Upload folder using huggingface_hub

README.md

@@ -80,6 +80,39 @@ Reduce overfitting, improve generalization with richer features and better hyper
 
 All three models achieve ~0.70 R². RF train/test gap reduced to ~0.10 (was ~0.32). Good Fit.
 
+## Iteration 3 Room Scaling and Correct Defaults
+Fix the prediction plateau and improve scaling across all room counts and price ranges.
+
+**Steps:**
+- Added log_rooms
+- Added area_rooms_interact = area × rooms
+- Corrected pop_dens defaults in the app: `4,729` for Zurich City, `1,328` for outside (both derived from training data medians)
+
+**Models and Hyperparameters:**
+- Ridge(alpha=10.0)
+- RandomForestRegressor(n_estimators=300, max_depth=15, min_samples_leaf=3, random_state=42)
+- GradientBoostingRegressor(n_estimators=800, max_depth=5, learning_rate=0.03, min_samples_leaf=3, subsample=0.8, random_state=42)
+
+**Features:** `rooms, area, log_area, log_rooms, pop_dens, log_pop_dens, frg_pct, tax_income, income_density_score, log_income_dens, rooms_area_ratio, area_rooms_interact, lat, lon, luxurious, furnished, temporary, zurich_city, room_per_m2, Kreis 1–12, (ATTIKA), (LOFT), (SEESICHT), (LUXURIÖS), (POOL), (EXKLUSIV)`
+
+**Results:**
+
+| Model | CV R² | CV Std |
+|-------|--------|--------|
+| Ridge (alpha=10) | 0.72 | 0.04 |
+| Random Forest (tuned) | 0.72 | 0.05 |
+| Gradient Boosting (tuned) | 0.72 | 0.05 |
+
+Example predictions after fix (Zurich City, Kreis 3):
+
+| Rooms | Area | Predicted Rent |
+|-------|------|----------------|
+| 1.0 | 30 m² | CHF 1,157 |
+| 3.0 | 80 m² | CHF 3,121 |
+| 4.5 | 115 m² | CHF 3,741 |
+| 5.5 | 145 m² | CHF 4,972 |
+| 6.5 | 175 m² | CHF 5,879 |
+
 ---
 
 ## New Feature: `income_density_score`

app.py

@@ -13,11 +13,13 @@ model = model_data["model"]
 features = model_data["features"]
 log_target = model_data["log_target"]
 
-# Default values for removed inputs
-DEFAULT_POP_DENS = 1500.0
-DEFAULT_FRG_PCT = 25.0
-DEFAULT_LAT = 47.38
-DEFAULT_LON = 8.54
+DEFAULT_POP_DENS_CITY    = 4729.0
+DEFAULT_POP_DENS_OUTSIDE = 1328.0
+DEFAULT_FRG_PCT          = 25.0
+DEFAULT_LAT_CITY         = 47.380402
+DEFAULT_LON_CITY         = 8.530496
+DEFAULT_LAT_OUTSIDE      = 47.424900
+DEFAULT_LON_OUTSIDE      = 8.638663
 
 
 def predict_price(
@@ -26,19 +28,21 @@ def predict_price(
     attika, loft, seesicht,
     kreis
 ):
-    # Use defaults for hidden features
-    pop_dens = DEFAULT_POP_DENS
-    frg_pct = DEFAULT_FRG_PCT
-    lat = DEFAULT_LAT
-    lon = DEFAULT_LON
+    # Use data-derived defaults for hidden features
+    pop_dens = DEFAULT_POP_DENS_CITY if zurich_city else DEFAULT_POP_DENS_OUTSIDE
+    lat      = DEFAULT_LAT_CITY      if zurich_city else DEFAULT_LAT_OUTSIDE
+    lon      = DEFAULT_LON_CITY      if zurich_city else DEFAULT_LON_OUTSIDE
+    frg_pct  = DEFAULT_FRG_PCT
 
     # Derived features
-    log_area = np.log1p(area)
-    log_rooms = np.log1p(rooms)
-    rooms_area_ratio = rooms / (area + 1)
-    room_per_m2 = area / rooms if rooms > 0 else area
+    log_area             = np.log1p(area)
+    log_rooms            = np.log1p(rooms)
+    rooms_area_ratio     = rooms / (area + 1)
+    room_per_m2          = area / rooms if rooms > 0 else area
     income_density_score = tax_income * pop_dens / 1e6
-    area_rooms_interact = area * rooms
+    log_income_dens      = np.log1p(income_density_score)
+    log_pop_dens         = np.log1p(pop_dens)
+    area_rooms_interact  = area * rooms
 
     # Kreis dummies
     kreis_cols = {f"Kreis {i}": 0 for i in range(1, 13)}
@@ -51,9 +55,11 @@ def predict_price(
         "log_area": log_area,
         "log_rooms": log_rooms,
         "pop_dens": pop_dens,
+        "log_pop_dens": log_pop_dens,
         "frg_pct": frg_pct,
         "tax_income": tax_income,
         "income_density_score": income_density_score,
+        "log_income_dens": log_income_dens,
         "rooms_area_ratio": rooms_area_ratio,
         "area_rooms_interact": area_rooms_interact,
         "lat": lat,
@@ -108,7 +114,7 @@ demo = gr.Interface(
     title="Zurich Apartment Rent Predictor",
     description=(
         "Predict the monthly rental price for an apartment in the Canton of Zurich.\n\n"
-        "This model uses a **Random Forest Regressor** trained on ~800 Zurich apartment listings, "
+        "This model uses a **Gradient Boosting Regressor** trained on ~800 Zurich apartment listings, "
         "with features including location (district), apartment characteristics, "
         "and the **Income-Density Score** (a neighbourhood affluence proxy)."
     ),
@@ -116,4 +122,4 @@ demo = gr.Interface(
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()