Update app.py

app.py

@@ -9,8 +9,9 @@ citizen_data = pd.read_csv("citizen_data_50000.csv")
 services_data = pd.read_csv("citizen_services_50000.csv")
 merged_data = pd.merge(citizen_data, services_data, on="citizen_id")
 
-# Encode categorical features
-categorical_cols = ['gender', 'education', 'marital_status', 'social_category']
+# Encode categorical features including location
+categorical_cols = ['gender', 'education', 'marital_status', 'social_category',
+                    'village', 'block', 'district']
 encoders = {}
 for col in categorical_cols:
     le = LabelEncoder()
@@ -21,17 +22,17 @@ for col in categorical_cols:
 scaler = StandardScaler()
 merged_data[['age', 'annual_income']] = scaler.fit_transform(merged_data[['age', 'annual_income']])
 
-# Define feature columns (location removed)
+# Define feature columns including location
 feature_cols = ['age', 'gender', 'education', 'marital_status', 'social_category',
-                'annual_income']
+                'annual_income', 'village', 'block', 'district']
 features_matrix = merged_data[feature_cols].values
 
 # Train KNN model
 knn = NearestNeighbors(n_neighbors=10, metric='cosine')
 knn.fit(features_matrix)
 
-# Recommendation function with weighted scoring
-def recommend(age, gender, education, marital, social, income, occupation):
+# Recommendation function with location
+def recommend(age, gender, education, marital, social, income, village, block, district):
     input_data = {
         'age': [age],
         'gender': [encoders['gender'].transform([gender])[0]],
@@ -39,11 +40,13 @@ def recommend(age, gender, education, marital, social, income, occupation):
         'marital_status': [encoders['marital_status'].transform([marital])[0]],
         'social_category': [encoders['social_category'].transform([social])[0]],
         'annual_income': [income],
-        # 'occupation': [encoders['occupation'].transform([occupation])[0]]
+        'village': [encoders['village'].transform([village])[0]],
+        'block': [encoders['block'].transform([block])[0]],
+        'district': [encoders['district'].transform([district])[0]],
     }
     input_vector = pd.DataFrame(input_data)
 
-    # Normalize numeric
+    # Normalize numeric columns
     input_vector[['age', 'annual_income']] = scaler.transform(input_vector[['age', 'annual_income']])
 
     # Get neighbors and calculate weighted similarity
@@ -60,7 +63,7 @@ def recommend(age, gender, education, marital, social, income, occupation):
     recommended_services = top_users[service_cols].sum().sort_values(ascending=False).head(5)
     return [f"{service} ✅" for service in recommended_services.index]
 
-# Gradio UI
+# Gradio UI with location inputs
 iface = gr.Interface(
     fn=recommend,
     inputs=[
@@ -69,11 +72,14 @@ iface = gr.Interface(
         gr.Dropdown(encoders['education'].classes_.tolist(), label="Education Level"),
         gr.Dropdown(encoders['marital_status'].classes_.tolist(), label="Marital Status"),
         gr.Dropdown(encoders['social_category'].classes_.tolist(), label="Social Category"),
-        gr.Slider(0, 2000000, value=300000, step=10000, label="Annual Income")
+        gr.Slider(0, 2000000, value=300000, step=10000, label="Annual Income"),
+        gr.Dropdown(encoders['village'].classes_.tolist(), label="Village"),
+        gr.Dropdown(encoders['block'].classes_.tolist(), label="Block"),
+        gr.Dropdown(encoders['district'].classes_.tolist(), label="District"),
     ],
     outputs=gr.List(label="Top 5 Recommended Services"),
-    title="🧠 Citizen Service Recommender ",
-    description="Get recommended services based on citizens similar to you — without using location info.",
+    title="🧠 Citizen Service Recommender",
+    description="Get recommended services based on citizens similar to you — using your demographic and location data.",
 )
 
-iface.launch()
+iface.launch()