change input to be df

app.py

@@ -17,20 +17,50 @@ def predict(
     '''
     Predict the label for the data inputed
     '''
-    # Combine the input data into a NumPy array
-    input_array = np.array([
-        age, height, weight, 
-        waist, eye_L, eye_R, 
-        hear_L, hear_R, systolic, 
-        relaxation, fasting_blood_sugar, cholesterol, 
-        triglyceride, HDL, LDL, 
-        hemoglobin, urine_protein, 
-        serum_creatinine, AST, ALT, 
-        Gtp, dental_caries
-    ])
+    # # Combine the input data into a NumPy array
+    # input_array = np.array([
+    #     age, height, weight, 
+    #     waist, eye_L, eye_R, 
+    #     hear_L, hear_R, systolic, 
+    #     relaxation, fasting_blood_sugar, cholesterol, 
+    #     triglyceride, HDL, LDL, 
+    #     hemoglobin, urine_protein, 
+    #     serum_creatinine, AST, ALT, 
+    #     Gtp, dental_caries
+    # ])
+
+    # Create a dictionary with input data and dataset var names
+    input_data = {
+        "age": age,
+        "height(cm)": height,
+        "weight(kg)": weight,
+        "waist(cm)": waist,
+        "eyesight(left)": eye_L,
+        "eyesight(right)": eye_R,
+        "hearing(left)": hear_L,
+        "hearing(right)": hear_R,
+        "systolic": systolic,
+        "relaxation": relaxation,
+        "fasting blood sugar": fasting_blood_sugar,
+        "Cholesterol": cholesterol,
+        "triglyceride": triglyceride,
+        "HDL": HDL,
+        "LDL": LDL,
+        "hemoglobin": hemoglobin,
+        "Urine protein": urine_protein,
+        "serum creatinine": serum_creatinine,
+        "AST": AST,
+        "ALT": ALT,
+        "Gtp": Gtp,
+        "dental caries": dental_caries
+    }
+    
+    # Convert the dictionary to a pandas DataFrame
+    input_df = pd.DataFrame(input_data, index=[0])
 
     #predict
-    label = MODEL.predict(input_array)
+    # label = MODEL.predict(input_array)
+    label = MODEL.predict(input_df)
 
     return label
 

model.py

@@ -31,7 +31,7 @@ class SmokerModel:
 
         return new_data_scaled
 
-    def predict(self, X: np.ndarray) -> str:
+    def predict(self, X: np.ndarray) -> str: #TODO: change type to pd df
         """
         Make a prediction on one sample using the loaded model.
 
@@ -44,16 +44,20 @@ class SmokerModel:
         predicted label
         """
 
+        # scale the data
+        X_scaled = self.scale(X)
+
         # Check if the array is 1-dimensional aka one sample
-        if len(X.shape) != 1:
+        if len(X_scaled.shape) != 1:
             raise ValueError("Input array must be one-dimensional (one sample), but got a shape of {}".format(X.shape))
             return
             
         # Reshape the array
-        X = X.reshape(1, -1)  
+        # X = X.reshape(1, -1)  
+        X_scaled = X_scaled.reshape(1, -1) 
 
-        # scale the data
-        X_scaled = self.scale(X)
+        # # scale the data
+        # X_scaled = self.scale(X)
 
         # Now, use the scaled data to make predictions using the loaded model
         array = self.model.predict(X_scaled)