push, ahhhhhhh

app.py

@@ -30,7 +30,6 @@ def load_model():
     return model
 
 model = load_model()
-print(dir(model))
 
 def predict_proba(data_dict):
     pred_dict = model.predict_proba([data_dict])[1][0]
@@ -166,12 +165,24 @@ if predict_button:
     data_dict = convert_dictionary(data_dict, nacc_mapping)
     pred_dict = predict_proba(data_dict)
 
-    # change key name
-    # key_mappings = {
-    #     'NC': 'Normal cognition',
-    #     'MCI':
-
-    # }
-
-    st.write("Predicted probabilities:")
-    st.code(json.dumps(pred_dict, indent=2))
+    # change key name and value representations
+    key_mappings = {
+        'NC': 'Normal cognition',
+        'MCI': 'Mild cognitive impairment',
+        'DE': 'Dementia',
+        'AD': 'Alzheimer\'s disease',
+        'LBD': 'Lewy bodies and Parkinson\'s disease',
+        'VD': 'Vascular brain injury or vascular dementia including stroke',
+        'PRD': 'Prion disease including Creutzfeldt-Jakob disease',
+        'FTD': 'Frontotemporal lobar degeneration',
+        'NPH': 'Normal pressure hydrocephalus',
+        'SEF': 'Systemic and external factors',
+        'PSY': 'Psychiatric diseases',
+        'TBI': 'Traumatic brain injury',
+        'ODE': 'Other causes which include neoplasms, multiple systems atrophy, essential tremor, Huntington\'s disease, Down syndrome, and seizures'
+    }
+    pred_dict = {key_mappings[k]: f"{v * 100:.2f}%" for k, v in pred_dict.items()}
+
+    st.write("Predictions")
+    df = pd.DataFrame(list(pred_dict.items()), columns=['Label', 'Probability'])
+    st.table(df)