Add feature selection Class skeleton.

machine_learning/feature_selection.py

@@ -1,21 +1,3 @@
-# ---
-# jupyter:
-#   jupytext:
-#     formats: ipynb,py:percent
-#     text_representation:
-#       extension: .py
-#       format_name: percent
-#       format_version: '1.3'
-#       jupytext_version: 1.13.0
-#   kernelspec:
-#     display_name: straw2analysis
-#     language: python
-#     name: straw2analysis
-# ---
-
-# %%
-# %matplotlib inline
-
 import os
 import sys
 
@@ -23,7 +5,10 @@ import numpy as np
 import matplotlib.pyplot as plt
 import pandas as pd
 
-# %%
+from sklearn.feature_selection import SequentialFeatureSelector
+from sklearn.naive_bayes import GaussianNB
+
+
 """ Feature selection pipeline: a methods that can be used in the wrapper metod alongside other wrapper contents (hyperparameter tuning etc.).
 
 (1) Establish methods for each of the steps in feature selection protocol: 
@@ -33,4 +18,28 @@ import pandas as pd
 (3) Implement a method which gives graphical exploration of (1) (a) and (b) steps of the feature selection.
 (4) Prepare a core method that can be fit into a wrapper (see sklearn wrapper methods) and integrates methods from (1)
 
-"""
+"""
+
+class FeatureSelection:
+
+    def __init__(self, X_train, X_test, y_train, y_test): # TODO: what about leave-one-subject-out CV?
+        pass
+
+
+    def within_sensors_feature_selection(estimator, scoring, tol):
+        features_list = []
+
+        nb = GaussianNB()
+        sfs = SequentialFeatureSelector(nb, n_features_to_select='auto', tol=0.02) # Can set n_features to an absolute value -> then remove tol parameter.
+
+
+        return features_list
+
+    def between_sensors_feature_selection():
+        pass
+
+    def vizualize_feature_selection_process():
+        pass
+
+    def execute_feature_selection_step():
+        pass