Upload app.py with huggingface_hub

app.py

@@ -4,13 +4,12 @@ import numpy as np
 import joblib
 import plotly.express as px
 import re
-import string
-import nltk
 import os
 from datetime import datetime
 from nltk.corpus import stopwords
+import nltk
 
-st.set_page_config(page_title="Tokopedia Project Dashboard", layout="wide")
+st.set_page_config(page_title="Tokopedia Price Predictor", layout="wide")
 
 ARTIFACTS_DIR = 'artifacts'
 
@@ -26,14 +25,10 @@ def load_resources():
         }
         final_stopwords = indo_stopwords.union(custom_stopwords)
 
-        # Load core artifacts
         vectorizer = joblib.load(os.path.join(ARTIFACTS_DIR, 'tfidf_vectorizer.pkl'))
-
-        # Load Price Artifacts
         price_preprocess = joblib.load(os.path.join(ARTIFACTS_DIR, 'price_preprocessor.pkl'))
         price_cols = joblib.load(os.path.join(ARTIFACTS_DIR, 'price_columns.pkl'))
 
-        # Load Models
         price_models = {
             "Random Forest": joblib.load(os.path.join(ARTIFACTS_DIR, 'Random_Forest_price.pkl')),
             "XGBoost": joblib.load(os.path.join(ARTIFACTS_DIR, 'XGBoost_price.pkl')),
@@ -45,8 +40,7 @@ def load_resources():
         st.error(f"Error loading resources: {e}")
         return None, None, None, None, None
 
-(vectorizer, price_preprocess, price_cols,
- price_models, final_stopwords) = load_resources()
+(vectorizer, price_preprocess, price_cols, price_models, final_stopwords) = load_resources()
 
 @st.cache_data
 def get_categories():
@@ -54,7 +48,6 @@ def get_categories():
     if price_cols:
         cat_cols = [c for c in price_cols if c.startswith('cat_')]
         columns = [c.replace('cat_', '') for c in cat_cols]
-
     return sorted(columns)
 
 def clean_text(text):
@@ -75,22 +68,19 @@ def get_date_features(date_obj, prefix):
 def prepare_raw_dataframe(user_input, target_columns, vectorizer):
     input_df = pd.DataFrame(0, index=[0], columns=target_columns)
 
-    # Text
     combined_text = clean_text(user_input.get('product_name', '')) + " " + clean_text(user_input.get('description', ''))
     tfidf_matrix = vectorizer.transform([combined_text])
     tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=[f"word_{w}" for w in vectorizer.get_feature_names_out()])
-
+    
     common_text_cols = input_df.columns.intersection(tfidf_df.columns)
     input_df[common_text_cols] = tfidf_df[common_text_cols]
 
-    # Categories
     cat_col = f"cat_{user_input.get('category', 'Other')}"
     if cat_col in input_df.columns:
         input_df[cat_col] = 1
     elif 'cat_Other' in input_df.columns:
         input_df['cat_Other'] = 1
 
-    # Numerical
     for key, value in user_input.items():
         if key in input_df.columns:
             input_df[key] = value
@@ -104,134 +94,193 @@ def load_and_plot_importance(model_name, target_name):
         df = pd.read_csv(path)
         fig = px.bar(
             df.head(15), x='Importance', y='Feature', orientation='h', error_x='Std',
-            title=f"Feature Importance ({model_name}) - {target_name.title()}", color='Importance'
+            title=f"Feature Importance ({model_name})", color='Importance'
         )
         fig.update_layout(yaxis=dict(autorange="reversed"))
         st.plotly_chart(fig)
 
