Update app.py

app.py

@@ -192,6 +192,7 @@ def predict_inverse(hardness_target, ys_target, request: gr.Request):
         [el['name'] for el in domain],
         [[x] for x in x_best]))
     optimized_x = pd.DataFrame.from_dict(best_params)
+    plot = utils.interpret(optimized_x)
     #for c in optimized_x.columns:
      #   if c in continuous_variables:
       #      optimized_x[c]=optimized_x[c]*(scaling_factors[c][1]-scaling_factors[c][0])+scaling_factors[c][0]
@@ -204,7 +205,7 @@ def predict_inverse(hardness_target, ys_target, request: gr.Request):
                                'Single/Multiphase ', 'Single/Multiphase M', 'Single/Multiphase S']]
     result = optimized_x
     result = result[result>0.0].dropna(axis=1)
-    return result
+    return result, plot
 
 
 example_inputs = [420, 10]
@@ -248,11 +249,16 @@ with gr.Blocks(css=css_styling, title=page_title) as demo:
             input_hardness = gr.Text(label="Enter your target hardness (in HV)")
             input_yield_strength = gr.Text(label="Enter your target yield strength (MPa)")
         with gr.Column():
-            gr.Markdown("### Your optimal formulation and processing conditions")
-            optimal_parameters = gr.DataFrame(label="Optimal parameters", wrap=True)
-
-            gr.Markdown("### Model interpretation")
-### Fill plot
+            with gr.Row():
+                gr.Markdown("### Your optimal formulation and processing conditions")
+                optimal_parameters = gr.DataFrame(label="Optimal parameters", wrap=True)
+            with gr.Row():
+                with gr.Column():
+                    with gr.Row():
+                        gr.Markdown("### Interpretation of hardness prediction")
+                        gr.Markdown("### Interpretation of yield strength prediction")
+                    with gr.Row():
+                        output_interpretation = gr.Plot(label="Interpretation")
 
     with gr.Row():
         gr.Examples([example_inputs], [input_hardness, input_yield_strength])
@@ -263,17 +269,19 @@ with gr.Blocks(css=css_styling, title=page_title) as demo:
         fn=predict_inverse,
         inputs=[input_hardness, input_yield_strength],
         outputs=[
-            optimal_parameters
+            optimal_parameters,
+            output_interpretation,
         ],
         show_progress=True,
     )
     clear_button.click(
-        lambda x: [gr.update(value=None)] * 8,
+        lambda x: [gr.update(value=None)] * 4,
         [],
         [
             optimal_parameters,
             input_hardness,
             input_yield_strength,
+            output_interpretation,
         ],
     )