kg-idg.yaml

name: kg-idg
description: kg-idg-xxxxx
output_directory: output_data
graph_data:
  graph:
    node_path: ./merged-kg_nodes.tsv
    edge_path: ./merged-kg_edges.tsv
    directed: false
    verbose: true
    nodes_column: id
    node_types_column: category
    default_node_type: biolink:NamedThing
    sources_column: subject
    destinations_column: object
    default_edge_type: biolink:related_to
  pos_validation:
    edge_path: ./merged-kg_edges.tsv
  neg_training:
    edge_path: ./neg_train_edges.tsv
  neg_validation:
    edge_path: ./neg_valid_edges.tsv
embeddings:
  embedding_file_name: test_embeddings_test_yaml.tsv
  embedding_history_file_name: embedding_history.json
  node_embedding_params:
    node_embedding_method_name: SkipGram
    walk_length: 10
    batch_size: 512
    window_size: 3
    return_weight: 1.0
    explore_weight: 1.0
    iterations: 1
classifier:
  edge_method: Average
  classifiers:
  - type: neural network
    model:
      outfile: model_mlp_test_yaml.h5
      classifier_history_file_name: mlp_classifier_history.json
      type: tensorflow.keras.models.Sequential
      layers:
      - type: tensorflow.keras.layers.Input
        parameters:
          shape: 100
      - type: tensorflow.keras.layers.Dense
        parameters:
          units: 128
          activation: relu
      - type: tensorflow.keras.layers.Dense
        parameters:
          units: 32
          activation: relu
      - type: tensorflow.keras.layers.Dropout
        parameters:
          rate: 0.5
      - type: tensorflow.keras.layers.Dense
        parameters:
          units: 16
          activation: relu
      - type: tensorflow.keras.layers.Dense
        parameters:
          units: 1
          activation: sigmoid
    model_compile:
      loss: binary_crossentropy
      optimizer: nadam
      metrics:
      - type: tensorflow.keras.metrics.AUC
        parameters:
          curve: PR
          name: auprc
      - type: tensorflow.keras.metrics.AUC
        parameters:
          curve: ROC
          name: auroc
      - type: tensorflow.keras.metrics.Recall
        parameters:
          name: Recall
      - type: tensorflow.keras.metrics.Precision
        parameters:
          name: Precision
      - type: accuracy
    model_fit:
      parameters:
        batch_size: 4096
        epochs: 5
        callbacks:
        - type: tensorflow.keras.callbacks.EarlyStopping
          parameters:
            monitor: val_loss
            patience: 5
            min_delta: 0.001
        - type: tensorflow.keras.callbacks.ReduceLROnPlateau
  - type: Decision Tree
    model:
      outfile: model_decision_tree_test_yaml.h5
      type: sklearn.tree.DecisionTreeClassifier
      parameters:
        max_depth: 30
        random_state: 42
  - type: Random Forest
    model:
      outfile: model_random_forest_test_yaml.h5
      type: sklearn.ensemble.RandomForestClassifier
      parameters:
        n_estimators: 500
        max_depth: 30
        n_jobs: 8
        random_state: 42
  - type: Logistic Regression
    model:
      outfile: model_lr_test_yaml.h5
      type: sklearn.linear_model.LogisticRegression
      parameters:
        random_state: 42
        max_iter: 1000