PHOTONAI WIZARD

Design your pipeline

Analysis Name

Specify a name for this analysis.

Project Description

Please provide a short description of your project.

Project Folder

Please give a local directory for your photon analysis

Design Choices

You optimize for balanced_accuracy using random_grid_search.

Optimizer	random_grid_search	n_configurations: 30
Inner Cross Validation Strategy	KFold	n_splits: 3 \|shuffle: True
Outer Cross Validation Strategy	KFold	n_splits: 5 \|shuffle: True
Metrics	accuracy
	balanced_accuracy
	specificity
	sensitivity
Best Config Metric	balanced_accuracy

Transformers

Your pipeline contains 3 transformer elements specifying 4 hyperparameters.

LabelEncoder
SimpleImputer	missing_values	np.nan
	strategy	mean
	fill_value	0
PCA	n_components	FloatRange(0.2, 0.99)

Estimators

Your learning algorithm is RandomForestClassifier with 5 hyperparameters.

RandomForestClassifier	n_estimators	[25, 50, 75]
	criterion	gini
	max_depth	None
	min_samples_split	IntegerRange(2, 10)
	min_samples_leaf	IntegerRange(1, 10)

                        
                            
# Specify how results are going to be saved
# Define hyperpipe
hyperpipe = Hyperpipe('None',
                      project_folder = './results',
                      optimizer="random_grid_search",
                      optimizer_params={'n_configurations': 30},
                      metrics=['accuracy', 'balanced_accuracy', 'specificity', 'sensitivity'],
                      best_config_metric="balanced_accuracy",
                      outer_cv = KFold(n_splits=5,shuffle=True),
                      inner_cv = KFold(n_splits=3, shuffle=True))
        
# Add transformer elements
preprocessing_pipe = Preprocessing()
hyperpipe += preprocessing_pipe
preprocessing_pipe += PipelineElement("LabelEncoder") 
                        
hyperpipe += PipelineElement("SimpleImputer", hyperparameters={}, 
                             test_disabled=False, missing_values=np.nan, strategy='mean', fill_value=0)
hyperpipe += PipelineElement("PCA", hyperparameters={'n_components': FloatRange(0.2, 0.99)}, 
                             test_disabled=False)
hyperpipe += PipelineElement("RandomForestClassifier", hyperparameters={'n_estimators': [25, 50, 75], 'min_samples_split': IntegerRange(2, 10), 'min_samples_leaf': IntegerRange(1, 10)}, criterion='gini', max_depth=None)

PHOTONAI Wizard