mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 03:08:01 +00:00
Mark Aron Szulyovszky
1cd0119589
* fix(FeatureExtractor): apply log to transform some series to normality * feat(DataLoader): add ability of not returning returns when they're not needed (exogenous data), applied log to certain features * feat(FeatureExtractors): added standard scaling for exogenous data * feat(FeatureSelection): scale data with the passed in scaler before doing feature-selection * fix(Config): sweep config * feat(Models): output probability, store it * feat(Core): added caching to select_features() and load_data() * fix(Dependencies): added diskcache * fix(Training): error when creating results DF * feat(Models): added xgboost, fixed tests * refactor(Cache): moved hashing to a separate function, created wrapper functions to separate business logic and caching * fix(Tests): new syntax * fix(Model): XGboost can't handle -1 class, so we'll use the deprecated label_encoder fornow * fix(Model): XGBoost config * feat(Cache): add run_clear_cache script * fix(Pipeline) accidentally re-instatiating all_predictions for each asset
25 lines
1.1 KiB
Python
25 lines
1.1 KiB
Python
|
|
from utils.types import DataCollection
|
|
|
|
def hash_data_config(data_config: dict) -> str:
|
|
|
|
def hash_data_collection(data_collection: DataCollection) -> str: return ''.join([a[0] + a[1] for a in data_collection])
|
|
def hash_feature_extractors(feature_extractos) -> str: return ''.join([f[0] for f in feature_extractos])
|
|
def to_str(x): return ''.join([str(i) for i in x])
|
|
return '_'.join(to_str([
|
|
hash_data_collection(data_config['assets']),
|
|
hash_data_collection(data_config['other_assets']),
|
|
hash_data_collection(data_config['exogenous_data']),
|
|
data_config['target_asset'][0] + data_config['target_asset'][1],
|
|
data_config['load_non_target_asset'],
|
|
data_config['log_returns'],
|
|
data_config['forecasting_horizon'],
|
|
hash_feature_extractors(data_config['own_features']),
|
|
hash_feature_extractors(data_config['other_features']),
|
|
hash_feature_extractors(data_config['exogenous_features']),
|
|
data_config['index_column'],
|
|
data_config['method'],
|
|
data_config['no_of_classes'],
|
|
data_config['narrow_format']
|
|
]))
|