Create app.py

app.py

@@ -0,0 +1,414 @@
+# app.py
+# 🎁 GIfty — Smart Gift Recommender (Embeddings + FAISS)
+# Dataset: ckandemir/amazon-products (Hugging Face)
+# UI: Gradio (English)
+#
+# Works on common Spaces stacks (no RangeSlider; two sliders for budget)
+# Chosen model: sentence-transformers/all-MiniLM-L6-v2 (fast, strong baseline)
+#
+# Tip: First query builds embeddings+FAISS (cached in-memory).
+
+import os, re, random
+from typing import Dict, List, Tuple
+
+import numpy as np
+import pandas as pd
+import gradio as gr
+from datasets import load_dataset
+from sentence_transformers import SentenceTransformer
+import faiss
+
+# ---------------- Config ----------------
+MAX_ROWS = int(os.getenv("MAX_ROWS", "6000"))  # cap to keep build time reasonable on CPU
+TITLE = "# 🎁 GIfty — Smart Gift Recommender\n*Top-3 similar picks + 1 generated idea + personalized message*"
+
+OCCASION_OPTIONS = [
+    "birthday", "anniversary", "valentines", "graduation",
+    "housewarming", "christmas", "hanukkah", "thank_you",
+]
+
+AGE_OPTIONS = {
+    "any": "any",
+    "kid (3–12)": "kids",
+    "teen (13–17)": "teens",
+    "adult (18–64)": "adult",
+    "senior (65+)": "senior",
+}
+
+INTEREST_OPTIONS = [
+    "reading","writing","tech","travel","fitness","cooking","tea","coffee",
+    "games","movies","plants","music","design","stationery","home","experience",
+    "digital","aesthetic","premium","eco","practical","minimalist","social","party",
+    "photography","outdoors","pets","beauty","jewelry"
+]
+
+# Query-expansion dictionary (improves semantic match with catalog wording)
+SYNONYMS = {
+    "music": ["audio", "headphones", "vinyl", "earbuds", "speaker"],
+    "tech": ["electronics", "gadgets", "computer", "smart", "device"],
+    "games": ["board game", "puzzle", "gaming", "toy"],
+    "home": ["home decor", "kitchen", "appliance", "furniture"],
+    "cooking": ["kitchen", "cookware", "chef", "bake"],
+    "fitness": ["sports", "yoga", "run", "workout"],
+    "photography": ["camera", "lens", "tripod"],
+    "travel": ["luggage", "passport", "map", "travel"],
+    "beauty": ["skincare", "makeup", "fragrance", "cosmetic"],
+    "jewelry": ["ring", "necklace", "bracelet"],
+    "coffee": ["espresso", "mug", "grinder", "coffee"],
+    "tea": ["teapot", "infuser", "tea"],
+    "plants": ["garden", "planter", "indoor"],
+    "reading": ["book", "novel", "literature"],
+    "writing": ["notebook", "pen", "planner"],
+    "pets": ["pet", "dog", "cat"],
+    "outdoors": ["camping", "hiking", "outdoor"],
+    "eco": ["sustainable", "recycled", "eco"],
+    "digital": ["online", "voucher"],
+    "experience": ["voucher", "ticket", "workshop"],
+}
+
+# ---------------- Data loading & schema ----------------
+def _to_price_usd(x):
+    s = str(x).strip().replace("$", "").replace(",", "")
+    try:
+        return float(s)
+    except Exception:
+        return np.nan
+
+def _infer_age_from_category(cat: str) -> str:
+    s = (cat or "").lower()
+    if any(k in s for k in ["baby", "toddler", "infant"]): return "kids"
+    if "toys & games" in s or "board games" in s or "toy" in s: return "kids"
+    if any(k in s for k in ["teen", "young adult", "ya"]): return "teens"
+    return "any"
+
+def _infer_occasion_tags(cat: str) -> str:
+    s = (cat or "").lower()
+    tags = set(["birthday"])
+    if any(k in s for k in ["home & kitchen","furniture","home décor","home decor","garden","tools","appliance","cookware","kitchen"]):
+        tags.update(["housewarming","thank_you"])
+    if any(k in s for k in ["beauty","jewelry","watch","fragrance","cosmetic","makeup","skincare"]):
+        tags.update(["valentines","anniversary"])
+    if any(k in s for k in ["toys","board game","puzzle","kids","lego"]):
+        tags.update(["hanukkah","christmas"])
+    if any(k in s for k in ["office","stationery","notebook","pen","planner"]):
+        tags.update(["graduation","thank_you"])
+    if any(k in s for k in ["electronics","camera","audio","headphones","gaming","computer"]):
+        tags.update(["birthday","christmas"])
+    if any(k in s for k in ["book","novel","literature"]):
+        tags.update(["graduation","thank_you"])
+    if any(k in s for k in ["sports","fitness","outdoor","camping","hiking","run","yoga"]):
