gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-16 12:28:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(Project): removed regression method (we can still use regression models, but we'll need map them to classification later) (#182)

Browse Source 
* refactor(Project): removed regression method (we can still use regression models, but we'll need map them to classes later)

* fix(Training): removed mistakenly left in `method` parameter
This commit is contained in:
Mark Aron Szulyovszky
2022-01-23 17:15:08 +01:00
committed by GitHub
parent 516c8bcc87
commit 5c4a5b0cf1
12 changed files with 11 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config/config.py
+3 -6
View File
@@ -25,7 +25,6 @@ def get_dev_config() -> tuple[dict, dict, dict]:
other_features = ['single_mom'],
exogenous_features = ['z_score'],
index_column= 'int',
method= 'classification',
no_of_classes= 'two',
narrow_format = False,
)
@@ -34,7 +33,7 @@ def get_dev_config() -> tuple[dict, dict, dict]:
classification_models = ["LogisticRegression_two_class"]
model_config = dict(
primary_models = regression_models if data_config['method'] == 'regression' else classification_models,
primary_models = classification_models,
meta_labeling_models = [],
ensemble_model = None
)
@@ -69,7 +68,6 @@ def get_default_ensemble_config() -> tuple[dict, dict, dict]:
other_features = ['level_2', 'lags_up_to_5'],
exogenous_features = ['z_score'],
index_column= 'int',
method= 'classification',
no_of_classes= 'two',
narrow_format = False,
)
@@ -80,7 +78,7 @@ def get_default_ensemble_config() -> tuple[dict, dict, dict]:
ensemble_model = 'Average'
model_config = dict(
primary_models = regression_models if data_config['method'] == 'regression' else classification_models,
primary_models = classification_models,
meta_labeling_models = meta_labeling_models,
ensemble_model = ensemble_model
)
@@ -115,7 +113,6 @@ def get_lightweight_ensemble_config() -> tuple[dict, dict, dict]:
other_features = ['level_2'],
exogenous_features = ['z_score'],
index_column= 'int',
method= 'classification',
no_of_classes= 'two',
narrow_format = False,
)
@@ -126,7 +123,7 @@ def get_lightweight_ensemble_config() -> tuple[dict, dict, dict]:
ensemble_model = 'Average'
model_config = dict(
primary_models = regression_models if data_config['method'] == 'regression' else classification_models,
primary_models = classification_models,
meta_labeling_models = meta_labeling_models,
ensemble_model = ensemble_model
)
config/hashing.py
-1
View File
@@ -18,7 +18,6 @@ def hash_data_config(data_config: dict) -> str:
hash_feature_extractors(data_config['other_features']),
hash_feature_extractors(data_config['exogenous_features']),
data_config['index_column'],
data_config['method'],
data_config['no_of_classes'],
data_config['narrow_format']
]))
config/preprocess.py
+2 -2
View File
@@ -5,7 +5,7 @@ from models.model_map import get_model_map
from data_loader.collections import data_collections
def preprocess_config(model_config:dict, training_config:dict, data_config:dict) -> tuple[dict, dict, dict]:
model_config = __preprocess_model_config(model_config, data_config['method'])
model_config = __preprocess_model_config(model_config)
data_config = __preprocess_feature_extractors_config(data_config)
data_config = __preprocess_data_collections_config(data_config)
@@ -20,7 +20,7 @@ def __preprocess_feature_extractors_config(data_dict: dict) -> dict:
data_dict[key] = flatten([feature_extractor_presets[preset_name] for preset_name in preset_names])
return data_dict
def __preprocess_model_config(model_config:dict, method:str) -> dict:
def __preprocess_model_config(model_config:dict) -> dict:
model_map = get_model_map(model_config)
model_config['primary_models'] = [(model_name, model_map['primary_models'][model_name]) for model_name in model_config['primary_models']]
if len(model_config['meta_labeling_models']) > 0:
config/sweep_ensemble.yaml
+58
View File
@@ -0,0 +1,58 @@
program: run_sweep.py
method: grid
project: price-forecasting
name: Meta labelling
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:
value: True
expanding_window_meta_labeling:
value: True
sliding_window_size_primary:
value: 380
sliding_window_size_meta_labeling:
values: [250, 300, 380]
distribution: categorical
n_features_to_select:
values: [40, 50, 60]
distribution: categorical
dimensionality_reduction:
value: True
retrain_every:
value: 20
scaler:
value: 'minmax'
no_of_classes:
value: 'two'
forecasting_horizon:
value: 1
load_non_target_asset:
value: True
log_returns:
value: True
index_column:
value: 'int'
primary_models:
distribution: categorical
values:
- ["LDA", "LogisticRegression_two_class", "KNN", "SVC", "CART", "NB", "AB", "RFC", "XGB_two_class", "LGBM", "StaticMom"]
- ["LogisticRegression_two_class", "LDA", "NB", "RFC", "XGB_two_class", "LGBM", "StaticMom"]
- ["LogisticRegression_two_class", "LDA", "LGBM", "RFC", "XGB_two_class"]
meta_labeling_models:
value: ["LGBM", "LogisticRegression_two_class"]
own_features:
value: ['date_days', 'level_2', 'lags_up_to_5']
other_features:
value: ['level_2', 'lags_up_to_5']
exogenous_features:
value: ['z_score']
config/sweep_meta_labeling.yaml
+61
View File
@@ -0,0 +1,61 @@
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'
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: ["LogisticRegression_two_class", "LDA", "KNN", "CART", "NB", "AB", "RFC", "StaticMom"]
meta_labeling_models:
values: ["LogisticRegression_two_class", "LDA", "KNN", "CART", "NB", "AB", "RFC"]
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
config/sweep_primary_models.yaml
+55
View File
@@ -0,0 +1,55 @@
program: run_sweep.py
method: grid
project: price-forecasting
name: Level-1 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:
value: False
n_features_to_select:
value: 50
dimensionality_reduction:
value: True
sliding_window_size_primary:
value: 380
sliding_window_size_meta_labeling:
value: 380
retrain_every:
values: [10, 20, 30]
distribution: categorical
scaler:
value: 'minmax'
no_of_classes:
value: 'two'
forecasting_horizon:
value: 1
load_non_target_asset:
value: True
log_returns:
value: True
index_column:
value: 'int'
primary_models:
values: [['LogisticRegression_two_class'], ['SVC'], ['LDA'], ['KNN'], ['CART'], ['MNB'], ['NB'], ['AB'], ['RFC'], ['XGB_two_class'], ['LGBM']]
distribution: categorical
meta_labeling_models:
value: ["LGBM", "LogisticRegression_two_class"]
own_features:
value: ['date_days', 'level_2', 'lags_up_to_5']
other_features:
value: ['level_2', 'lags_up_to_5']
exogenous_features:
value: ['z_score']