Hive-ML config

Hive-ML configuration template

A JSON template used to set the configuration parameters for experiments based on Hive-ML framework.
properties
image_suffix	File suffix (or list of File suffixes) of the files containing the image volume. Example: “_image.nii.gz”
	type	string / array
mask_suffix	File suffix (including file extension) of the files containing the segmentation mask of the ROI. Example: “_mask.nii.gz”
	type	string
models	Dictionary for all the classifiers to evaluate. Each element includes the classifier class name and an additional dictionary with the kwargs to pass to the classifier object.
	type	object
feature_selection	Type of Feature Selection to perform. Supported values are SFFS and PCA .
	type	string
n_features	Number of features to preserve when performing Feature Selection. Example: 30.
	type	integer
feature_aggregator	Aggregation strategy used when extracting features in the 4D. Supported values are: Flat (no aggregation, all features are preserved), Mean (Average over the 4-th dimension), SD (Standard Deviation over the 4-th dimension), Mean_Norm (Independent channel-normalization, followed by average over the 4-th dimension), SD_Norm (Independent channel-normalization, followed by SD over the 4-th dimension)
	type	string
random_seed	Random seed number used when randomizing events and actions. Example: 12345
	type	integer
label_dict	Dictionary describing the classes. The key-value pair contains the label value as key (starting from 0) and the class description as value. Example: “0”: “pCR”
	type	object
	properties
	0	Class 0 Identifier.
		type	string
	1	Class 1 Identifier.
		type	string
perfusion_maps	Dictionary describing the perfusion maps to extract. Each element includes the perfusion map name and the file suffix used to save the perfusion map.
	type	object
n_folds	Number of folds to run cross-validation. Example: 5.
	type	integer
metric_best_model	Classification Metric to consider when determining the best models from CV results.
	type	string
reduction_best_model	Reduction to perform on CV scores to determine the best models.
	type	string

{
  "image_suffix": "_image.nii.gz",
  "mask_suffix": "_mask.nii.gz",
  "label_dict": {
    "0": "non-pCR",
    "1": "pCR"
  },
  "models": {
    "rf": {
      "criterion": "gini",
      "n_estimators": 100,
      "max_depth": 10
    },
    "adab": {
      "criterion": "gini",
      "n_estimators": 100,
      "max_depth": 10
    },
    "knn": {},
    "lda": {},
    "qda": {},
    "logistic_regression": {},
    "svm": {
      "kernel": "rbf"
    },
    "naive": {}
  },
  "perfusion_maps": {
    "distance_map": "_distance_map.nii.gz",
    "distance_map_depth": {
      "suffix": "_distance_map_depth.nii.gz",
      "kwargs": [
        2
      ]
    },
    "ttp": "_ttp_map.nii.gz",
    "cbv": "_cbv_map.nii.gz",
    "cbf": "_cbf_map.nii.gz",
    "mtt": "_mtt_map.nii.gz"
 },
  "feature_selection": "SFFS",
  "n_features": 30,
  "n_folds": 5,
  "random_seed": 12345,
  "feature_aggregator": "SD",
  "k_ensemble": [1,5],
  "metric_best_model": "roc_auc",
  "reduction_best_model": "mean"
}