mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-04 14:47:49 +00:00
Mark Aron Szulyovszky
1cd0119589
* fix(FeatureExtractor): apply log to transform some series to normality * feat(DataLoader): add ability of not returning returns when they're not needed (exogenous data), applied log to certain features * feat(FeatureExtractors): added standard scaling for exogenous data * feat(FeatureSelection): scale data with the passed in scaler before doing feature-selection * fix(Config): sweep config * feat(Models): output probability, store it * feat(Core): added caching to select_features() and load_data() * fix(Dependencies): added diskcache * fix(Training): error when creating results DF * feat(Models): added xgboost, fixed tests * refactor(Cache): moved hashing to a separate function, created wrapper functions to separate business logic and caching * fix(Tests): new syntax * fix(Model): XGboost can't handle -1 class, so we'll use the deprecated label_encoder fornow * fix(Model): XGBoost config * feat(Cache): add run_clear_cache script * fix(Pipeline) accidentally re-instatiating all_predictions for each asset
61 lines
1.5 KiB
YAML
61 lines
1.5 KiB
YAML
program: run_sweep.py
|
|
method: grid
|
|
project: price-forecasting
|
|
name: Exogenous data / data transformation
|
|
metric:
|
|
goal: maximize
|
|
name: sharpe
|
|
parameters:
|
|
assets:
|
|
value: ['daily_crypto']
|
|
other_assets:
|
|
value: ['daily_etf']
|
|
exogenous_data:
|
|
values: [['daily_glassnode'], []]
|
|
distribution: categorical
|
|
expanding_window_level1:
|
|
value: True
|
|
expanding_window_level2:
|
|
value: False
|
|
sliding_window_size_level1:
|
|
value: 380
|
|
sliding_window_size_level2:
|
|
value: 1
|
|
feature_selection:
|
|
value: True
|
|
n_features_to_select:
|
|
value: 30
|
|
dimensionality_reduction:
|
|
value: True
|
|
retrain_every:
|
|
value: 20
|
|
scaler:
|
|
value: 'minmax'
|
|
include_original_data_in_ensemble:
|
|
value: False
|
|
method:
|
|
value: 'classification'
|
|
no_of_classes:
|
|
value: 'three-balanced'
|
|
forecasting_horizon:
|
|
value: 1
|
|
load_non_target_asset:
|
|
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:
|
|
values: [['date_days', 'level_2', 'lags_up_to_5'], ['date_days', 'level_2', 'fracdiff']]
|
|
distribution: categorical
|
|
other_features:
|
|
values: [['level_2', 'lags_up_to_5'], ['level_2', 'fracdiff']]
|
|
distribution: categorical
|
|
exogenous_features:
|
|
values: [[], ['fracdiff'], ['standard_scaling']]
|
|
distribution: categorical
|