From 1436557287df0978a0d297f37ac457f317c35fb0 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Mon, 23 May 2022 00:31:02 +0100
Subject: [PATCH] saving work and wrapping up from the weekend

---
 UQ_FS_eg.py               |  2 +-
 UQ_LR_FS_p2.py            | 21 ++++++++++-----------
 uq_ml_models/UQ_LR_FS2.py |  2 +-
 3 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/UQ_FS_eg.py b/UQ_FS_eg.py
index 49ae5c9..5167729 100644
--- a/UQ_FS_eg.py
+++ b/UQ_FS_eg.py
@@ -66,7 +66,7 @@ print('\nbest model with feature selection:', fs_bmod)
 
 pipe = Pipeline([
     ('pre', MinMaxScaler())
-    ('selector', RFECV(LogisticRegression(**rs), cv = skf_cv, scoring = 'matthews_corrcoef'))
+    , ('selector', RFECV(LogisticRegression(**rs), cv = skf_cv, scoring = 'matthews_corrcoef'))
     , ('classifier',  LogisticRegression(**rs))])
 
 search_space = [{'selector__min_features_to_select': [1,2]},
diff --git a/UQ_LR_FS_p2.py b/UQ_LR_FS_p2.py
index fb5432c..1a8f7c3 100644
--- a/UQ_LR_FS_p2.py
+++ b/UQ_LR_FS_p2.py
@@ -73,22 +73,21 @@ parameters = [
     # }
     
     {'fs__min_features_to_select': [1,2]},
-                    {'classifier': [LogisticRegression()],
-                     #'classifier__C': np.logspace(0, 4, 10),
-                     'classifier__C': [2, 2.8],
-                     'classifier__max_iter': [100],
-                     'classifier__penalty': ['l1', 'l2'],
-                     'classifier__solver': ['saga']
+                    {'clf': [LogisticRegression(**rs)],
+                     #'clf__C': np.logspace(0, 4, 10),
+                     'clf__C': [2, 2.8],
+                     'clf__max_iter': [100],
+                     'clf__penalty': ['l1', 'l2'],
+                     'clf__solver': ['saga']
     
     }
 ]    
 #%% Create pipeline
 pipeline = Pipeline([
-   # ('pre', MinMaxScaler())
-     ('fs', RFECV(LogisticRegression(**rs), scoring = 'matthews_corrcoef'))#cant be my mcc_fn
-    #, ('clf',  ClfSwitcher())
-    , ('classifier',  ClfSwitcher())
-
+    ('pre', MinMaxScaler())
+    , ('fs', RFECV(LogisticRegression(**rs), scoring = 'matthews_corrcoef'))#cant be my mcc_fn
+    #, ('clf',  ClfSwitcher()) # gives me slightly lower results
+    #, ('clf',  LogisticRegression(**rs))
     ])
 
 #%%
diff --git a/uq_ml_models/UQ_LR_FS2.py b/uq_ml_models/UQ_LR_FS2.py
index 91d28a5..61cca74 100644
--- a/uq_ml_models/UQ_LR_FS2.py
+++ b/uq_ml_models/UQ_LR_FS2.py
@@ -62,6 +62,7 @@ Created on Tue Mar 15 11:09:50 2022
 ################
 # NOTE: GS is going into pipeline, 
 # Cannot get BEST model out
+# https://stackoverflow.com/questions/55609339/how-to-perform-feature-selection-with-gridsearchcv-in-sklearn-in-python
 ################ 
 # Create pipeline
 # pipeline = Pipeline([('pre', MinMaxScaler())
@@ -144,7 +145,6 @@ param_grid2 = [
         'clf__solver': ['saga']
     }
 
-
 ]
 # step 4: create  pipeline
 pipeline = Pipeline([