gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-14 03:18:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(Project): use SKLearn models directly, removed custom ensembling, use 5 minute data, batch inference, numba cusum filter (#192)

Browse Source 
* feat(Project): use 5 minute data, running training in parallel, sped up cusum filter by 10x with numba

* fix(WalkForward): inference mini-batch parallelization

* fix(WalkForward): don't use the parallel version of any of the functions

* feat(CI): download the data required

* fix(Project): 5min_crypto folder added

* fix(Evaluate): make sure we have numerical stability in returns

* feat(Models): use SKLearn models directly to enable composability

* feat(Inference): batched inference now working, added forecasting_horizon

* fix(Inference): works again

* fix(Inference)

* chore(Models): remove unused Ensemble model

* fix(Labeller): don't just forward shift returns, also take the sum of the data happened until then

* Update test.yml
This commit is contained in:
Mark Aron Szulyovszky
2022-02-17 16:36:35 +01:00
committed by GitHub
parent 5c94af8b01
commit 9d47ee942d
52 changed files with 470 additions and 628 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config/presets.py
+20 -20
View File
@@ -2,7 +2,6 @@ from .types import RawConfig, Config
def get_dev_config() -> RawConfig:
regression_models = ["Lasso"]
classification_models = ["LogisticRegression_two_class"]
return RawConfig(
@@ -29,13 +28,13 @@ def get_dev_config() -> RawConfig:
meta_models = [],
event_filter = 'none',
labeling = 'two_class'
labeling = 'two_class',
forecasting_horizon = 100,
)
def get_default_ensemble_config() -> RawConfig:
regression_models = ["Lasso", "KNN", "RFR"]
classification_models = ["LogisticRegression_two_class", "LDA", "NB", "RFC", "XGB_two_class", "LGBM", "StaticMom"]
meta_models = ['LogisticRegression_two_class', 'LGBM']
@@ -63,42 +62,43 @@ def get_default_ensemble_config() -> RawConfig:
meta_models = meta_models,
event_filter = 'cusum_vol',
labeling = 'two_class'
labeling = 'two_class',
forecasting_horizon = 100,
)
def get_lightweight_ensemble_config() -> RawConfig:
regression_models = ["Lasso", "KNN"]
classification_models = ['LogisticRegression_two_class', 'SVC']
classification_models = ['LogisticRegression_two_class', 'LGBM']
meta_models = ['LogisticRegression_two_class', 'LGBM']
return RawConfig(
directional_models_meta = True,
dimensionality_reduction = True,
n_features_to_select = 30,
expanding_window_base = False,
expanding_window_base = True,
expanding_window_meta = True,
sliding_window_size_base = 380,
sliding_window_size_meta = 240,
retrain_every = 40,
sliding_window_size_base = 3800,
sliding_window_size_meta = 2400,
retrain_every = 1000,
scaler = 'minmax', # 'normalize' 'minmax' 'standardize'
assets = ['daily_crypto_lightweight'],
target_asset = 'BCH_USD',
other_assets = ['daily_etf'],
exogenous_data = ['daily_glassnode'],
load_non_target_asset= True,
own_features = ['level_2' ],
other_features = ['level_2'],
exogenous_features = ['z_score'],
assets = ['fivemin_crypto'],
target_asset = 'BTC_USD',
other_assets = [],
exogenous_data = [],
load_non_target_asset= False,
own_features = ['level_1'],
other_features = [],
exogenous_features = [],
directional_models = classification_models,
meta_models = meta_models,
event_filter = 'none',
labeling = 'two_class'
event_filter = 'cusum_fixed',
labeling = 'two_class',
forecasting_horizon = 50,
)