small_ole.yaml

dataset:
    # Type: String
    # Meaning: Name of the used dataset
    # Possible values: String ended with a ".csv" extension
    filename: small_ole.csv

model_details:
    # Type: String
    # Meaning: Objective of the model
    # Possible values: "MALICE", "CLASSIFICATION"
    objective: MALICE

    # Type: Boolean
    # Meaning: Activation status of the retraining
    # Possible values: "True", "False"
    retraining: False

# Type: Nested lists
# Meaning: Combination of extractors and their preprocessors
# Possible values: All implemented extractors and preprocessors
extractors_preprocessors:
    - GENERAL_OLE_DETAILS:
          - N_GRAMS
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - IDENTITY
          - N_GRAMS
          - K_BINS_DISCRETIZER
          - IDENTITY
    - OLE_MACROS:
          - N_GRAMS

dimensionality_reduction:
    # Type: String
    # Meaning: Dimensionality reduction algorithm
    # Possible values: All implemented algorithms
    algorithm: PCA

    # Type: Integer or float
    # Meaning: Number of components to return or included variation (PCA-only)
    # Possible values: Between 0 and the number of the extracted features
    components_count: 0.999999

machine_learning:
    # Type: String
    # Meaning: Machine learning algorithm
    # Possible values: All implemented algorithms
    algorithm: RANDOM_FOREST

    # Type: Float
    # Meaning: Ratio of samples used for training
    # Possible values: Between 0 and 1
    split_ratio: 0.8