Update app.py

app.py

@@ -144,6 +144,8 @@ def fit_outputs_constraints(x, hardness_target, ys_target):
 
 def predict_inverse(hardness_target, ys_target, request: gr.Request):
 
+    one_hot_colums = utils.return_feature_names()
+
     continuous_variables = ['PROPERTY: Calculated Density (g/cm$^3$)',
                          'PROPERTY: Calculated Young modulus (GPa)']
     categorical_variables = list(one_hot.columns)
@@ -151,7 +153,7 @@ def predict_inverse(hardness_target, ys_target, request: gr.Request):
         categorical_variables.remove(c)
 
     domain = []
-    for c in one_hot.columns:
+    for c in one_hot_columns:
         if c in continuous_variables:
             if c == continuous_variables[0]:
                 domain.append({'name': str(c), 'type': 'continuous', 'domain': (0.528, 0.528)})#(0.,1.)})
@@ -162,7 +164,7 @@ def predict_inverse(hardness_target, ys_target, request: gr.Request):
 
     constraints = []
     constrained_columns = ['Single/Multiphase', 'Preprocessing method', 'BCC/FCC/other']#, 'Microstructure']
-    one_hot_colums = utils.return_feature_names()
+
     for constraint in constrained_columns:
         sum_string = ''
         for i in range (len(one_hot_columns)):
@@ -173,7 +175,7 @@ def predict_inverse(hardness_target, ys_target, request: gr.Request):
         constraints.append({'name': constraint + "-1", 'constraint': '-1*(' + sum_string + ')+1'})
 
     def fit_outputs(x):
-        return fit_outputs_constraints(x, harndess_target, ys_target)
+        return fit_outputs_constraints(x, hardness_target, ys_target)
 
     opt = GPyOpt.methods.BayesianOptimization(f = fit_outputs,            # function to optimize       
                                               domain = domain,        # box-constraints of the problem