gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-16 04:18:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Refactor(Training): new outcome types, representative pipeline steps, bet-sizing (#187)

Browse Source 
* refactor(Training): added InferenceResult & TrainedModel types

* refactor(Pipeline): introduced TrainingOutcome, BetSizingWithMetaOutcome, etc.

* fix(Pipeline): getting it to compile

* refactor(WalkForward): separate preprocessing step

* feat(Pipeline): separate out transformations processing step

* refactor(Pipeline): use the Directional model terminology, put bet_sizing into pipeline instead of hiding it in a step

* refactor(WalkForward): moved functions to separate folder

* fix(WalkForward): use sparse array to store models, process transformations in parallel (lot faster)

* fix(Tests): and evaluation

* fix(Tests): for realz

* fix(Inference): preloading everything now, renamed primary models to directional models

* fix(BetSizing): was running transformations on the wrong data, oops

* fix(BetSizing): concatenated on the wrong axis accidentally

* fix(Reporting): able to use the new Stats type

* fix(BetSizing): renamed int column names

* fix(Portfolio): name the column properly

* fix(Reporting): rename the correct Series, lol

* fix(Inference): walk_forwad_inference() can deal with models not being aligned with the starting index

* fix(WalkForward): accidentally using the wrong index

* fix(WalkForward): use the correct indicies to fetch last model/transformations

* fix(CI): changed the name of the results
This commit is contained in:
Mark Aron Szulyovszky
2022-01-29 06:41:40 +01:00
committed by GitHub
parent 42a1bc59cb
commit 3eb3ea94e3
42 changed files with 772 additions and 736 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config/presets.py
+17 -22
View File
@@ -6,13 +6,13 @@ def get_dev_config() -> RawConfig:
classification_models = ["LogisticRegression_two_class"]
return RawConfig(
primary_models_meta_labeling = False,
directional_models_meta = False,
dimensionality_reduction = False,
n_features_to_select = 30,
expanding_window_base = False,
expanding_window_meta_labeling = False,
expanding_window_meta = False,
sliding_window_size_base = 380,
sliding_window_size_meta_labeling = 1,
sliding_window_size_meta = 1,
retrain_every = 20,
scaler = 'minmax', # 'normalize' 'minmax' 'standardize'
@@ -25,9 +25,8 @@ def get_dev_config() -> RawConfig:
other_features = ['single_mom'],
exogenous_features = ['z_score'],
primary_models = classification_models,
meta_labeling_models = [],
ensemble_model = None,
directional_models = classification_models,
meta_models = [],
event_filter = 'none',
labeling = 'two_class'
@@ -38,17 +37,16 @@ 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_labeling_models = ['LogisticRegression_two_class', 'LGBM']
ensemble_model = 'Average'
meta_models = ['LogisticRegression_two_class', 'LGBM']
return RawConfig(
primary_models_meta_labeling = True,
directional_models_meta = True,
dimensionality_reduction = False,
n_features_to_select = 30,
expanding_window_base = False,
expanding_window_meta_labeling = True,
expanding_window_meta = True,
sliding_window_size_base = 380,
sliding_window_size_meta_labeling = 240,
sliding_window_size_meta = 240,
retrain_every = 10,
scaler = 'minmax', # 'normalize' 'minmax' 'standardize'
@@ -61,9 +59,8 @@ def get_default_ensemble_config() -> RawConfig:
other_features = ['level_2', 'lags_up_to_5'],
exogenous_features = ['z_score'],
primary_models = classification_models,
meta_labeling_models = meta_labeling_models,
ensemble_model = ensemble_model,
directional_models = classification_models,
meta_models = meta_models,
event_filter = 'cusum_vol',
labeling = 'two_class'
@@ -75,17 +72,16 @@ def get_lightweight_ensemble_config() -> RawConfig:
regression_models = ["Lasso", "KNN"]
classification_models = ['LogisticRegression_two_class', 'SVC']
meta_labeling_models = ['LogisticRegression_two_class', 'LGBM']
ensemble_model = 'Average'
meta_models = ['LogisticRegression_two_class', 'LGBM']
return RawConfig(
primary_models_meta_labeling = True,
directional_models_meta = True,
dimensionality_reduction = True,
n_features_to_select = 30,
expanding_window_base = False,
expanding_window_meta_labeling = True,
expanding_window_meta = True,
sliding_window_size_base = 380,
sliding_window_size_meta_labeling = 240,
sliding_window_size_meta = 240,
retrain_every = 40,
scaler = 'minmax', # 'normalize' 'minmax' 'standardize'
@@ -98,9 +94,8 @@ def get_lightweight_ensemble_config() -> RawConfig:
other_features = ['level_2'],
exogenous_features = ['z_score'],
primary_models = classification_models,
meta_labeling_models = meta_labeling_models,
ensemble_model = ensemble_model,
directional_models = classification_models,
meta_models = meta_models,
event_filter = 'none',
labeling = 'two_class'