None,
test_data_file_path=None,
valid_data_file_path=None,
df=None,
data_set=None,
features=_feature_learning_engineer.get_predictors(),
re_split_data=False,
re_sample_cases=False,
re_sample_features=False,
re_populate=True,
max_trials=2,
max_features=-1,
labels=None,
models=['cat'],
model_params=None,
burn_in_generations=-1,
warm_start=True,
warm_start_strategy='monotone',
warm_start_constant_hidden_layers=0,
warm_start_constant_category='very_small',
max_generations=10,
pop_size=64,
mutation_rate=0.1,
mutation_prob=0.15,
parents_ratio=0.5,
early_stopping=0,
convergence=True,
convergence_measure='min',
timer_in_seconds=43200,
force_target_type=None,
plot=False,
output_file_path='data',
deep_learning_type='batch',
deep_learning_output_size=None,
log=False,
feature_engineer=_feature_learning_engineer,
sampling_function=None)
_ga_using_new_features.optimize()
self.assertTrue(
expr=_ga_using_new_features.final_generation[
_ga_using_new_features.best_individual_idx]['fitness_score'] >=
_ga.final_generation[_ga.best_individual_idx]['fitness_score'])