def lasso_regression(self,
scoring_metric='neg_mean_squared_error',
hyperparameter_grid=None,
randomized_search=True,
number_iteration_samples=2):
"""
A light wrapper for Sklearn's lasso regression that performs randomized search over an overridable default
hyperparameter grid.
Args:
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('Lasso Regression')
if hyperparameter_grid is None:
hyperparameter_grid = {"fit_intercept": [True, False]}
number_iteration_samples = 2
algorithm = get_algorithm(
Lasso,
scoring_metric,
hyperparameter_grid,
randomized_search,
number_iteration_samples=number_iteration_samples)
trained_supervised_model = self._create_trained_supervised_model(
algorithm)
return trained_supervised_model
def logistic_regression(self,
scoring_metric='roc_auc',
hyperparameter_grid=None,
randomized_search=True,
number_iteration_samples=10):
"""
A light wrapper for Sklearn's logistic regression that performs randomized search over an overideable default
hyperparameter grid.
Args:
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_classification('Logistic Regression')
if hyperparameter_grid is None:
hyperparameter_grid = {'C': [0.01, 0.1, 1, 10, 100], 'class_weight': [None, 'balanced']}
number_iteration_samples = 10
algorithm = get_algorithm(LogisticRegression,
scoring_metric,
hyperparameter_grid,
randomized_search,
number_iteration_samples=number_iteration_samples)
trained_supervised_model = self._create_trained_supervised_model(algorithm)
return trained_supervised_model
def knn(self,
scoring_metric='roc_auc',
hyperparameter_grid=None,
randomized_search=True,
number_iteration_samples=10):
"""
A light wrapper for Sklearn's knn classifier that performs randomized search over an overridable default
hyperparameter grid.
Args:
scoring_metric (str): Any sklearn scoring metric appropriate for classification
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_classification('KNN')
if hyperparameter_grid is None:
neighbors = list(range(5, 26))
hyperparameter_grid = {'n_neighbors': neighbors, 'weights': ['uniform', 'distance']}
number_iteration_samples = 10
print('KNN Grid: {}'.format(hyperparameter_grid))
algorithm = get_algorithm(KNeighborsClassifier,
scoring_metric,
hyperparameter_grid,
randomized_search,
number_iteration_samples=number_iteration_samples)
trained_supervised_model = self._create_trained_supervised_model(algorithm)
return trained_supervised_model
def lasso_regression(self, scoring_metric='neg_mean_squared_error',
hyperparameter_grid=None,
randomized_search=True,
number_iteration_samples=2):
"""
A light wrapper for Sklearn's lasso regression that performs randomized
search over an overridable default hyperparameter grid.
Args:
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('Lasso Regression')
if hyperparameter_grid is None:
hyperparameter_grid = {"fit_intercept": [True, False]}
number_iteration_samples = 2
algorithm = get_algorithm(Lasso,
scoring_metric,
hyperparameter_grid,
randomized_search,
number_iteration_samples=number_iteration_samples)
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 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 knn(self,
scoring_metric='roc_auc',
hyperparameter_grid=None,
randomized_search=True,
number_iteration_samples=10):
"""
A light wrapper for Sklearn's knn classifier that performs randomized
search over an overridable default
hyperparameter grid.
Args:
scoring_metric (str): Any sklearn scoring metric appropriate for classification
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_classification('KNN')
if hyperparameter_grid is None:
neighbors = list(range(5, 26))
hyperparameter_grid = {'n_neighbors': neighbors, 'weights': ['uniform', 'distance']}
number_iteration_samples = 10
print('KNN Grid: {}'.format(hyperparameter_grid))
algorithm = get_algorithm(KNeighborsClassifier,
scoring_metric,
hyperparameter_grid,
randomized_search,
number_iteration_samples=number_iteration_samples)
trained_supervised_model = self._create_trained_supervised_model(algorithm)
return trained_supervised_model
def logistic_regression(self,
scoring_metric='roc_auc',
hyperparameter_grid=None,
randomized_search=True,
number_iteration_samples=10):
"""
A light wrapper for Sklearn's logistic regression that performs randomized
search over an overideable default
hyperparameter grid.
Args:
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_classification('Logistic Regression')
if hyperparameter_grid is None:
hyperparameter_grid = {'C': [0.01, 0.1, 1, 10, 100], 'class_weight': [None, 'balanced']}
number_iteration_samples = 10
algorithm = get_algorithm(LogisticRegression,
scoring_metric,
hyperparameter_grid,
randomized_search,
number_iteration_samples=number_iteration_samples)
trained_supervised_model = self._create_trained_supervised_model(algorithm)
return trained_supervised_model
