mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-27 18:57:55 +00:00
Daniel Szemerey
fc4e59a7d2
* feat: Added ensemble models to sweep and configured naming convention. * fix: Default value was misconfigured. * feat(Sweep): separated level-1 and level-2 sweep configs, skip assets with too few samples to train on, simplified model mapping * fix(Sweep): syntax error * chore(Sweep): set sweep names accordingly * fix(Sweep): set sliding window * fix(Sweep): adjusted sweep config * fix(Sweep): removed invalid feature extractor preset Co-authored-by: Mark Aron Szulyovszky <mark.szulyovszky@gmail.com>
57 lines
2.3 KiB
Python
57 lines
2.3 KiB
Python
from collections import defaultdict
|
|
from utils.load_data import get_crypto_assets
|
|
from feature_extractors.feature_extractor_presets import presets
|
|
from models.model_map import model_names_classification, model_names_regression
|
|
|
|
def get_default_config() -> tuple[dict, dict, dict]:
|
|
|
|
training_config = dict(
|
|
expanding_window = False,
|
|
sliding_window_size = 220,
|
|
retrain_every = 20,
|
|
scaler = 'minmax', # 'normalize' 'minmax' 'standardize' 'none'
|
|
include_original_data_in_ensemble = True,
|
|
)
|
|
|
|
data_config = dict(
|
|
path='data/',
|
|
all_assets = get_crypto_assets('data/'),
|
|
load_other_assets= False,
|
|
log_returns= True,
|
|
forecasting_horizon = 1,
|
|
own_features = ['level_1', 'date_days'],
|
|
other_features = [],
|
|
index_column= 'int',
|
|
method= 'classification',
|
|
no_of_classes= 'two'
|
|
)
|
|
|
|
regression_models = ["Lasso", "KNN", "RF"]
|
|
regression_ensemble_models = ['KNN']
|
|
classification_models = ["LR", "LDA", "KNN", "CART", "RF", "StaticMom"]
|
|
classification_ensemble_models = ['LR']
|
|
|
|
model_config = dict(
|
|
level_1_models = regression_models if data_config['method'] == 'regression' else classification_models,
|
|
level_2_models = regression_ensemble_models if data_config['method'] == 'regression' else classification_ensemble_models
|
|
)
|
|
|
|
return model_config, training_config, data_config
|
|
|
|
|
|
def validate_config(model_config:dict, training_config:dict, data_config:dict):
|
|
# We need to make sure there's only one output from the pipeline
|
|
# We're not prepared for more than 1 level-2 models at the moment
|
|
assert len(model_config["level_2_models"]) <= 1
|
|
# If level-2 model is there, we need more than one level-1 models to train
|
|
if len(model_config["level_2_models"]) == 1: assert len(model_config["level_1_models"]) > 0
|
|
# If there's no level-2 model, we need to have only one level-1 model
|
|
if len(model_config["level_2_models"]) == 0: assert len(model_config["level_1_models"]) == 1
|
|
|
|
def get_model_name(model_config:dict) -> str:
|
|
if len(model_config["level_2_models"]) == 1:
|
|
return model_config["level_2_models"][0][0]
|
|
elif len(model_config["level_1_models"]) == 1:
|
|
return model_config["level_1_models"][0][0]
|
|
else:
|
|
raise Exception("No model name found") |