mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-05 15:17:46 +00:00
Mark Aron Szulyovszky
b1c04afb13
* refactor(Naming): use `primary_models` & `meta_labeling_models` * refactor(Naming): using primary * meta_labeling across config and in pipeline * feat(Pipeline): added back Ensemble models * fix(Pipeline): compiler error * fix(Config): typo * chore(Pipeline): removed unused averaging step * revert the changes in discretizing * chore(Pipeline): remove sharpe improvement logging * fix(Pipeline): ensemble predictions should be a pd.Series instead of a DataFrame * fix(Pipeline): discard unnecessary ensemble_probabilities * fix(Pipeline): fixes regarding various meta-labeling ensemble bugs * fix(Reporting): use the new naming convention * fix(Reporting): use the right variable * feat(Sweep): new sweep for ensemble models * fix(Sweep): config reference * fix(Config): simplified dev config * fix(Models): use the faster LR model * fix(Models): use LGBM in the meta-labeling model for speed * fix(Selection): always use the first model for feature selection, commented out caching from select_features() as it's close to redundant in terms of speed
63 lines
1.7 KiB
YAML
63 lines
1.7 KiB
YAML
program: run_sweep.py
|
|
method: bayes
|
|
project: price-forecasting
|
|
name: Level-2 models
|
|
metric:
|
|
goal: maximize
|
|
name: sharpe
|
|
parameters:
|
|
primary_models_meta_labeling:
|
|
value: True
|
|
assets:
|
|
value: ['daily_crypto']
|
|
other_assets:
|
|
value: ['daily_etf']
|
|
exogenous_data:
|
|
value: ['daily_glassnode']
|
|
expanding_window_primary:
|
|
values: [True, False]
|
|
distribution: categorical
|
|
expanding_window_meta_labeling:
|
|
values: [True, False]
|
|
distribution: categorical
|
|
n_features_to_select:
|
|
values: [10, 20, 30]
|
|
distribution: categorical
|
|
dimensionality_reduction:
|
|
value: True
|
|
sliding_window_size_primary:
|
|
values: [180, 280, 380]
|
|
distribution: categorical
|
|
sliding_window_size_meta_labeling:
|
|
values: [180, 280, 380]
|
|
distribution: categorical
|
|
retrain_every:
|
|
values: [10, 20, 30]
|
|
distribution: categorical
|
|
scaler:
|
|
value: 'minmax'
|
|
method:
|
|
value: 'classification'
|
|
no_of_classes:
|
|
values: ['two', 'three-balanced', 'three-imbalanced']
|
|
distribution: categorical
|
|
forecasting_horizon:
|
|
value: 1
|
|
load_non_target_asset:
|
|
values: [True, False]
|
|
distribution: categorical
|
|
log_returns:
|
|
value: True
|
|
index_column:
|
|
value: 'int'
|
|
primary_models:
|
|
value: ["LR_two_class", "LDA", "KNN", "CART", "NB", "AB", "RF", "StaticMom"]
|
|
meta_labeling_models:
|
|
values: ["LR_two_class", "LDA", "KNN", "CART", "NB", "AB", "RF"]
|
|
distribution: categorical
|
|
own_features:
|
|
values: [['single_mom', 'date_days'], [], ['level_1', 'date_days'], ['date_days', 'level_2']]
|
|
distribution: categorical
|
|
other_features:
|
|
values: [[], ['level_1']]
|
|
distribution: categorical |