def test_less_than_three_columns_raises_error_with_correct_message(self):
try:
calculate_random_forest_mtry_hyperparameter(2, 'classification')
# Fail the test if the above call doesn't throw an error
self.fail()
except HealthcareAIError as e:
self.assertEqual(e.message, 'You need more than two columns to tune hyperparameters.')
def test_non_integer_columns_raises_error(self):
try:
calculate_random_forest_mtry_hyperparameter('regression_metrics', 'classification')
# Fail the test if the above call doesn't throw an error
self.fail()
except HealthcareAIError as e:
self.assertEqual(e.message, 'The number_of_columns must be an integer')
def test_bad_model_type_raises_error_with_correct_message(self):
try:
calculate_random_forest_mtry_hyperparameter(3, 'regression_metrics')
# Fail the test if the above call doesn't throw an error
self.fail()
except HealthcareAIError as e:
self.assertEqual(e.message, 'Please specify model type of \'regression\' or \'classification\'')
def test_bad_model_type_raises_error_with_correct_message(self):
try:
calculate_random_forest_mtry_hyperparameter(3, 'regression_metrics')
# Fail the test if the above call doesn't throw an error
self.fail()
except HealthcareAIError as e:
self.assertEqual(e.message, 'Please specify model type of \'regression\' or \'classification\'')
def test_non_integer_columns_raises_error(self):
try:
calculate_random_forest_mtry_hyperparameter('regression_metrics', 'classification')
# Fail the test if the above call doesn't throw an error
self.fail()
except HealthcareAIError as e:
self.assertEqual(e.message, 'The number_of_columns must be an integer')
def test_negative_columns_raises_error_with_correct_message(self):
try:
calculate_random_forest_mtry_hyperparameter(-10, 'classification')
# Fail the test if the above call doesn't throw an error
self.fail()
except HealthcareAIError as e:
self.assertEqual(e.message, 'You need more than two columns to tune hyperparameters.')
def random_forest_regressor(self,
trees=200,
scoring_metric='neg_mean_squared_error',
hyperparameter_grid=None,
randomized_search=True,
number_iteration_samples=5):
"""
A light wrapper for Sklearn's random forest regressor that performs
randomized search over an overridable default hyperparameter grid.
Args:
trees (int): number of trees to use if not performing a randomized
grid search scoring_metric (str): Any sklearn scoring metric
appropriate for regression
hyperparameter_grid (dict): hyperparameters by name
randomized_search (bool): True for randomized search (default)
number_iteration_samples (int): Number of models to train during the
randomized search for exploring the hyperparameter space. More may
lead to a better model, but will take longer.
Returns:
TrainedSupervisedModel:
"""
self.validate_regression('Random Forest Regressor')
if hyperparameter_grid is None:
max_features = hcai_helpers.calculate_random_forest_mtry_hyperparameter(
len(self.X_test.columns), self.model_type)
hyperparameter_grid = {
'n_estimators': [10, 50, 200],
'max_features': max_features
}
number_iteration_samples = 5
algorithm = get_algorithm(
RandomForestRegressor,
scoring_metric,
hyperparameter_grid,
randomized_search,
number_iteration_samples=number_iteration_samples,
n_estimators=trees)
trained_supervised_model = self._create_trained_supervised_model(
algorithm)
return trained_supervised_model
def random_forest_regressor(self,
trees=200,
scoring_metric='neg_mean_squared_error',
hyperparameter_grid=None,
randomized_search=True,
number_iteration_samples=5):
"""
A light wrapper for Sklearn's random forest regressor that performs
randomized search over an overridable default hyperparameter grid.
Args:
trees (int): number of trees to use if not performing a randomized
grid search scoring_metric (str): Any sklearn scoring metric
appropriate for regression
hyperparameter_grid (dict): hyperparameters by name
randomized_search (bool): True for randomized search (default)
number_iteration_samples (int): Number of models to train during the
randomized search for exploring the hyperparameter space. More may
lead to a better model, but will take longer.
Returns:
TrainedSupervisedModel:
"""
self.validate_regression('Random Forest Regressor')
if hyperparameter_grid is None:
max_features = hcai_helpers.calculate_random_forest_mtry_hyperparameter(len(self.X_test.columns),
self.model_type)
hyperparameter_grid = {'n_estimators': [10, 50, 200], 'max_features': max_features}
number_iteration_samples = 5
algorithm = get_algorithm(RandomForestRegressor,
scoring_metric,
hyperparameter_grid,
randomized_search,
number_iteration_samples=number_iteration_samples,
n_estimators=trees)
trained_supervised_model = self._create_trained_supervised_model(algorithm)
return trained_supervised_model
def test_one_hundred_columns_regression(self):
result = calculate_random_forest_mtry_hyperparameter(100, 'regression')
self.assertEqual(result, [32, 33, 34])
def test_one_hundred_columns_classification(self):
result = calculate_random_forest_mtry_hyperparameter(
100, 'classification')
self.assertEqual(result, [9, 10, 11])
def test_ten_columns_regression(self):
result = calculate_random_forest_mtry_hyperparameter(10, 'regression')
self.assertEqual(result, [2, 3, 4])
def test_three_columns_regression(self):
result = calculate_random_forest_mtry_hyperparameter(3, 'regression')
self.assertEqual(result, [1, 2, 3])
def test_one_hundred_columns_regression(self):
result = calculate_random_forest_mtry_hyperparameter(100, 'regression')
self.assertEqual(result, [32, 33, 34])
def test_one_hundred_columns_classification(self):
result = calculate_random_forest_mtry_hyperparameter(100, 'classification')
self.assertEqual(result, [9, 10, 11])
def test_ten_columns_regression(self):
result = calculate_random_forest_mtry_hyperparameter(10, 'regression')
self.assertEqual(result, [2, 3, 4])
def test_three_columns_regression(self):
result = calculate_random_forest_mtry_hyperparameter(3, 'regression')
self.assertEqual(result, [1, 2, 3])
