Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,229 @@
+import streamlit as st
+import pandas as pd
+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
+
+st.set_page_config(page_title="Tokopedia Project Dashboard", layout="wide")
+
+ARTIFACTS_DIR = 'artifacts'
+
+@st.cache_resource
+def load_resources():
+    try:
+        nltk.download('stopwords')
+        indo_stopwords = set(stopwords.words('indonesian'))
+        custom_stopwords = {
+            'yg', 'dg', 'dgn', 'ny', 'nya', 'kalo', 'klo', 'gan', 'sis', 'kak', 'bro',
+            'bosh', 'boss', 'nomor', 'wa', 'hub', 'cod', 'ready', 'stock', 'stok',
+            'promo', 'murah', 'diskon', 'termurah', 'terlaris', 'bestseller'
+        }
+        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_scaler = joblib.load(os.path.join(ARTIFACTS_DIR, 'scaler.pkl'))
+        price_cols = joblib.load(os.path.join(ARTIFACTS_DIR, 'feature_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')),
+            "MLP": joblib.load(os.path.join(ARTIFACTS_DIR, 'MLP_price.pkl'))
+        }
+
+        return vectorizer, price_scaler, price_cols, price_models, final_stopwords
+    except Exception as e:
+        st.error(f"Error loading resources: {e}")
+        return None, None, None, None, None
+
+(vectorizer, price_scaler, price_cols,
+ price_models, final_stopwords) = load_resources()
+
+@st.cache_data
+def get_categories():
+    columns = ['Other']
+    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):
+    if not isinstance(text, str): return ""
+    text = text.lower()
+    text = re.sub(r'[^a-z0-9\s]', ' ', text)
+    text = re.sub(r'\s+', ' ', text).strip()
+    words = text.split()
+    return " ".join([w for w in words if w not in final_stopwords])
+
+def get_date_features(date_obj, prefix):
+    return {
+        f"{prefix}_dayofweek": date_obj.weekday(),
+        f"{prefix}_month": date_obj.month,
+        f"{prefix}_is_weekend": 1 if date_obj.weekday() >= 5 else 0
+    }
+
+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
+
+    return input_df
+
+def load_and_plot_importance(model_name, target_name):
+    filename = f"importance_data_{target_name}_{model_name.replace(' ', '_')}.csv"
+    path = os.path.join(ARTIFACTS_DIR, filename)
+    if os.path.exists(path):
+        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'
+        )
+        fig.update_layout(yaxis=dict(autorange="reversed"))
+        st.plotly_chart(fig)
+
+st.title("🛍️ Advanced E-Commerce Predictor")
+
+with st.sidebar:
+    st.header("1. 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("2. 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("3. Media")
+    vid_count = st.number_input("Video Count", 0)
+    img_count = st.number_input("Image Count", 1)
+
+with st.expander("Detailed Ratings", expanded=True):
+    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)
+
+with st.expander("Shipping & Shop Metadata", expanded=False):
+    c1, c2 = st.columns(2)
+    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)
+    with c2:
+        shop_rating = st.slider("Shop Rating Score", 0.0, 5.0, 4.8)
+        shop_age = st.number_input("Shop Age (Days)", 365)
+        shop_pop = st.number_input("Shop City Popularity", 0.0)
+
+        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])
+
+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,
+    'is_discount': 1 if is_discount else 0,
+    'weight_grams': weight,
+    'min_order': min_order, 'max_order': max_order,
+    'stock': stock,
+    'video_count': vid_count, 'image_count': img_count,
+    'can_shipping_sameday': 1 if ship_sameday 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,
+    '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,
+    **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)
+
+st.divider()
+
+st.subheader("💰 Price Prediction")
+if price_models:
+    model_name = st.selectbox("Select Price Model", list(price_models.keys()), key="p_model")
+
+    if st.button("Predict Price", type="primary"):
+        raw_df = prepare_raw_dataframe(base_input, price_cols, vectorizer)
+        X_scaled = price_scaler.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")
+else:
+    st.error("Price models not loaded.")