-st.title("🛍️ Advanced E-Commerce Predictor")
-
-with st.expander("Product Metadata"):
-    st.header("Product Info")
-    p_name = st.text_input("Product Name", "Samsung Galaxy S24 Ultra")
-    p_desc = st.text_area("Description", "Original SEIN, Garansi Resmi 1 Tahun")
-
-    cat_options = get_categories()
-    category = st.selectbox("Category", cat_options)
-
-    condition = st.radio("Condition", ["New", "Used"])
-    is_regular = st.checkbox("Regular Merchant?", value=True)
-    is_discount = st.checkbox("Is Discounted?", value=False)
-
-    st.header("Physical & Stock")
-    col1, col2 = st.columns(2)
-    with col1:
-        weight = st.number_input("Weight (g)", value=500)
-        min_order = st.number_input("Min Order", value=1)
-    with col2:
-        max_order = st.number_input("Max Order", value=100)
-        stock = st.number_input("Stock", value=50)
-        sold_input = st.number_input("Sold (Current)", value=0)
-
-    st.header("Media")
-    vid_count = st.number_input("Video Count", 0)
-    img_count = st.number_input("Image Count", 1)
-
-with st.expander("Detailed Ratings", expanded=False):
-    c1, c2, c3, c4, c5 = st.columns(5)
-    r5 = c1.number_input("5 Star Count", value=10)
-    r4 = c2.number_input("4 Star Count", value=2)
-    r3 = c3.number_input("3 Star Count", value=0)
-    r2 = c4.number_input("2 Star Count", value=0)
-    r1 = c5.number_input("1 Star Count", value=0)
-
-    total_rating = r5 + r4 + r3 + r2 + r1
-
-    c_qual, c_srv, c_ship,  = st.columns(3)
-    rev_qual = c_qual.number_input("Reviews: Quality", 0)
-    rev_srv = c_srv.number_input("Reviews: Service", 0)
-    rev_ship = c_ship.number_input("Reviews: Shipping", 0)
-
-    c_pack, c_price, c_desc = st.columns(3)
-    rev_pack = c_pack.number_input("Reviews: Packaging", 0)
-    rev_price = c_price.number_input("Reviews: Price", 0)
-    rev_desc = c_desc.number_input("Reviews: Description", 0)
-
-with st.expander("Shipping & Shop Metadata", expanded=False):
-    c1, c2 = st.columns(2)
+st.title("🛍️ Advanced E-Commerce Price Predictor")
+
+with st.container():
+    c1, c2 = st.columns([2, 1])
     with c1:
-        ship_sameday = st.checkbox("Same Day", True)
-        ship_reg = st.checkbox("Regular", True)
-        ship_cargo = st.checkbox("Cargo", False)
-        ship_eco = st.checkbox("Economy", True)
+        p_name = st.text_input("Product Name", "Samsung Galaxy S24 Ultra")
+        p_desc = st.text_area("Description", "Original SEIN, Garansi Resmi 1 Tahun")
     with c2:
-        shop_rating = st.slider("Shop Rating Score", 0.0, 5.0, 4.8)
+        category = st.selectbox("Category", get_categories())
+        shop_tier = st.selectbox("Shop Tier", ["Regular Merchant", "Power Merchant", "Official Store"])
+        condition = st.radio("Condition", ["New", "Used"], horizontal=True)
+
+c_left, c_right = st.columns(2)
+
+with c_left:
+    with st.expander("📦 Physical, Stock & Shipping", expanded=True):
+        col1, col2 = st.columns(2)
+        weight = col1.number_input("Weight (g)", value=500)
+        stock = col2.number_input("Stock", value=50)
+        min_order = col1.number_input("Min Order", value=1)
+        max_order = col2.number_input("Max Order", value=100)
+        
+        st.caption("Shipping Options")
+        sc1, sc2, sc3 = st.columns(3)
+        ship_inst = sc1.checkbox("Instant", False)
+        ship_same = sc2.checkbox("Same Day", True)
+        ship_next = sc3.checkbox("Next Day", False)
+        ship_reg = sc1.checkbox("Regular", True)
+        ship_cargo = sc2.checkbox("Cargo", False)
+        ship_eco = sc3.checkbox("Economy", True)
+
+        is_preorder = st.checkbox("Preorder?", False)
+        is_discount = st.checkbox("Discounted?", False)
+
+    with st.expander("🏪 Shop Performance", expanded=False):
         shop_age = st.number_input("Shop Age (Days)", 365)
-        shop_pop = st.number_input("Shop City Popularity", 0.0)
+        shop_pop = st.number_input("Shop Popularity Score", 100)
+        shop_city_pop = st.number_input("City Popularity", 1)
+        resp_time = st.number_input("Response Time (mins)", 30)
+        date_shop_open = st.date_input("Shop Open Since", datetime(2020, 1, 1))
 
