gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-17 04:48:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(Sweep): try to filter out some not great models (#144)

Browse Source 
* feat(Sweep): try to filter out some not great models

* fix(Sweep): yaml

* fix(Sweep): yaml

* fix(Config): remove some models that do not perform well
This commit is contained in:
Mark Aron Szulyovszky
2022-01-11 10:33:18 +01:00
committed by GitHub
parent 2c03959315
commit 54ea59c0cf
3 changed files with 12 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config/config.py
+1 -1
View File
@@ -73,7 +73,7 @@ def get_default_ensemble_config() -> tuple[dict, dict, dict]:
) )
regression_models = ["Lasso", "KNN", "RF"] regression_models = ["Lasso", "KNN", "RF"]
classification_models = ['LR_two_class', 'SVC', 'KNN', 'CART', 'NB', 'AB', 'RF', 'XGB_two_class', 'LGBM', 'StaticMom'] classification_models = ["LR_two_class", "LDA", "NB", "RF", "XGB_two_class", "LGBM", "StaticMom"]
meta_labeling_models = ['LR_two_class', 'LGBM'] meta_labeling_models = ['LR_two_class', 'LGBM']
ensemble_model = 'Average' ensemble_model = 'Average'
models/model_map.py
+1 -2
View File
@@ -5,7 +5,7 @@ from sklearn.tree import DecisionTreeClassifier
from sklearnex.neighbors import KNeighborsRegressor, KNeighborsClassifier from sklearnex.neighbors import KNeighborsRegressor, KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearnex.svm import SVR, SVC from sklearnex.svm import SVR, SVC
from sklearn.naive_bayes import GaussianNB, MultinomialNB from sklearn.naive_bayes import GaussianNB
from sklearn.neural_network import MLPRegressor, MLPClassifier from sklearn.neural_network import MLPRegressor, MLPClassifier
from sklearn.ensemble import AdaBoostRegressor, RandomForestRegressor, ExtraTreesRegressor, AdaBoostClassifier, GradientBoostingClassifier, ExtraTreesClassifier from sklearn.ensemble import AdaBoostRegressor, RandomForestRegressor, ExtraTreesRegressor, AdaBoostClassifier, GradientBoostingClassifier, ExtraTreesClassifier
from sklearnex.ensemble import RandomForestClassifier from sklearnex.ensemble import RandomForestClassifier
@@ -51,7 +51,6 @@ model_map = {
KNN= SKLearnModel(KNeighborsClassifier()), KNN= SKLearnModel(KNeighborsClassifier()),
CART= SKLearnModel(DecisionTreeClassifier(max_depth=15, random_state=1)), CART= SKLearnModel(DecisionTreeClassifier(max_depth=15, random_state=1)),
NB= SKLearnModel(GaussianNB()), NB= SKLearnModel(GaussianNB()),
MNB = SKLearnModel(MultinomialNB()),
AB= SKLearnModel(AdaBoostClassifier(n_estimators=15)), AB= SKLearnModel(AdaBoostClassifier(n_estimators=15)),
RF= SKLearnModel(RandomForestClassifier(n_jobs=-1, max_depth=20, random_state=1)), RF= SKLearnModel(RandomForestClassifier(n_jobs=-1, max_depth=20, random_state=1)),
SVC = SKLearnModel(SVC(kernel='rbf', C=1e3, probability=True, random_state=1)), SVC = SKLearnModel(SVC(kernel='rbf', C=1e3, probability=True, random_state=1)),
sweep_ensemble.yaml
+10 -5
View File
@@ -21,9 +21,11 @@ parameters:
sliding_window_size_primary: sliding_window_size_primary:
value: 380 value: 380
sliding_window_size_meta_labeling: sliding_window_size_meta_labeling:
value: 380 values: [250, 300, 380]
distribution: categorical
n_features_to_select: n_features_to_select:
value: 50 values: [40, 50, 60]
distribution: categorical
dimensionality_reduction: dimensionality_reduction:
value: True value: True
retrain_every: retrain_every:
@@ -43,10 +45,13 @@ parameters:
index_column: index_column:
value: 'int' value: 'int'
primary_models: primary_models:
value: ["LDA", "KNN", "SVC", "CART", "NB", "AB", "RF", "XGB_two_class", "LGBM", "StaticMom"]
meta_labeling_models:
values: [["LDA"], ["XGB_two_class"], ["LR_two_class"], ["LGBM"], ["LGBM", "LR_two_class"], ["XGB_two_class", "LDA"], ["XGB_two_class", "LR_two_class"]]
distribution: categorical distribution: categorical
values:
- ["LDA", "LR_two_class", "KNN", "SVC", "CART", "NB", "AB", "RF", "XGB_two_class", "LGBM", "StaticMom"]
- ["LR_two_class", "LDA", "NB", "RF", "XGB_two_class", "LGBM", "StaticMom"]
- ["LR_two_class", "LDA", "LGBM", "RF", "XGB_two_class"]
meta_labeling_models:
value: ["LGBM", "LR_two_class"]
own_features: own_features:
value: ['date_days', 'level_2', 'lags_up_to_5'] value: ['date_days', 'level_2', 'lags_up_to_5']
other_features: other_features: