gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-18 21:38:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(Config): feature extractors are enabled one-by-one with a bool, added previous model to model.fit() (#77)

Browse Source 
* feat(Config): feature extractors are enabled one-by-one with a bool, added previous model to model.fit()

* fix(Sweep): removed unused `other_features` parameter that fails sweep

* feat(Config): using preset names for defining feature extractors again

* fix(Tests): fixed model stub classes
This commit is contained in:
Mark Aron Szulyovszky
2021-12-23 10:35:20 +01:00
committed by GitHub
parent 6ae8acf70e
commit b6cd6b14fe
14 changed files with 78 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files
feature_extractors/feature_extractor_presets.py
+42 -17
View File
@@ -1,24 +1,49 @@
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
debug_future_lookahead = [('debug_future', feature_debug_future_lookahead, [1])]
__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])],
)
lags = [('lag', feature_lag, [1,2,3,4,5,6,7,8,9])]
presets = __presets | dict(
level_1 = __presets["mom"] + __presets["vol"],
level_2 = __presets["mom"] + __presets["vol"] + __presets["roc"] + __presets["rsi"] + __presets["stod"] + __presets["stok"],
)
only_mom = [('mom', feature_mom, [30])]
def preprocess_feature_extractors_config(data_dict: dict) -> dict:
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
date = [
('day_of_week', feature_day_of_week, [0]),
('day_of_month', feature_day_of_month, [0]),
('month', feature_month, [0])]
level1 = [
('mom', feature_mom, [10, 20, 30, 60, 90]),
('vol', feature_vol, [10, 20, 30, 60]),
]
# 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])
level2 = level1 + [
('roc', feature_ROC, [10, 30]),
('rsi', feature_RSI, [10, 30, 100]),
('stod', feature_STOD, [10, 30, 200]),
('stok', feature_STOK, [10, 30, 200]),
]
# 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)