aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa

UQ_FS_eg.py

@@ -68,7 +68,6 @@ pipe = Pipeline([
     ('pre', MinMaxScaler())
 #    , ('fs', RFECV(LogisticRegression(**rs), cv = cv, scoring = 'matthews_corrcoef'))
     , ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
-
     , ('clf',  LogisticRegression(**rs))])
 
 search_space = [
@@ -204,7 +203,7 @@ print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, bts_predict),2))
 bts_mcc_score = round(matthews_corrcoef(y_bts, bts_predict),2)
 
 # Diff b/w train and bts test scores
-train_test_diff = train_bscore - bts_mcc
+train_test_diff = train_bscore - bts_mcc_score
 print('\nDiff b/w train and blind test score (MCC):', train_test_diff)
 
 
@@ -232,16 +231,25 @@ lr_btsD
 #===========================
 # Add FS related model info
 #===========================
-output_modelD = {'model_name': model_name
+model_namef = str(model_name)
+# FIXME: doesn't tell you which it has chosen
+fs_methodf = str(gscv_fs.best_estimator_.named_steps['fs'])
+all_featuresL = list(all_features)
+fs_res_arrayf = str(list( gscv_fs.best_estimator_.named_steps['fs'].get_support()))
+fs_res_array_rankf = list( gscv_fs.best_estimator_.named_steps['fs'].ranking_)
+sel_featuresf = list(sel_features)
+n_sf = int(n_sf)
+
+output_modelD = {'model_name': model_namef
                  , 'model_refit_param': mod_refit_param
                  , 'Best_model_params': b_model_params 
                  , 'n_all_features': n_all_features
-                 , 'fs_method': gscv_fs.best_estimator_.named_steps['fs'] # FIXME: doesn't tell you which it has chosen
-                 , 'fs_res_array': gscv_fs.best_estimator_.named_steps['fs'].get_support()
-                 , 'fs_res_array_rank': gscv_fs.best_estimator_.named_steps['fs'].ranking_
-                 , 'all_feature_names': all_features
+                 , 'fs_method': fs_methodf
+                 , 'fs_res_array': fs_res_arrayf
+                 , 'fs_res_array_rank': fs_res_array_rankf
+                 , 'all_feature_names': all_featuresL
                  , 'n_sel_features': n_sf
-                 , 'sel_features_names': sel_features}
+                 , 'sel_features_names': sel_featuresf}
 output_modelD
 
 #========================================
@@ -252,18 +260,33 @@ output_modelD
 
 output_modelD['train_score (MCC)'] = train_bscore
 output_modelD['bts_mcc'] = bts_mcc_score
-output_modelD['train_bts_diff'] = train_test_diff
+output_modelD['train_bts_diff'] = round(train_test_diff,2)
 output_modelD
 
+class NpEncoder(json.JSONEncoder):
+    def default(self, obj):
+        if isinstance(obj, np.integer):
+            return int(obj)
+        if isinstance(obj, np.floating):
+            return float(obj)
+        if isinstance(obj, np.ndarray):
+            return obj.tolist()
+        return super(NpEncoder, self).default(obj)
+
+json.dumps(output_modelD, cls=NpEncoder)
 
 #========================================
 # Write final output file
 # https://stackoverflow.com/questions/19201290/how-to-save-a-dictionary-to-a-file
 #========================================
-# output final dict as a json
-# outFile = 'LR_FS.json'
-# with open(outFile, 'w') as f:
-#     json.dump(output_modelD, f)
-# #
-# with open(file, 'r') as f:
-#     data = json.load(f)
+#output final dict as a json
+outFile = 'LR_FS.json'
+with open(outFile, 'w') as f:
+    f.write(json.dumps(output_modelD,cls=NpEncoder))
+    
+# read json
+file = 'LR_FS.json'
+with open(file, 'r') as f:
+    data = json.load(f)
+##############################################################################
+