model creation

src/pages/2-model_creation.py

@@ -257,6 +257,9 @@ if not x_block.empty and not y.empty:
     from utils.miscellaneous import data_split
     X_train, X_test, y_train, y_test, train_index, test_index = data_split(
         x=x_block, y=y)
+    import functools
+    train_pos = functools.reduce(lambda acc, x: acc + [list(x_block.index).index(x)], list(train_index), [])
+    test_pos = functools.reduce(lambda acc, x: acc + [list(x_block.index).index(x)], list(test_index), [])
 
     with c3:
         st.write('Loaded data summary')
@@ -471,9 +474,6 @@ if not x_block.empty and not y.empty:
                     Model = None
                     st.info(
                         'Info: Choose a modelling algorithm from the dropdown list!')
-            import pickle
-            with open('star.pkl', "wb") as f:
-                pickle.dump(Model, f)
             return Model
 
         c7, c8 = st.columns([2, 2])
@@ -739,12 +739,12 @@ if model:
                 imp_fig.savefig(res_path / "figures/vipscores.png")
 
             # pickle the results
-            pklfile = {'data': {'raw-spectra': x_block, 'target': y, 'training_data_idx': train_index, 'testing_data_idx': test_index},
+            pklfile = {'data': {'raw-spectra': x_block, 'target': y, 'training_data_idx': train_pos, 'testing_data_idx': test_pos},
                        'spec-preprocessing': {"normalization": modelling.best_hyperparams_['normalization'], 'SavGol(polyorder,window_length,deriv)': [modelling.best_hyperparams_["polyorder"],
                                                                                                                                                        modelling.best_hyperparams_[
                                                                                                                                                            'window_length'],
                                                                                                                                                        modelling.best_hyperparams_['deriv']]},
-                       "model_type": model_type, 'model_': modelling.model_, 'predictors_': predictors if model_type == 'TPE-iPLS' else list(x_block.columns)}
+                       "model_type": model_type, 'model_': modelling.model_, 'predictors_': list(x_block.columns), 'selected-wls': predictors if model_type == 'TPE-iPLS' else None}
 
             with open(res_path / 'file_system.pkl', "wb") as pkl:
                 dump(pklfile, pkl)
@@ -776,7 +776,7 @@ if model:
 #         def preparing_results_for_downloading(change):
 #            # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~            ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
 
-        pklfile = {'model_': modelling.model_, "model_type": model_type, 'data': {'raw-spectra': x_block, 'target': y, 'training_data_idx': train_index, 'testing_data_idx': test_index},
+        pklfile = {'model_': modelling.model_, "model_type": model_type, 'data': {'raw-spectra': x_block, 'target': y, 'training_data_idx': train_pos, 'testing_data_idx': test_pos},
                    'spec-preprocessing': {"normalization": modelling.best_hyperparams_['normalization'], 'SavGol(polyorder,window_length,deriv)': [modelling.best_hyperparams_["polyorder"],
                                                                                                                                                    modelling.best_hyperparams_[
                        'window_length'],