gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-20 06:18:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(Data): create DataSource, DataCollection, added hourly crypto data (#96)

Browse Source 
* feat(Data): create DataSource, DataCollection, added hourly crypto data

* fix(Data): hourly data format, loading & config
This commit is contained in:
Mark Aron Szulyovszky
2021-12-31 19:04:27 +01:00
committed by GitHub
parent f762ceed2a
commit 442915f847
59 changed files with 276175 additions and 43473 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config.py
+52 -12
View File
@@ -1,10 +1,7 @@
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_level_1_config() -> tuple[dict, dict, dict]:
def get_default_level_1_daily_config() -> tuple[dict, dict, dict]:
training_config = dict(
dimensionality_reduction = True,
@@ -20,9 +17,10 @@ def get_default_level_1_config() -> tuple[dict, dict, dict]:
)
data_config = dict(
path='data/',
all_assets = get_crypto_assets('data/'),
load_other_assets= True,
assets = ['hourly_crypto'],
other_assets = [],
# exogenous_data = [],
load_non_target_asset= True,
log_returns= True,
forecasting_horizon = 1,
own_features = ['level_2', 'date_days'],
@@ -43,8 +41,49 @@ def get_default_level_1_config() -> tuple[dict, dict, dict]:
return model_config, training_config, data_config
def get_default_level_2_hourly_config() -> tuple[dict, dict, dict]:
training_config = dict(
dimensionality_reduction = True,
feature_selection = True,
n_features_to_select = 30,
expanding_window_level1 = True,
expanding_window_level2 = False,
sliding_window_size_level1 = 2480,
sliding_window_size_level2 = 1,
retrain_every = 100,
scaler = 'minmax', # 'normalize' 'minmax' 'standardize' 'none'
include_original_data_in_ensemble = False,
)
def get_default_level_2_config() -> tuple[dict, dict, dict]:
data_config = dict(
assets = ['hourly_crypto'],
other_assets = [],
# exogenous_data = [],
load_non_target_asset= True,
log_returns= True,
forecasting_horizon = 1,
own_features = ['level_2', 'date_days', 'lags_up_to_5'],
other_features = ['level_2'],
index_column= 'int',
method= 'classification',
no_of_classes= 'three-balanced'
)
regression_models = ["Lasso", "KNN", "RF"]
regression_ensemble_model = 'KNN'
classification_models = ["LDA", "KNN", "CART", "RF", "StaticMom"]
classification_ensemble_model = 'Ensemble_Average'
model_config = dict(
level_1_models = regression_models if data_config['method'] == 'regression' else classification_models,
level_2_model = regression_ensemble_model if data_config['method'] == 'regression' else classification_ensemble_model
)
return model_config, training_config, data_config
def get_default_level_2_daily_config() -> tuple[dict, dict, dict]:
training_config = dict(
dimensionality_reduction = True,
@@ -60,9 +99,10 @@ def get_default_level_2_config() -> tuple[dict, dict, dict]:
)
data_config = dict(
path='data/',
all_assets = get_crypto_assets('data/'),
load_other_assets= True,
assets = ['daily_crypto'],
other_assets = ['daily_etf'],
# exogenous_data = [],
load_non_target_asset= True,
log_returns= True,
forecasting_horizon = 1,
own_features = ['level_2', 'date_days', 'fracdiff'],
@@ -74,7 +114,7 @@ def get_default_level_2_config() -> tuple[dict, dict, dict]:
regression_models = ["Lasso", "KNN", "RF"]
regression_ensemble_model = 'KNN'
classification_models = ["LR", "LDA", "KNN", "CART", "RF", "StaticMom"]
classification_models = ["LDA", "KNN", "CART", "RF", "StaticMom"]
classification_ensemble_model = 'Ensemble_Average'
model_config = dict(