Update valuation

valuation

@@ -66,3 +66,71 @@ def deal_score(predicted_resale: float, ask: float, fee_rate: float=0.13, ship:
     elif profit >= 5: label = "Meh"
     else: label = "Pass"
     return round(fees,2), round(net,2), round(profit,2), round(margin,2), label
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.pipeline import Pipeline
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import OneHotEncoder
+from sklearn.linear_model import Ridge
+
+# Tiny seed comps to learn rough resale from titles/brands
+SEED = [
+    ("Nintendo Wii Console with controllers","Electronics","Nintendo","Used-Good",85),
+    ("Vintage Pyrex mixing bowl set","Home & Kitchen","Pyrex","Used-Good",120),
+    ("Levi's 501 jeans men's 34x32","Clothing","Levi's","Used-Good",28),
+    ("Patagonia Synchilla fleece pullover M","Clothing","Patagonia","Used-Good",45),
+    ("KitchenAid Artisan stand mixer","Home & Kitchen","KitchenAid","Used-Good",220),
+    ("Bose QuietComfort 35 headphones","Electronics","Bose","Used-Good",140),
+    ("Apple iPhone 11 128GB unlocked","Electronics","Apple","Used-Good",240),
+    ("Herman Miller Aeron chair size B","Furniture","Herman Miller","Used-Good",500),
+    ("Sony PlayStation 2 console slim","Electronics","Sony","Used-Good",75),
+    ("Le Creuset dutch oven 5.5 qt","Home & Kitchen","Le Creuset","Used-Good",240),
+    ("Sony Walkman cassette player","Electronics","Sony","Used-Good",95),
+    ("All-Clad stainless pan 10 inch","Home & Kitchen","All-Clad","Used-Good",55),
+    ("Coach leather handbag crossbody","Accessories","Coach","Used-Good",65),
+    ("Seiko 5 automatic watch SNK809","Accessories","Seiko","Used-Good",95),
+]
+
+def _seed_df():
+    return pd.DataFrame(SEED, columns=["title","category","brand","condition","price"])
+
+class DealValuator:
+    def __init__(self, df: pd.DataFrame | None = None):
+        self.df = df if df is not None else _seed_df()
+        self.model = self._train(self.df)
+
+    def _train(self, df: pd.DataFrame):
+        text_features = 'title'
+        cat_features = ['category','brand','condition']
+        pre = ColumnTransformer([
+            ('t', TfidfVectorizer(ngram_range=(1,2), min_df=1), text_features),
+            ('c', OneHotEncoder(handle_unknown='ignore'), cat_features),
+        ])
+        model = Pipeline([('pre', pre), ('reg', Ridge(alpha=1.0))])
+        X = df[['title','category','brand','condition']]
+        y = df['price']
+        model.fit(X, y)
+        return model
+
+    def predict_resale(self, title: str, category: str | None = None,
+                       brand: str | None = None, condition: str = 'Used-Good') -> float:
+        X = pd.DataFrame([{
+            'title': title or '',
+            'category': category or 'Unknown',
+            'brand': brand or 'Unknown',
+            'condition': condition or 'Used-Good'
+        }])
+        pred = float(self.model.predict(X)[0])
+        return max(5.0, round(pred, 2))
+
+def deal_score(predicted_resale: float, ask: float, fee_rate: float = 0.13, ship: float = 12.0):
+    fees = predicted_resale * fee_rate
+    net = predicted_resale - fees - ship
+    profit = net - ask
+    margin = (profit / ask) if ask > 0 else 0.0
+    if profit >= 50 and margin >= 0.8: label = "Home Run"
+    elif profit >= 25 and margin >= 0.5: label = "Great"
+    elif profit >= 10 and margin >= 0.3: label = "Good"
+    elif profit >= 5: label = "Meh"
+    else: label = "Pass"
+    return round(fees,2), round(net,2), round(profit,2), round(margin,2), label