From 8d8fc03f72e899ef16e7c1a5183a058dade36fa7 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Mon, 20 Jun 2022 21:53:15 +0100
Subject: [PATCH] added test script to test dissected model

---
 scripts/ml/Mult_dissected_CALL.py | 87 +++++++++++++++++++++++++++++++
 1 file changed, 87 insertions(+)
 create mode 100644 scripts/ml/Mult_dissected_CALL.py

diff --git a/scripts/ml/Mult_dissected_CALL.py b/scripts/ml/Mult_dissected_CALL.py
new file mode 100644
index 0000000..229ed92
--- /dev/null
+++ b/scripts/ml/Mult_dissected_CALL.py
@@ -0,0 +1,87 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Jun 20 13:05:23 2022
+
+@author: tanu
+"""
+#==================
+# Baseline models 
+#==================
+cm_di2 = MultModelsCl_dissected(input_df = X
+                    , target = y
+                    , var_type = 'mixed'
+                    , skf_cv = skf_cv
+                    , blind_test_input_df = X_bts
+                    , blind_test_target = y_bts
+                    , add_cm = True 
+                    , add_yn = True)
+
+baseline_all2 = pd.DataFrame(cm_di2)
+baseline_all2 = baseline_all2.T
+baseline_CTBT2 = baseline_all2.filter(regex = 'test_.*|bts_.*|TN|FP|FN|TP|.*_neg|.*_pos' , axis = 1)
+
+#================
+# Stability cols
+#================
+
+
+#================
+# Affinity cols
+#================
+
+
+#================
+# Residue level
+#================
+
+
+#================
+# Genomics
+# X_genomicFN
+#================
+feature_gp_name = 'genomics'
+
+scores_mm_gn = MultModelsCl_dissected(input_df = X[X_genomicFN]
+                    , target = y
+                    , var_type = 'mixed'
+                    , skf_cv = skf_cv
+                    , blind_test_input_df = X_bts[X_genomicFN]
+                    , blind_test_target = y_bts
+                    , add_cm = True 
+                    , add_yn = True)
+
+baseline_all_gn = pd.DataFrame(scores_mm_gn)
+baseline_CTBT_gn = baseline_all_gn.filter(regex = '.*_time|test_.*|bts_.*|TN|FP|FN|TP|.*_neg|.*_pos' , axis = 0)
+baseline_CTBT_gn['feature_group'] = feature_gp_name
+
+
+
+baseline_CT = baseline_CTBT_gn.filter(regex = '.*_time|test_.*|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0)
+
+baseline_CT = baseline_CT.reset_index()
+baseline_CT.rename(columns = {'index': 'original_index'}, inplace = True)
+baseline_CT['score_type'] = baseline_CT['original_index'] 
+baseline_CT['score_type'] = baseline_CT['score_type'].str.replace('test_*', '', regex = True)
+baseline_CT['data_source'] = 'CT_score'
+
+
+baseline_BT = baseline_CTBT_gn.filter(regex = 'bts_', axis = 0)
+baseline_BT = baseline_BT.reset_index()
+baseline_BT.rename(columns = {'index': 'original_index'}, inplace = True)
+baseline_BT['score_type'] = baseline_BT['original_index'] 
+baseline_BT['score_type'] = baseline_BT['score_type'].str.replace('bts_*', '', regex = True)
+baseline_BT['data_source'] = 'BT_score'
+
+# rpow bind 
+if all(baseline_CT.columns == baseline_BT.columns):
+    print('\nPASS:colnames match, proceeding to rowbind')
+    comb_df = pd.concat([baseline_BT,baseline_CT], axis = 0, ignore_index = True ) 
+    
+baseline_CT
+baseline_CT
+
+#================
+# Evolution
+#================
+