data:
  annotations_path: data/annotations/export.json
  enriched_path: data/enriched/features.csv
  labeled_path: data/labeled/dataset.csv
  raw_path: data/raw/OHLCV.csv
stages:
  annotation_ingestion:
    context_padding: 20
    enabled: true
    label_encoding: window
    merge_strategy: human_priority
    min_confidence: 1
    programmatic_labels:
      enabled: true
      talib_patterns:
      - CDLENGULFING
      - CDLHAMMER
      - CDLINVERTEDHAMMER
      - CDLSHOOTINGSTAR
      - CDLDOJI
      - CDLDOJISTAR
      - CDLMORNINGSTAR
      - CDLEVENINGSTAR
      - CDLHARAMI
      - CDLPIERCING
      - CDLDARKCLOUDCOVER
      - CDL3WHITESOLDIERS
      - CDL3BLACKCROWS
    window_size: 30
  feature_engineering:
    candle_features: true
    custom_features: []
    enabled: true
    talib_indicators:
    - name: RSI
      params:
        timeperiod: 14
    - name: EMA
      params:
        timeperiod: 20
    - name: EMA
      params:
        timeperiod: 50
    - name: MACD
      params:
        fastperiod: 12
        signalperiod: 9
        slowperiod: 26
    - name: BBANDS
      params:
        nbdevdn: 2
        nbdevup: 2
        timeperiod: 20
    - name: ATR
      params:
        timeperiod: 14
    - name: ADX
      params:
        timeperiod: 14
    - name: CCI
      params:
        timeperiod: 14
    - name: MFI
      params:
        timeperiod: 14
    - name: STOCH
      params:
        fastk_period: 14
        slowd_period: 3
        slowk_period: 3
  inference:
    batch_size: 1000
    enabled: true
    local_model_path: models/best_model.pkl
    mlflow_model_name: candlestick_pattern_v1
    mlflow_model_stage: Production
    model_source: local
    use_training_config: true
  training:
    class_weights: balanced
    enabled: true
    hyperparameters:
      max_depth: 15
      min_samples_leaf: 2
      min_samples_split: 5
      n_estimators: 200
      n_jobs: -1
      random_state: 42
    mlflow:
      experiment_name: candlestick_patterns
      log_artifacts: true
      register_model: false
      tracking_uri: file:./mlruns
    model_type: random_forest
    split_method: temporal
    test_split: 0.2
    validation_split: 0.1