update:model mod for handling NAN

app/app.py

@@ -22,4 +22,5 @@ def match(request: MatchRequest):
         result = matcher.predict(request.current_user, request.other_users)
         return {"matches": result}
     except Exception as e:
-        return {"error": str(e)}
+        return {"error": str(e)}
+        

app/model.py

@@ -1,4 +1,3 @@
-# model.py
 import numpy as np
 import pandas as pd
 from sklearn.preprocessing import OneHotEncoder, MinMaxScaler
@@ -6,18 +5,33 @@ from sklearn.metrics.pairwise import cosine_similarity
 from sentence_transformers import SentenceTransformer
 from typing import Dict, List
 
+
+def safe_normalize(v: np.ndarray) -> np.ndarray:
+    """Avoid division by zero when normalizing vectors."""
+    norm = np.linalg.norm(v, axis=1, keepdims=True)
+    norm[norm == 0] = 1e-6  # prevent division by 0
+    return v / norm
+
+
 class RoommateMatcher:
     def __init__(self):
         self.text_model = SentenceTransformer('all-MiniLM-L6-v2')
-        self.financial_encoder = OneHotEncoder(sparse_output=False, handle_unknown="ignore")
+        self.financial_encoder = OneHotEncoder(
+            sparse_output=False, handle_unknown="ignore"
+        )
         self.scaler = MinMaxScaler()
         self.is_fitted = False
 
+        # Fit encoder in advance with known categories to avoid all-zero rows
+        self.financial_encoder.fit([["split-rent"], ["single-payment"]])
+
     def predict(self, current_user: Dict, other_users: List[Dict]) -> List[Dict]:
         if not self.is_fitted and other_users:
             self._fit_encoders(other_users)
 
         others_df = pd.DataFrame(other_users)
+
+        # === TEXT VECTOR ===
         others_df['combined_text'] = others_df.apply(
             lambda x: " ".join(filter(None, [
                 str(x.get('personal_description', '')),
@@ -25,29 +39,30 @@ class RoommateMatcher:
                 *[str(s) for s in x.get('social_preference', [])]
             ])), axis=1
         )
-
         text_embeds = self.text_model.encode(others_df['combined_text'].tolist())
-        text_block = text_embeds / np.linalg.norm(text_embeds, axis=1, keepdims=True)
+        text_block = safe_normalize(text_embeds)
 
+        # === FINANCIAL VECTOR ===
         fin_block = self.financial_encoder.transform(others_df[['financials']])
-        fin_block = fin_block / np.linalg.norm(fin_block, axis=1, keepdims=True)
+        fin_block = safe_normalize(fin_block)
 
+        # === NUMERIC VECTOR ===
         num_features = np.hstack([
             np.array([x for x in others_df['location']]),
             others_df[['budget_min', 'budget_max']].values
         ])
-        num_block = self.scaler.transform(num_features)
-        num_block = num_block / np.linalg.norm(num_block, axis=1, keepdims=True)
+        num_block = safe_normalize(self.scaler.transform(num_features))
 
+        # === CURRENT USER VECTORS ===
         current_text = self.text_model.encode(" ".join(filter(None, [
             str(current_user.get('personal_description', '')),
             str(current_user.get('occupation', '')),
             *[str(s) for s in current_user.get('social_preference', [])]
         ])))
-        current_text = current_text / np.linalg.norm(current_text)
+        current_text = safe_normalize(current_text.reshape(1, -1))
 
         current_fin = self.financial_encoder.transform([[current_user['financials']]])
-        current_fin = current_fin / np.linalg.norm(current_fin)
+        current_fin = safe_normalize(current_fin)
 
         current_num = self.scaler.transform([[
             current_user['location'][0],
@@ -55,19 +70,21 @@ class RoommateMatcher:
             current_user['budget_min'],
             current_user['budget_max']
         ]])
-        current_num = current_num / np.linalg.norm(current_num)
+        current_num = safe_normalize(current_num)
 
+        # === STACK FEATURES ===
         combined_existing = np.hstack([
             text_block * 0.6,
             fin_block * 0.1,
             num_block * 0.3
         ])
         current_block = np.hstack([
-            current_text.reshape(1, -1) * 0.6,
+            current_text * 0.6,
             current_fin * 0.2,
             current_num * 0.2
         ])
 
+        # === SIMILARITY ===
         others_df['similarity'] = np.round(
             cosine_similarity(current_block, combined_existing)[0] * 100, 2
         )
@@ -75,9 +92,8 @@ class RoommateMatcher:
         return others_df.sort_values('similarity', ascending=False).head(10).to_dict('records')
 
     def _fit_encoders(self, users: List[Dict]):
-        financials = np.array([u['financials'] for u in users]).reshape(-1, 1)
         locations = np.array([u['location'] for u in users])
         budgets = np.array([[u['budget_min'], u['budget_max']] for u in users])
-        self.financial_encoder.fit(financials)
-        self.scaler.fit(np.hstack([locations, budgets]))
+        numeric_block = np.hstack([locations, budgets])
+        self.scaler.fit(numeric_block)
         self.is_fitted = True