mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-04 06:37:45 +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
36 lines
1.8 KiB
Python
36 lines
1.8 KiB
Python
from feature_extractors.feature_extractors import feature_lag, feature_mom, feature_ROC, feature_RSI, feature_STOD, feature_STOK, feature_standard_scaling, feature_vol, feature_day_of_month, feature_day_of_week, feature_month, feature_debug_future_lookahead
|
|
from utils.types import FeatureExtractorConfig
|
|
from utils.helpers import flatten
|
|
from feature_extractors.fractional_differentiation import feature_fractional_differentiation, feature_fractional_differentiation_log
|
|
|
|
__presets = dict(
|
|
debug_future_lookahead = [('debug_future', feature_debug_future_lookahead, [1])],
|
|
single_mom = [('mom', feature_mom, [30])],
|
|
single_vol = [('vol', feature_vol, [30])],
|
|
mom = [('mom', feature_mom, [10, 20, 30, 60, 90])],
|
|
vol = [('vol', feature_vol, [10, 20, 30, 60])],
|
|
lags_up_to_5 = [('lag', feature_lag, [1,2,3,4,5])],
|
|
lags_up_to_10 = [('lag', feature_lag, [1,2,3,4,5,6,7,8,9,10])],
|
|
date_all = [
|
|
('day_of_week', feature_day_of_week, [0]),
|
|
('day_of_month', feature_day_of_month, [0]),
|
|
('month', feature_month, [0])],
|
|
date_days = [
|
|
('day_of_week', feature_day_of_week, [0]),
|
|
('day_of_month', feature_day_of_month, [0]),
|
|
],
|
|
roc = [('roc', feature_ROC, [10, 30])],
|
|
rsi = [('rsi', feature_ROC, [10, 30, 100])],
|
|
stod = [('stod', feature_STOD, [10, 30, 200])],
|
|
stok = [('stok', feature_STOK, [10, 30, 200])],
|
|
fracdiff = [('fracdiff', feature_fractional_differentiation, [10, 30])],
|
|
fracdiff_log = [('fracdiff_log', feature_fractional_differentiation_log, [10, 30])],
|
|
standard_scaling = [('standard_scaling', feature_standard_scaling, [0])],
|
|
)
|
|
|
|
presets = __presets | dict(
|
|
level_1 = __presets["mom"] + __presets["vol"],
|
|
level_2 = __presets["mom"] + __presets["vol"] + __presets["roc"] + __presets["rsi"] + __presets["stod"] + __presets["stok"],
|
|
)
|
|
|