Upload app.py with huggingface_hub

app.py

@@ -6,13 +6,10 @@ from pydantic import BaseModel
 from typing import Dict, Any
 from huggingface_hub import hf_hub_download
 
-# Hugging Face model repo to pull artifacts from
 MODEL_REPO_ID = "singhina/tourism-tuned-model"
+HF_TOKEN = os.environ.get("HF_TOKEN")  # read token from Space secret
 
-# Read token from environment (set this in Space → Settings → Secrets)
-HF_TOKEN = os.environ.get("HF_TOKEN")
-
-# Download model + features (token may be None if repo is public)
+# Download model + features from HF Hub
 model_file = hf_hub_download(repo_id=MODEL_REPO_ID, filename="best_xgb.json",
                              repo_type="model", token=HF_TOKEN)
 features_file = hf_hub_download(repo_id=MODEL_REPO_ID, filename="features.txt",
@@ -22,7 +19,7 @@ features_file = hf_hub_download(repo_id=MODEL_REPO_ID, filename="features.txt",
 with open(features_file, "r") as f:
     FEATURE_NAMES = [line.strip() for line in f if line.strip()]
 
-# Load XGBoost booster
+# Load trained booster
 booster = xgb.Booster()
 booster.load_model(model_file)
 
@@ -43,18 +40,14 @@ class CustomerInput(BaseModel):
 def predict(input: CustomerInput):
     row = input.data
 
-    # Build a full feature row (missing columns default to 0.0)
+    # Fill missing features with 0.0
     full_row = {name: 0.0 for name in FEATURE_NAMES}
     for k, v in row.items():
         if k in full_row:
             try:
                 full_row[k] = float(v)
             except Exception:
-                # basic coercion for booleans / strings
-                try:
-                    full_row[k] = float(str(v).strip().lower() in ["true","1","yes"])
-                except Exception:
-                    full_row[k] = 0.0
+                full_row[k] = float(str(v).strip().lower() in ["true","1","yes"])
 
     df = pd.DataFrame([full_row])[FEATURE_NAMES].astype(float)
     dmat = xgb.DMatrix(df)