feat(Transformations): replaced feature selection pre-processing step with online version (with cache) (#170)

* feat(Transformations): removed feature-selection pre-processing step completely

* fix(Core): removed unnecessary `original_X`

* fix(Transformations): use the X_expanding_window to transform subsequent data

* fix(RFE): should check for model correctly

* fix(Config): only re-train the model every 40 timestamp

* fix(MetaLabeling): pass in the correct X to meta-labeling step

* fix(Transformation): PCA should at least keep as many features as sliding_window_size

* feat(Transformations): cache transformations across the same asset

* fix(Tests): missing preloaded_transformations arg

* chore(Config): got rid of unnecessary 'classification_models' and 'regression_models' dictionary keys

transformations/pca.py

@@ -0,0 +1,39 @@
+from __future__ import annotations
+from transformations.base import Transformation
+from typing import Optional
+from copy import deepcopy
+from sklearn.decomposition import PCA
+import pandas as pd
+
+class PCATransformation(Transformation):
+
+    pca: PCA
+
+    def __init__(self, ratio_components_to_keep: float, sliding_window_size: int):
+        self.ratio_components_to_keep = ratio_components_to_keep
+        self.sliding_window_size = sliding_window_size
+
+    def fit(self, X: pd.DataFrame, y: Optional[pd.Series] = None) -> None:
+        self.pca = PCA(n_components = min(int(len(X.columns) * self.ratio_components_to_keep), self.sliding_window_size))
+        self.pca.fit(X, y)
+    
+    def fit_transform(self, X: pd.DataFrame, y: Optional[pd.Series] = None) -> pd.DataFrame:
+        self.fit(X, y)
+        return self.transform(X)
+
+    def transform(self, X: pd.DataFrame) -> pd.DataFrame:
+        X = pd.DataFrame(self.pca.transform(X), index = X.index)
+        X.columns = ['PCA_' + str(i) for i in range(1, len(X.columns)+1)]
+        return X
+
+    def clone(self) -> PCATransformation:
+        return deepcopy(self)
+
+    def get_name(self) -> str:
+        return "PCA"
+
+    
+
+
+    
+    

transformations/rfe.py

@@ -0,0 +1,46 @@
+from __future__ import annotations
+from transformations.base import Transformation
+from typing import Optional
+from copy import deepcopy
+from sklearn.feature_selection import RFE
+import pandas as pd
+from models.base import Model
+from models.model_map import default_feature_selector_classification
+
+class RFETransformation(Transformation):
+
+    rfe: RFE
+    n_feature_to_select: int
+
+    def __init__(self, n_feature_to_select: int, model: Model, step = 0.1):
+        self.n_feature_to_keep = n_feature_to_select
+        self.model = model
+        if hasattr(self.model, 'model') == False: return
+        if hasattr(self.model.model, 'feature_importances_') == False and hasattr(self.model.model, 'coef_') == False:
+            model = default_feature_selector_classification
+        self.rfe = RFE(model.model, n_features_to_select= n_feature_to_select, step=step)
+
+    def fit(self, X: pd.DataFrame, y: Optional[pd.Series] = None) -> None:
+        if self.rfe is None: return
+        self.rfe.fit(X, y)
+
+    def fit_transform(self, X: pd.DataFrame, y: Optional[pd.Series] = None) -> pd.DataFrame:
+        if self.rfe is None: return X
+        self.fit(X, y)
+        return self.transform(X)
+
+    def transform(self, X: pd.DataFrame) -> pd.DataFrame:
+        if self.rfe is None: return X
+        return pd.DataFrame(X[X.columns[self.rfe.support_]], index= X.index)
+
+    def clone(self) -> RFETransformation:
+        return deepcopy(self)
+
+    def get_name(self) -> str:
+        return "RFE"
+
+    
+
+
+    
+