mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-02 13:47:47 +00:00
Mark Aron Szulyovszky
cc70d3f907
* feat(Selection): added prototype feature selection python script * feat(Utils): added some helpers for the future from Advances in Financial ML book * feat(Selection): added RFECV * feat(Selection): added configurable feature selection step into pipeline * feat(Config): added level_1 & level_2 default config, PCA before feature selection process starts * feat(Selection): added backup feature selector models if current one can't output feature importance, removed unnecessary array for level-2 models * fix(Training): deal with zero first value coming out of static models * feat(Sweep): added feature selection sweep * fix(Sweep): config problem * fix(Sweep): config * chore(Utils): removed unnecessary purged k-fold crossval class * feat(Config): added dimensionality_reduction as a separate flag * fix(Sweep): config updated * fix(Sweep): sweep name * chore(Config): updated level_2 config to the best performing configuation
48 lines
1.1 KiB
YAML
48 lines
1.1 KiB
YAML
program: run_sweep.py
|
|
method: bayes
|
|
project: price-forecasting
|
|
name: Feature selection
|
|
metric:
|
|
goal: maximize
|
|
name: sharpe
|
|
parameters:
|
|
path :
|
|
value: 'data/'
|
|
expanding_window:
|
|
value: True
|
|
sliding_window_size:
|
|
value: 380
|
|
feature_selection:
|
|
values: [True, False]
|
|
distribution: categorical
|
|
dimensionality_reduction:
|
|
values: [True, False]
|
|
distribution: categorical
|
|
retrain_every:
|
|
value: 20
|
|
scaler:
|
|
value: 'minmax'
|
|
include_original_data_in_ensemble:
|
|
value: False
|
|
method:
|
|
value: 'classification'
|
|
no_of_classes:
|
|
values: ['two', 'three-balanced', 'three-imbalanced']
|
|
distribution: categorical
|
|
forecasting_horizon:
|
|
value: 1
|
|
load_other_assets:
|
|
value: True
|
|
log_returns:
|
|
value: True
|
|
index_column:
|
|
value: 'int'
|
|
level_1_models:
|
|
value: ["LR", "LDA", "KNN", "CART", "NB", "AB", "RF", "StaticMom"]
|
|
level_2_model:
|
|
value: "Ensemble_Average"
|
|
own_features:
|
|
value: ['date_days', 'level_2', 'lags_up_to_5']
|
|
other_features:
|
|
value: ['level_2', 'lags_up_to_5']
|