Update app.py

app.py

@@ -22,23 +22,27 @@ rf_model = joblib.load(rf_model_path)
 def preprocess_input(input_data, method="ml"):
     if method == "ml":
         # For Random Forest prediction, apply necessary transformations like scaling or encoding.
+        
+        # Convert ClaimDate to ordinal (number of days since a particular date)
+        input_data['ClaimDate'] = pd.to_datetime(input_data['ClaimDate']).apply(lambda date: date.toordinal())
+
         # Wrap each feature value in a list to create a valid DataFrame
         input_df = pd.DataFrame({
-            'ClaimDate': [input_data['ClaimDate']],  # Wrapped in list
-            'ClaimAmount': [input_data['ClaimAmount']],  # Wrapped in list
-            'PatientAge': [input_data['PatientAge']],  # Wrapped in list
-            'PatientIncome': [input_data['PatientIncome']],  # Wrapped in list
-            'PatientGender': [input_data['PatientGender']],  # Wrapped in list
-            'ProviderSpecialty': [input_data['ProviderSpecialty']],  # Wrapped in list
-            'ClaimStatus': [input_data['ClaimStatus']],  # Wrapped in list
-            'PatientMaritalStatus': [input_data['PatientMaritalStatus']],  # Wrapped in list
-            'PatientEmploymentStatus': [input_data['PatientEmploymentStatus']],  # Wrapped in list
-            'ProviderLocation': [input_data['ProviderLocation']],  # Wrapped in list
-            'ClaimType': [input_data['ClaimType']],  # Wrapped in list
-            'ClaimSubmissionMethod': [input_data['ClaimSubmissionMethod']],  # Wrapped in list
+            'ClaimDate': [input_data['ClaimDate']],  # Now converted to ordinal value
+            'ClaimAmount': [input_data['ClaimAmount']],
+            'PatientAge': [input_data['PatientAge']],
+            'PatientIncome': [input_data['PatientIncome']],
+            'PatientGender': [input_data['PatientGender']],
+            'ProviderSpecialty': [input_data['ProviderSpecialty']],
+            'ClaimStatus': [input_data['ClaimStatus']],
+            'PatientMaritalStatus': [input_data['PatientMaritalStatus']],
+            'PatientEmploymentStatus': [input_data['PatientEmploymentStatus']],
+            'ProviderLocation': [input_data['ProviderLocation']],
+            'ClaimType': [input_data['ClaimType']],
+            'ClaimSubmissionMethod': [input_data['ClaimSubmissionMethod']],
         })
 
-        # Assuming ML preprocessing: Encoding and scaling (use the same scaler and encoders as in training)
+        # Apply necessary preprocessing: Encoding and scaling (use the same scaler and encoders as in training)
         input_df['PatientGender'] = input_df['PatientGender'].apply(lambda x: 1 if x == 'Male' else 0)
         claim_status_mapping = {"Denied": 0, "Pending": 1, "Approved": 2}
         input_df['ClaimStatus'] = input_df['ClaimStatus'].map(claim_status_mapping)
@@ -47,7 +51,6 @@ def preprocess_input(input_data, method="ml"):
         input_scaled = scaler.fit_transform(input_df)  # Scaling the data
 
         return input_scaled
-
     elif method == "nlp":
         # For NLP-based prediction, concatenate features into a single paragraph
         claim_date = input_data['ClaimDate']
@@ -78,6 +81,7 @@ def preprocess_input(input_data, method="ml"):
 
 
 
+
 # Title and description for the app
 st.title("Insurance Claim Fraud Detection")
 st.write("""