mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-27 18:57:55 +00:00
Mark Aron Szulyovszky
f762ceed2a
* feat(FeatureExtraction): added fractionally differentiated returns to remove lagged returns * fix(Sweep): config * fix(Sweep): name * fix(Sweep): grid * feat(Config): separated sliding_window_size_level1 & sliding_window_size_level2 * feat(Dependencies): added ray, now using it to parallel process feature extraction * fix(Dependencies): added pip explicitly * fix(Dependencies): removed ray from root * fix(Models): average model was probably not taking the right timestamp to average * feat(Config): separated expanding_window_level1 & expanding_window_level2 * fix(Config): set n_features_to_select to the optimal 30
52 lines
2.5 KiB
Python
52 lines
2.5 KiB
Python
from feature_extractors.feature_extractors import feature_lag, feature_mom, feature_ROC, feature_RSI, feature_STOD, feature_STOK, feature_vol, feature_day_of_month, feature_day_of_week, feature_month, feature_debug_future_lookahead
|
|
from utils.typing import FeatureExtractorConfig
|
|
from utils.helpers import flatten
|
|
from feature_extractors.fractional_differentiation import feature_fractional_differentiation
|
|
|
|
__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])],
|
|
)
|
|
|
|
presets = __presets | dict(
|
|
level_1 = __presets["mom"] + __presets["vol"],
|
|
level_2 = __presets["mom"] + __presets["vol"] + __presets["roc"] + __presets["rsi"] + __presets["stod"] + __presets["stok"],
|
|
)
|
|
|
|
def preprocess_feature_extractors_config(data_dict: dict) -> dict:
|
|
data_dict = data_dict.copy()
|
|
keys = ['own_features', 'other_features']
|
|
for key in keys:
|
|
preset_names = data_dict[key]
|
|
data_dict[key] = flatten([presets[preset_name] for preset_name in preset_names])
|
|
return data_dict
|
|
|
|
|
|
# Use this if ever we want to create an independent boolean for each featureextractor
|
|
# def preprocess_feature_extractors_config(data_dict: dict) -> dict:
|
|
# prefixes = ['own_features', 'other_features']
|
|
# features_dict = dict()
|
|
# for prefix in prefixes:
|
|
# features_to_include = [key.replace(prefix + "_", "") for key, value in data_dict.items() if key.startswith(prefix) and value == True]
|
|
# features_dict[prefix] = flatten([presets[feature_name] for feature_name in features_to_include])
|
|
|
|
# data_dict = {k: v for k, v in data_dict.items() if not (k.startswith(prefixes[0]) or k.startswith(prefixes[1]))}
|
|
# return (data_dict | features_dict) |