Update src/streamlit_app.py

src/streamlit_app.py

@@ -8,7 +8,7 @@ import json
 from datetime import datetime
 from huggingface_hub import hf_hub_download
 
-st.set_page_config(page_title="FinTech Fraud Guard", page_icon="🛡️", layout="wide")
+st.set_page_config(page_title="FinTech Fraud Guard", layout="wide")
 
 st.markdown("""
     <style>
@@ -32,17 +32,25 @@ class MoEFraudModel(nn.Module):
         self.num_idx = {name: i for i, name in enumerate(self.num_cols)}
         
         total_input_dim = (len(self.cat_cols) * embed_dim) + len(self.num_cols)
+        
         self.gating_network = nn.Sequential(
-            nn.Linear(total_input_dim, 64), nn.BatchNorm1d(64), nn.ReLU(),
-            nn.Dropout(0.2), nn.Linear(64, 4), nn.Softmax(dim=1)
+            nn.Linear(total_input_dim, 64),
+            nn.BatchNorm1d(64),
+            nn.ReLU(),
+            nn.Dropout(0.2),
+            nn.Linear(64, 4),
+            nn.Softmax(dim=1)
         )
         
         self.e1_cols_num = ['amt', 'hour', 'day_of_week', 'is_weekend', 'unix_time']
         self.e1_cols_cat = ['category']
+        
         self.e2_cols_num = ['city_pop', 'age', 'time_diff_cc', 'cc_avg_amt_last_5', 'cc_std_amt_last_5', 'cc_max_amt_last_5']
         self.e2_cols_cat = ['cc_num', 'gender', 'job', 'city', 'state', 'zip']
+        
         self.e3_cols_num = ['merchant_fraud_rate', 'merchant_txn_count']
         self.e3_cols_cat = ['merchant', 'category']
+        
         self.e4_cols_num = ['lat', 'long', 'merch_lat', 'merch_long', 'distance_customer_merchant', 'state_mismatch_flag']
         self.e4_cols_cat = [] 
 
@@ -51,11 +59,25 @@ class MoEFraudModel(nn.Module):
         self.expert3 = self._make_expert(self._get_dim(self.e3_cols_cat, self.e3_cols_num, embed_dim))
         self.expert4 = self._make_expert(self._get_dim(self.e4_cols_cat, self.e4_cols_num, embed_dim))
 
-        self.classifier = nn.Sequential(nn.Linear(32, 16), nn.ReLU(), nn.Dropout(0.2), nn.Linear(16, 1))
+        self.classifier = nn.Sequential(
+            nn.Linear(32, 16),
+            nn.ReLU(),
+            nn.Dropout(0.2),
+            nn.Linear(16, 1)
+        )
+
+    def _get_dim(self, cats, nums, embed_dim):
+        return len(nums) + (len(cats) * embed_dim)
 
-    def _get_dim(self, cats, nums, embed_dim): return len(nums) + (len(cats) * embed_dim)
     def _make_expert(self, input_dim):
-        return nn.Sequential(nn.Linear(input_dim, 128), nn.BatchNorm1d(128), nn.ReLU(), nn.Dropout(0.2), nn.Linear(128, 32), nn.ReLU())
+        return nn.Sequential(
+            nn.Linear(input_dim, 128),
+            nn.BatchNorm1d(128),
+            nn.ReLU(),
+            nn.Dropout(0.2),
+            nn.Linear(128, 32),
+            nn.ReLU()
+        )
 
     def get_features(self, cat_input, num_input, req_cat, req_num):
         parts = []
@@ -72,12 +94,16 @@ class MoEFraudModel(nn.Module):
     def forward(self, cat_input, num_input):
         all_embs = [self.embeddings[c](cat_input[:, i]) for i, c in enumerate(self.cat_cols)]
         global_features = torch.cat([torch.cat(all_embs, dim=1), num_input], dim=1)
+        
         weights = self.gating_network(global_features)
+        
         h1 = self.expert1(self.get_features(cat_input, num_input, self.e1_cols_cat, self.e1_cols_num))
         h2 = self.expert2(self.get_features(cat_input, num_input, self.e2_cols_cat, self.e2_cols_num))
         h3 = self.expert3(self.get_features(cat_input, num_input, self.e3_cols_cat, self.e3_cols_num))
         h4 = self.expert4(self.get_features(cat_input, num_input, self.e4_cols_cat, self.e4_cols_num))
+        
         h_final = (weights[:, 0:1]*h1 + weights[:, 1:2]*h2 + weights[:, 2:3]*h3 + weights[:, 3:4]*h4)
+        
         return self.classifier(h_final)
 
 REPO_ID = "rocky250/FinTech"
@@ -133,19 +159,30 @@ if submit:
     try:
         dt_obj = datetime.strptime(trans_dt, "%d-%m-%Y %H:%M")
         
-        Build numerical feature vector (Must match the 19 features in training)
-        Order: ['amt', 'hour', 'day_of_week', 'is_weekend', 'unix_time', 'city_pop', 'age', 
-                'time_diff_cc', 'cc_avg_amt_last_5', 'cc_std_amt_last_5', 'cc_max_amt_last_5', 
-                'merchant_fraud_rate', 'merchant_txn_count', 'lat', 'long', 'merch_lat', 
-                'merch_long', 'distance_customer_merchant', 'state_mismatch_flag']
-        
         num_feats = [
-            amt, dt_obj.hour, dt_obj.weekday(), 1 if dt_obj.weekday() >= 5 else 0, dt_obj.timestamp(),
-            50000, 35, 3600, 50.0, 10.0, 100.0, 0.02, 1000, 33.5, -86.8, 33.6, -86.9, 15.5, 0
+            amt, 
+            dt_obj.hour, 
+            dt_obj.weekday(), 
+            1 if dt_obj.weekday() >= 5 else 0, 
+            dt_obj.timestamp(),
+            50000, 
+            35, 
+            3600, 
+            50.0, 
+            10.0, 
+            100.0, 
+            0.02, 
+            1000, 
+            33.5, 
+            -86.8, 
+            33.6, 
+            -86.9, 
+            15.5, 
+            0
         ]
         
         cat_feats = [category, cc_num, gender, "Job", city, state, zip_code, merchant]
-
+        
         num_input = scaler.transform([num_feats])
         
         cat_encoded = []
@@ -154,7 +191,7 @@ if submit:
             if val in encoders[col].classes_:
                 cat_encoded.append(encoders[col].transform([val])[0])
             else:
-                cat_encoded.append(0) 
+                cat_encoded.append(0)
         
         with torch.no_grad():
             cat_t = torch.tensor([cat_encoded], dtype=torch.long)
@@ -179,4 +216,4 @@ if submit:
     except Exception as e:
         st.error(f"Error in processing: {e}")
 
-st.sidebar.info("This model uses a **MoE Architecture** with 4 specialized experts for Financial Fraud Detection.")
+st.sidebar.info("This model uses a MoE Architecture with 4 specialized experts for Financial Fraud Detection.")