66 lines
1.8 KiB
Python
66 lines
1.8 KiB
Python
from dataclasses import dataclass, field
|
|
from typing import List, Optional
|
|
|
|
|
|
@dataclass
|
|
class DataConfig:
|
|
"""Configuration for data loading and basic filtering."""
|
|
csv_path: str
|
|
min_date: str = "2017-06-01"
|
|
max_date: Optional[str] = None
|
|
drop_volume_zero: bool = True
|
|
|
|
|
|
@dataclass
|
|
class FeatureConfig:
|
|
"""Configuration for feature engineering."""
|
|
ohlcv_cols: List[str] = field(default_factory=lambda: ["Open", "High", "Low", "Close", "Volume"])
|
|
lags: int = 3
|
|
window_sizes: List[int] = field(default_factory=lambda: [5, 15, 30])
|
|
|
|
|
|
@dataclass
|
|
class PreprocessConfig:
|
|
"""Configuration for preprocessing and NaN handling."""
|
|
impute_nans: bool = True
|
|
|
|
|
|
@dataclass
|
|
class PruningConfig:
|
|
"""Configuration for feature pruning and CV."""
|
|
do_walk_forward_cv: bool = True
|
|
n_splits: int = 5
|
|
auto_prune: bool = True
|
|
top_k: int = 150
|
|
known_low_features: List[str] = field(
|
|
default_factory=lambda: [
|
|
"supertrend_12_3.0",
|
|
"supertrend_10_1.0",
|
|
"supertrend_11_2.0",
|
|
"supertrend_trend_12_3.0",
|
|
"supertrend_trend_10_1.0",
|
|
"supertrend_trend_11_2.0",
|
|
"hour",
|
|
]
|
|
)
|
|
|
|
|
|
@dataclass
|
|
class OutputConfig:
|
|
"""Configuration for outputs and artifacts."""
|
|
charts_dir: str = "charts"
|
|
results_csv: str = "../data/cumulative_feature_results.csv"
|
|
model_output_path: str = "../data/xgboost_model_all_features.json"
|
|
|
|
|
|
@dataclass
|
|
class RunConfig:
|
|
"""Top-level configuration grouping for a pipeline run."""
|
|
data: DataConfig
|
|
features: FeatureConfig = field(default_factory=FeatureConfig)
|
|
preprocess: PreprocessConfig = field(default_factory=PreprocessConfig)
|
|
pruning: PruningConfig = field(default_factory=PruningConfig)
|
|
output: OutputConfig = field(default_factory=OutputConfig)
|
|
|
|
|