save_name: "xgboost_OS"

target: "OS"

#### Data paths + pre-processing for each modality (e.g. simple imputation)

clinical_data:

  clinical_file: "data/clinicals.csv"

  imputation:

    numericals: [1, 3, 4, 13, 14, 15, 16, 17, 18, 19, -4]

    categoricals: [20, -5, -3]

radiomics_data:

  radiomics_file: "data/radiomics.csv"

  preprocessing:

    f_log_transform: ['TMTV', 'T_TMTV', 'N1_TMTV', 'N2_TMTV', 'N3_TMTV', 'M1a_TMTV', 'M1bc_TMTV']

  imputation:

    numericals: [2]

    categoricals: null

pathomics_data:

  pathomics_file: "data/pathomics.csv"

  imputation:

    numericals: [ 27, 28, 29, 31, 33, 35, 38, 40, 41, 43, 44, 45, 47, 48, 49, 52, 53, 54, 55, 56, 57, 58, 59, 60,

                  61, 62, 63, 64, 65, 66, 67, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130,

                  131, 132, 133 ]

    categoricals: null

RNA_data:

  RNA_file: "data/omics.csv"

  imputation:

    numericals: [32]

    categoricals: null

####  Define classifier + hyperparameters

classifier:

#  type: "LR"

#  args:

#    penalty: "elasticnet"

#    max_iter: 2500

#    solver: "saga"

#    class_weight: "balanced"

#    C: 0.1

#    l1_ratio: 0.5

  type: "xgboost"

  args:

    n_jobs: 1

  optim_params: # Uncomment and modify for parameter optimization

#     LR__l1_ratio: [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]

#     LR__C: [0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1, 5, 10]

#

#     xgboost__max_depth: [3, 6, 9, 12]

#     xgboost__learning_rate: [0.001, 0.01, 0.05, 0.1, 0.2, 0.3]

#     xgboost__subsample: [0.5, 0.6, 0.7, 0.8, 0.9, 1.]

#     xgboost__colsample_bytree: [0.5, 0.6, 0.7, 0.8, 0.9, 1.]

#     xgboost__n_estimators: [100, 200, 300, 400, 500]

#  n_iter_randomcv: 80 # number of iterations/samples for randomsearch

#### Define latefusion parameters  (see multipit.multi_model.latefusion)

latefusion:

  n_repeats: 100 # number of repeats for 10-fold cross-validation

  seed: 3 # random seed

  args:

    sup_weights: False # learn weights with inner cross-validation for weighted late fusion

    calibration: 'late' # if 'late' calibrate the fused model, if 'early' calibrate each unimodal model before fusion

    n_jobs: 1

    # tuning: "gridsearch" # uncomment for parameter optimization

    # score: "roc_auc" # uncomment for parameter optimization

##### Additionnal parameters

parallelization: # number of jobs for dealing with several repeats in parallel (conflict with n_jobs of latefusion)

  n_jobs_repeats: 1

collect_thresholds: False  # collect threshold that optimizes log-rank test on the training set

permutation_test: False # perform permutation test

n_permutations: 1