+    with st.expander("⚙️ Advanced Shop Setup (Detailed Ratings)", expanded=False):
+        st.caption("Input exact review counts for the entire shop")
+        ac1, ac2, ac3, ac4, ac5 = st.columns(5)
+        shop_r5 = ac1.number_input("Shop 5★", value=100)
+        shop_r4 = ac2.number_input("Shop 4★", value=10)
+        shop_r3 = ac3.number_input("Shop 3★", value=0)
+        shop_r2 = ac4.number_input("Shop 2★", value=0)
+        shop_r1 = ac5.number_input("Shop 1★", value=0)
+        
+        shop_total_rating = shop_r5 + shop_r4 + shop_r3 + shop_r2 + shop_r1
+        
+        weighted_shop_sum = (shop_r5*5 + shop_r4*4 + shop_r3*3 + shop_r2*2 + shop_r1*1)
+        shop_rating_score = weighted_shop_sum / shop_total_rating if shop_total_rating > 0 else 0.0
+        
+        st.text(f"Calculated Total Ratings: {shop_total_rating}")
+        st.text(f"Calculated Avg Score: {shop_rating_score:.2f}")
+
+with c_right:
+    with st.expander("⭐ Product Ratings & Reviews", expanded=True):
+        c1, c2, c3, c4, c5 = st.columns(5)
+        r5 = c1.number_input("Prod 5★", value=10)
+        r4 = c2.number_input("Prod 4★", value=2)
+        r3 = c3.number_input("Prod 3★", value=0)
+        r2 = c4.number_input("Prod 2★", value=0)
+        r1 = c5.number_input("Prod 1★", value=0)
+        
+        total_rating_count = r5 + r4 + r3 + r2 + r1
+        weighted_sum = (r5*5 + r4*4 + r3*3 + r2*2 + r1*1)
+        avg_rating = weighted_sum / total_rating_count if total_rating_count > 0 else 0.0
+        st.info(f"Avg Rating: {avg_rating:.2f} ({total_rating_count} ratings)")
+
+        total_reviews = st.number_input("Total Written Reviews", value=total_rating_count)
+        reviews_w_img = st.number_input("Reviews w/ Images", value=0)
+        satisfaction = st.slider("Buyer Satisfaction %", 0, 100, 95)
+
+    with st.expander("💬 Review Topics", expanded=False):
+        tc1, tc2 = st.columns(2)
+        rev_qual = tc1.number_input("Quality", 0)
+        rev_srv = tc2.number_input("Service", 0)
+        rev_pack = tc1.number_input("Packaging", 0)
+        rev_price = tc2.number_input("Price", 0)
+        rev_desc = tc1.number_input("Description", 0)
+        rev_ship = tc2.number_input("Shipping", 0)
+    
+    with st.expander("📸 Media & Listing Date", expanded=False):
+        mc1, mc2 = st.columns(2)
+        vid_count = mc1.number_input("Videos", 0)
+        img_count = mc2.number_input("Images", 1)
         date_listing = st.date_input("Listing Created", datetime.now())
-        date_shop_open = st.date_input("Shop Open Since", datetime(2020, 1, 1))
 
 feat_created = get_date_features(date_listing, "created_at")
 feat_shop = get_date_features(date_shop_open, "shop_open_since")
 listing_age_calc = (datetime.now().date() - date_listing).days
-total_shipping = sum([ship_sameday, ship_reg, ship_cargo, ship_eco])
+
+shipping_flags = [ship_inst, ship_same, ship_reg, ship_cargo, ship_eco, ship_next]
+total_shipping = sum(shipping_flags)
 
