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

* 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

config/config.py

@@ -73,7 +73,7 @@ def get_default_ensemble_config() -> tuple[dict, dict, dict]:
     )
 
     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']
     ensemble_model = 'Average'
 

models/model_map.py

@@ -5,7 +5,7 @@ from sklearn.tree import DecisionTreeClassifier
 from sklearnex.neighbors import KNeighborsRegressor, KNeighborsClassifier
 from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
 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.ensemble import AdaBoostRegressor, RandomForestRegressor, ExtraTreesRegressor, AdaBoostClassifier, GradientBoostingClassifier, ExtraTreesClassifier
 from sklearnex.ensemble import RandomForestClassifier
@@ -51,7 +51,6 @@ model_map = {
         KNN= SKLearnModel(KNeighborsClassifier()),
         CART= SKLearnModel(DecisionTreeClassifier(max_depth=15, random_state=1)),
         NB= SKLearnModel(GaussianNB()),
-        MNB = SKLearnModel(MultinomialNB()),
         AB= SKLearnModel(AdaBoostClassifier(n_estimators=15)),
         RF= SKLearnModel(RandomForestClassifier(n_jobs=-1, max_depth=20, random_state=1)),
         SVC = SKLearnModel(SVC(kernel='rbf', C=1e3, probability=True, random_state=1)),

sweep_ensemble.yaml

@@ -21,9 +21,11 @@ parameters:
     sliding_window_size_primary: 
       value: 380
     sliding_window_size_meta_labeling: 
-      value: 380
+      values: [250, 300, 380]
+      distribution: categorical
     n_features_to_select:
-      value: 50
+      values: [40, 50, 60]
+      distribution: categorical
     dimensionality_reduction:
       value: True
     retrain_every: 
@@ -43,10 +45,13 @@ parameters:
     index_column: 
       value: 'int'
     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
+      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:
       value: ['date_days', 'level_2', 'lags_up_to_5']
     other_features: