def run_fractional_stratification_model(
estimator=None,
data_path=None,
config_path=None,
num_iter=1,
seed=None):
'''
Fractional Stratification Model Analysis
'''
if estimator is None or data_path is None or config_path is None:
raise ValueError('Need Estimator, Data path and Config Path as arguments !')
data, config_map = read_input(data_path, config_path)
data = data_preprocessor(data, config_map, 5, 'string')
training_map = {}
for _ in range(0, num_iter):
training_data, validation_data, testing_data = fractional_stratification(
data, data.columns, 4, [0.6, 0.2, 0.2], config_map, seed)
X_train, y_train = split_data(training_data, config_map)
X_validation, y_validation = split_data(validation_data, config_map)
X_test, y_test = split_data(testing_data, config_map)
X_scaler, y_scaler, model, training_rmse = training(
estimator, X_train, y_train, config_map)
validation_rmse = calculate_rmse(
X_validation,
y_validation,
X_scaler,
y_scaler,
model,
config_map)
testing_rmse = calculate_rmse(
X_test, y_test, X_scaler, y_scaler, model, config_map)
if training_rmse < validation_rmse:
model_properties = {}
model_properties['estimator'] = estimator
model_properties['config_map'] = config_map
model_properties['X_train'] = X_train
model_properties['y_train'] = y_train
model_properties['X_validation'] = X_validation
model_properties['y_validation'] = y_validation
model_properties['X_test'] = X_test
model_properties['y_test'] = y_test
model_properties['X_scaler'] = X_scaler
model_properties['y_scaler'] = y_scaler
model_properties['model'] = model
model_properties['training_rmse'] = training_rmse
model_properties['validation_rmse'] = validation_rmse
model_properties['testing_rmse'] = testing_rmse
training_map[validation_rmse] = model_properties
if(len(training_map) > 0):
best_model_properties = training_map[min(training_map)]
print('Best Model train error: {} | Best Model validation error: {} | Best Model test error: {}'.format(
round(best_model_properties['training_rmse'], 7),
round(best_model_properties['validation_rmse'], 7),
round(best_model_properties['testing_rmse'], 7)))
return best_model_properties
return None
def run_model_tuning(model_properties=None):
'''
Tunes the Model based on Training and Validation error
'''
if model_properties is None:
raise ValueError('Need Model Properties as argument !')
alphas = np.logspace(-10, 1, 400)
config_map = model_properties['config_map']
X_train = model_properties['X_train']
y_train = model_properties['y_train']
X_validation = model_properties['X_validation']
y_validation = model_properties['y_validation']
X_test = model_properties['X_test']
y_test = model_properties['y_test']
tuning_map = {}
for alpha in alphas:
estimator = Ridge(alpha=alpha)
X_scaler, y_scaler, model, training_rmse = training(
estimator, X_train, y_train, config_map)
validation_rmse = calculate_rmse(
X_validation,
y_validation,
X_scaler,
y_scaler,
model,
config_map)
testing_rmse = calculate_rmse(
X_test, y_test, X_scaler, y_scaler, model, config_map)
tuning_properties = {}
tuning_properties['estimator'] = estimator
tuning_properties['config_map'] = config_map
tuning_properties['X_scaler'] = X_scaler
tuning_properties['y_scaler'] = y_scaler
tuning_properties['model'] = model
tuning_properties['training_rmse'] = training_rmse
tuning_properties['validation_rmse'] = validation_rmse
tuning_properties['testing_rmse'] = testing_rmse
tuning_map[validation_rmse] = tuning_properties
if(len(tuning_map) > 0):
best_model_properties = tuning_map[min(tuning_map)]
best_model_properties['config_map'] = config_map
best_model_properties['X_train'] = X_train
best_model_properties['y_train'] = y_train
best_model_properties['X_validation'] = X_validation
best_model_properties['y_validation'] = y_validation
best_model_properties['X_test'] = X_test
best_model_properties['y_test'] = y_test
print('Best Model train error: {} | Best Model validation error: {} | Best Model test error: {}'.format(
round(best_model_properties['training_rmse'], 7),
round(best_model_properties['validation_rmse'], 7),
round(best_model_properties['testing_rmse'], 7)))
return best_model_properties
return None
def run_train_test_model(
estimator=None,
data_path=None,
config_path=None,
num_iter=1,
seed=None):
'''
Train/test Model Analysis
'''
if estimator is None or data_path is None or config_path is None:
raise ValueError('Need Estimator, Data path and Config Path as arguments !')
data, config_map = read_input(data_path, config_path)
data = data_preprocessor(data, config_map, 5, 'string')
training_map = {}
for _ in range(0, num_iter):
X_train, y_train, X_test, y_test = split_train_test_data(
data, config_map, 0.3, seed)
X_scaler, y_scaler, model, training_rmse = training(
estimator, X_train, y_train, config_map)
testing_rmse = calculate_rmse(
X_test, y_test, X_scaler, y_scaler, model, config_map)
if training_rmse < testing_rmse:
model_properties = {}
model_properties['estimator'] = estimator
model_properties['config_map'] = config_map
model_properties['X_train'] = X_train
model_properties['y_train'] = y_train
model_properties['X_test'] = X_test
model_properties['y_test'] = y_test
model_properties['X_scaler'] = X_scaler
model_properties['y_scaler'] = y_scaler
model_properties['model'] = model
model_properties['training_rmse'] = training_rmse
model_properties['testing_rmse'] = testing_rmse
training_map[testing_rmse] = model_properties
if(len(training_map) > 0):
best_model_properties = training_map[min(training_map)]
print('Best Model train error: {} | Best Model test error: {}'.format(
round(best_model_properties['training_rmse'], 7),
round(best_model_properties['testing_rmse'], 7)))
return best_model_properties
return None
def test_testing_error(self):
testing_rmse = calculate_rmse(self.X_test, self.y_test, self.X_scaler,
self.y_scaler, self.model,
self.config_map)
self.assertAlmostEqual(testing_rmse, 0.0007581966925813912)
def test_validation_error(self):
validation_rmse = calculate_rmse(self.X_validation, self.y_validation,
self.X_scaler, self.y_scaler,
self.model, self.config_map)
self.assertAlmostEqual(validation_rmse, 0.0007615906548161986)