feat(Selection): added toggleable feature selection step into the pipeline (#83)

* feat(Selection): added prototype feature selection python script

* feat(Utils): added some helpers for the future from Advances in Financial ML book

* feat(Selection): added RFECV

* feat(Selection): added configurable feature selection step into pipeline

* feat(Config): added level_1 & level_2 default config, PCA before feature selection process starts

* feat(Selection): added backup feature selector models if current one can't output feature importance, removed unnecessary array for level-2 models

* fix(Training): deal with zero first value coming out of static models

* feat(Sweep): added feature selection sweep

* fix(Sweep): config problem

* fix(Sweep): config

* chore(Utils): removed unnecessary purged k-fold crossval class

* feat(Config): added dimensionality_reduction as a separate flag

* fix(Sweep): config updated

* fix(Sweep): sweep name

* chore(Config): updated level_2 config to the best performing configuation

models/average.py

@@ -6,9 +6,10 @@ class StaticAverageModel(Model):
     Model that averages .
     '''
 
-    # data_format = 'dataframe'
     data_scaling = 'unscaled'
     only_column = 'model_'
+    feature_selection = 'off'
+    model_type = 'static'
 
     def fit(self, X, y, prev_model):
         # This is a static model, it can' learn anything

models/base.py

@@ -5,10 +5,11 @@ from abc import ABC, abstractmethod, abstractproperty
 
 class Model(ABC):
 
-    # data_format: Literal['dataframe', 'numpy'] 
     data_scaling: Literal["scaled", "unscaled"]
+    feature_selection: Literal["on", "off"]
     # data_format: Literal["wide", "narrow"]
     only_column: Optional[str]
+    model_type: Literal['ml', 'static']
 
     @abstractmethod
     def fit(self, X, y, prev_model):
@@ -25,9 +26,10 @@ class Model(ABC):
 
 class SKLearnModel(Model):
 
-    # data_format = 'numpy'
     data_scaling = 'scaled'
     only_column = None
+    feature_selection = 'on'
+    model_type = 'ml'
 
     def __init__(self, model):
         self.model = model

models/model_map.py

@@ -22,12 +22,12 @@ model_map = {
         KNN = SKLearnModel(KNeighborsRegressor(n_neighbors=25)),
         AB = SKLearnModel(AdaBoostRegressor(random_state=1)),
         MLP = SKLearnModel(MLPRegressor(hidden_layer_sizes=(100,20), max_iter=1000)),
-        RF = SKLearnModel(RandomForestRegressor(n_jobs=-1, random_state=1)),
+        RF = SKLearnModel(RandomForestRegressor(n_jobs=-1, max_depth=20, random_state=1)),
         SVR = SKLearnModel(SVR(kernel='rbf', C=1e3, gamma=0.1)),
         StaticNaive = StaticNaiveModel(),
     ),
     "classification_models": dict(
-        LR= SKLearnModel(LogisticRegression(C=10, random_state=1, max_iter=1000)),
+        LR= SKLearnModel(LogisticRegression(C=10, random_state=1, max_iter=1000, n_jobs=-1)),
         LDA= SKLearnModel(LinearDiscriminantAnalysis()),
         KNN= SKLearnModel(KNeighborsClassifier()),
         CART= SKLearnModel(DecisionTreeClassifier(max_depth=15, random_state=1)),
@@ -42,10 +42,12 @@ model_map = {
 model_names_classification = list(model_map["classification_models"].keys())
 model_names_regression = list(model_map["regression_models"].keys())
 
+default_feature_selector_regression = model_map['regression_models']['RF']
+default_feature_selector_classification = model_map['classification_models']['RF']
 
 def map_model_name_to_function(model_config:dict, method:str) -> dict:
-    for level in ['level_1_models', 'level_2_models']:
-        model_category = method + '_models'
-        model_config[level] = [(model_name, model_map[model_category][model_name]) for model_name in  model_config[level]]
+    model_config['level_1_models'] = [(model_name, model_map[method + '_models'][model_name]) for model_name in  model_config['level_1_models']]
+    if model_config['level_2_model'] is not None:
+        model_config['level_2_model'] = (model_config['level_2_model'], model_map[method + '_models'][model_config['level_2_model']])
 
     return model_config

models/momentum.py

@@ -6,9 +6,10 @@ class StaticMomentumModel(Model):
     Model that uses only one feature: momentum. It's positive if momentum is greater than 0, otherwise it's negative.
     '''
 
-    # data_format = 'dataframe'
     data_scaling = 'unscaled'
     only_column = 'mom'
+    feature_selection = 'off'
+    model_type = 'static'
 
     def __init__(self, allow_short: bool) -> None:
         super().__init__()

models/naive.py

@@ -6,9 +6,10 @@ class StaticNaiveModel(Model):
     Model that carries the last observation (from returns) to the next one, naively.
     '''
 
-    # data_format = 'dataframe'
     data_scaling = 'unscaled'
     only_column = None
+    feature_selection = 'off'
+    model_type = 'static'
 
     def fit(self, X, y, prev_model):
         # This is a static model, it can' learn anything