 base_input = {
     'product_name': p_name, 'description': p_desc, 'category': category,
     'condition_encoded': 1 if condition == 'New' else 0,
-    'is_regular_merchant': 1 if is_regular else 0,
+    'weight_grams': weight, 'min_order': min_order, 'max_order': max_order,
+    'stock': stock, 'sold': 0, 
+    
+    'is_preorder': 1 if is_preorder else 0,
     'is_discount': 1 if is_discount else 0,
-    'weight_grams': weight,
-    'min_order': min_order, 'max_order': max_order,
-    'stock': stock,
+    'is_regular_merchant': 1 if shop_tier == "Regular Merchant" else 0,
+    'is_power_merchant': 1 if shop_tier == "Power Merchant" else 0,
+    'is_official_store': 1 if shop_tier == "Official Store" else 0,
+
     'video_count': vid_count, 'image_count': img_count,
-    'can_shipping_sameday': 1 if ship_sameday else 0,
+
+    'can_shipping_instant': 1 if ship_inst else 0,
+    'can_shipping_sameday': 1 if ship_same else 0,
+    'can_shipping_next_day': 1 if ship_next else 0,
     'can_shipping_regular': 1 if ship_reg else 0,
     'can_shipping_cargo': 1 if ship_cargo else 0,
     'can_shipping_economy': 1 if ship_eco else 0,
     'total_shipping_types': total_shipping,
-    'shop_rating_score': shop_rating,
-    'shop_age_days': shop_age,
-    'shop_city_popularity': shop_pop,
-    'listing_age_days': listing_age_calc,
+
+    'rating': avg_rating,
+    'total_product_rating': total_rating_count,
+    'total_product_review': total_reviews,
+    'total_product_review_with_image': reviews_w_img,
+    'buyer_satisfaction_percentage': satisfaction,
     'product_rating_5_star_count': r5,
     'product_rating_4_star_count': r4,
     'product_rating_3_star_count': r3,
     'product_rating_2_star_count': r2,
     'product_rating_1_star_count': r1,
-    'total_product_rating': total_rating,
+
     'total_review_about_kualitas': rev_qual,
     'total_review_about_pelayanan': rev_srv,
-    'total_review_about_pengiriman': rev_ship,
-    'total_review_about_kemasan' : rev_pack,
-    'total_review_about_harga': rev_price, 
+    'total_review_about_kemasan': rev_pack,
+    'total_review_about_harga': rev_price,
     'total_review_about_sesuai deskripsi': rev_desc,
+    'total_review_about_pengiriman': rev_ship,
+
+    'shop_rating_score': shop_rating_score,
+    'shop_total_rating': shop_total_rating,
+    'shop_rating_5': shop_r5, 
+    'shop_rating_4': shop_r4, 
+    'shop_rating_3': shop_r3, 
+    'shop_rating_2': shop_r2, 
+    'shop_rating_1': shop_r1, 
+    'shop_response_time_mins': resp_time,
+    'shop_age_days': shop_age,
+    'listing_age_days': listing_age_calc,
+    'shop_popularity': shop_pop,
+    'shop_city_popularity': shop_city_pop,
+
     **feat_created, **feat_shop
 }
 
-if sold_input:
-    base_input['sold'] = sold_input
-
-# Log Transforms (Stock & Sold)
 base_input['Log_stock'] = np.log1p(stock)
-base_input['Log_sold'] = np.log1p(sold_input)
+base_input['Log_sold'] = np.log1p(0) 
 
 st.divider()
-
 st.subheader("💰 Price Prediction")
+
 if price_models:
-    model_name = st.selectbox("Select Price Model", list(price_models.keys()), key="p_model")
+    col_model, col_btn = st.columns([1, 1])
+    with col_model:
+        model_name = st.selectbox("Select Model", list(price_models.keys()), label_visibility="collapsed")
+    with col_btn:
+        predict_btn = st.button("Predict Price", type="primary", use_container_width=True)
 
-    if st.button("Predict Price", type="primary"):
+    if predict_btn:
         raw_df = prepare_raw_dataframe(base_input, price_cols, vectorizer)
-        X_scaled = price_preprocess.transform(raw_df)
+        
+        missing_cols = set(price_cols) - set(raw_df.columns)
+        for c in missing_cols:
+            raw_df[c] = 0
+        raw_df = raw_df[price_cols]
 
+        X_scaled = price_preprocess.transform(raw_df)
         log_pred = price_models[model_name].predict(X_scaled)[0]
         price_pred = np.expm1(log_pred)
 
         st.success(f"Estimated Price: **Rp {price_pred:,.0f}**")
-        st.markdown("### Feature Importance")
-        load_and_plot_importance(model_name, "price")
+        
+        with st.expander("Feature Importance Analysis"):
+            load_and_plot_importance(model_name, "price")
 else:
-    st.error("Price models not loaded.")
+    st.error("Models failed to load.")