import os import random import joblib import numpy as np import pandas as pd import streamlit as st from sklearn.metrics.pairwise import cosine_similarity # -------------------------------------------------- # Paths (HuggingFace-safe) # -------------------------------------------------- REPO_ROOT = os.getcwd() # /app SRC_DIR = os.path.join(REPO_ROOT, "src") ARTIFACT_R = os.path.join(SRC_DIR, "R_sparse.pkl") ARTIFACT_PRODUCTS = os.path.join(SRC_DIR, "product_ids.pkl") ARTIFACT_MAP = os.path.join(SRC_DIR, "prod_to_idx.pkl") # -------------------------------------------------- # Page config # -------------------------------------------------- st.set_page_config( page_title="Amazon Electronics Recommender", page_icon="🛒", layout="wide" ) st.title("🛒 Amazon Electronics Product Recommender") st.caption( "Item-based Collaborative Filtering " "(Sparse User–Item Matrix + Cosine Similarity)" ) # -------------------------------------------------- # Load artifacts # -------------------------------------------------- @st.cache_resource def load_artifacts(): required = [ARTIFACT_R, ARTIFACT_PRODUCTS, ARTIFACT_MAP] missing = [p for p in required if not os.path.exists(p)] if missing: raise FileNotFoundError( f"Missing files: {missing}\n\n" f"Repo root files: {os.listdir(REPO_ROOT)}\n" f"src/ files: {os.listdir(SRC_DIR)}" ) R = joblib.load(ARTIFACT_R) # scipy.sparse csr_matrix product_ids = joblib.load(ARTIFACT_PRODUCTS) prod_to_idx = joblib.load(ARTIFACT_MAP) product_ids = np.array(list(product_ids)) return R, product_ids, prod_to_idx # -------------------------------------------------- # Recommendation function # -------------------------------------------------- def recommend_sparse( R, product_ids, prod_to_idx, product_id: str, top_n: int = 10, min_sim: float = 0.01 ): if product_id not in prod_to_idx: return pd.DataFrame( {"message": ["Product not found. Please try another product_id."]} ) j = prod_to_idx[product_id] # item vector (1 x users) item_vec = R[:, j].T # similarity to all items sims = cosine_similarity(item_vec, R.T).ravel() # remove self similarity sims[j] = -1.0 valid = np.where(sims >= float(min_sim))[0] if valid.size == 0: return pd.DataFrame( {"message": [f"No recommendations found with min_sim ≥ {min_sim}."]} ) top_idx = valid[np.argsort(sims[valid])[::-1][:top_n]] return pd.DataFrame({ "recommended_product_id": product_ids[top_idx], "similarity": sims[top_idx].astype(float) }) # -------------------------------------------------- # Sidebar # -------------------------------------------------- st.sidebar.header("⚙️ Settings") try: R, product_ids, prod_to_idx = load_artifacts() st.sidebar.success("Artifacts loaded successfully.") except Exception as e: st.sidebar.error("Artifacts could not be loaded.") st.error(str(e)) st.stop() st.sidebar.write("**Dataset scope (reduced subset):**") st.sidebar.write(f"- Users: **{R.shape[0]:,}**") st.sidebar.write(f"- Products: **{R.shape[1]:,}**") st.sidebar.write(f"- Interactions: **{R.nnz:,}**") top_n = st.sidebar.slider( "Top-N recommendations", min_value=3, max_value=30, value=10, step=1 ) min_sim = st.sidebar.slider( "Minimum similarity threshold", min_value=0.0, max_value=0.20, value=0.01, step=0.01 ) st.divider() # -------------------------------------------------- # Main UI # -------------------------------------------------- col1, col2 = st.columns([2, 1], gap="large") with col1: st.subheader("🔎 Find similar products") product_id = st.text_input( "Enter a product_id (ASIN)", placeholder="e.g. B00005N5PF" ) if st.button("Recommend", type="primary", use_container_width=True): product_id = product_id.strip() if not product_id: st.warning("Please enter a product_id.") else: with st.spinner("Computing recommendations..."): recs = recommend_sparse( R, product_ids, prod_to_idx, product_id, top_n=top_n, min_sim=min_sim ) if "message" in recs.columns: st.info(recs["message"].iloc[0]) else: st.success(f"Recommendations for **{product_id}**") st.dataframe(recs, use_container_width=True) with col2: st.subheader("🧪 Quick test") st.write("Try a random product_id from the dataset:") if st.button("Pick random product_id", use_container_width=True): st.session_state["random_pid"] = random.choice(product_ids.tolist()) if "random_pid" in st.session_state: st.code(st.session_state["random_pid"]) if st.button("Recommend for random product_id", use_container_width=True): pid = st.session_state["random_pid"] with st.spinner("Computing recommendations..."): recs = recommend_sparse( R, product_ids, prod_to_idx, pid, top_n=top_n, min_sim=min_sim ) if "message" in recs.columns: st.info(recs["message"].iloc[0]) else: st.success(f"Recommendations for **{pid}**") st.dataframe(recs, use_container_width=True) st.divider() st.caption( "Note: This demo uses a reduced subset of the original dataset " "(top 4,000 products and 200,000 most active users). " "Cosine similarity is computed on-the-fly using a sparse matrix." )