+        tags.update(["birthday"])
+    return ",".join(sorted(tags))
+
+def map_amazon_to_schema(df_raw: pd.DataFrame) -> pd.DataFrame:
+    cols = {c.lower().strip(): c for c in df_raw.columns}
+    get = lambda key: df_raw.get(cols.get(key, ""), "")
+    out = pd.DataFrame({
+        "name": get("product name"),
+        "short_desc": get("description"),
+        "tags": get("category"),
+        "price_usd": get("selling price").map(_to_price_usd) if "selling price" in cols else np.nan,
+        "age_range": "",
+        "gender_tags": "any",
+        "occasion_tags": "",
+        "persona_fit": get("category"),
+        "image_url": get("image") if "image" in cols else "",
+    })
+    # clean
+    out["name"] = out["name"].astype(str).str.strip().str.slice(0, 120)
+    out["short_desc"] = out["short_desc"].astype(str).str.strip().str.slice(0, 500)
+    out["tags"] = out["tags"].astype(str).str.replace("|", ", ").str.lower()
+    out["persona_fit"] = out["persona_fit"].astype(str).str.lower()
+    # infer occasion & age
+    out["occasion_tags"] = out["tags"].map(_infer_occasion_tags)
+    out["age_range"]    = out["tags"].map(_infer_age_from_category).fillna("any")
+    return out
+
+def build_doc(row: pd.Series) -> str:
+    parts = [
+        str(row.get("name","")),
+        str(row.get("short_desc","")),
+        str(row.get("tags","")),
+        str(row.get("persona_fit","")),
+        str(row.get("occasion_tags","")),
+        str(row.get("age_range","")),
+    ]
+    return " | ".join([p for p in parts if p])
+
+def load_catalog() -> pd.DataFrame:
+    try:
+        ds = load_dataset("ckandemir/amazon-products", split="train")
+        raw = ds.to_pandas()
+    except Exception:
+        # Fallback so the app never crashes if internet is blocked
+        raw = pd.DataFrame({
+            "Product Name": ["Wireless Earbuds", "Coffee Sampler", "Strategy Board Game"],
+            "Description": [
+                "Compact earbuds with noise isolation and long battery life.",
+                "Four single-origin roasts from small roasters.",
+                "Modern eurogame for 2–4 players, 45–60 minutes."
+            ],
+            "Category": ["Electronics | Audio","Grocery | Coffee","Toys & Games | Board Games"],
+            "Selling Price": ["$59.00","$34.00","$39.00"],
+            "Image": ["","",""],
+        })
+    df = map_amazon_to_schema(raw).drop_duplicates(subset=["name","short_desc"])
+    if len(df) > MAX_ROWS:
+        df = df.sample(n=MAX_ROWS, random_state=42).reset_index(drop=True)
+    df["doc"] = df.apply(build_doc, axis=1)
+    return df
+
+CATALOG = load_catalog()
+
+# ---------------- Business filters ----------------
+def _contains_ci(series: pd.Series, needle: str) -> pd.Series:
+    if not needle: return pd.Series(True, index=series.index)
+    pat = re.escape(needle)
+    return series.fillna("").str.contains(pat, case=False, regex=True)
+
+def filter_business(df: pd.DataFrame, budget_min=None, budget_max=None,
+                    occasion: str=None, age_range: str="any") -> pd.DataFrame:
+    m = pd.Series(True, index=df.index)
+    if budget_min is not None:
+        m &= df["price_usd"].fillna(0) >= float(budget_min)
+    if budget_max is not None:
+        m &= df["price_usd"].fillna(1e9) <= float(budget_max)
+    if occasion:
+        m &= _contains_ci(df["occasion_tags"], occasion)
+    if age_range and age_range != "any":
+        m &= (df["age_range"].fillna("any").isin([age_range, "any"]))
+    return df[m]
+
+# ---------------- Embeddings + FAISS ----------------
+class EmbeddingIndex:
+    def __init__(self, docs: List[str], model_id: str):
+        self.model_id = model_id
+        self.model = SentenceTransformer(model_id)
+        embs = self.model.encode(docs, convert_to_numpy=True, normalize_embeddings=True)
+        self.index = faiss.IndexFlatIP(embs.shape[1])  # cosine if normalized
+        self.index.add(embs)
+        self.dim = embs.shape[1]
+
+    def search(self, query: str, topn: int) -> Tuple[np.ndarray, np.ndarray]:
+        qv = self.model.encode([query], convert_to_numpy=True, normalize_embeddings=True)
+        sims, idxs = self.index.search(qv, topn)
+        return sims[0], idxs[0]
+
+# Choose the best all-around model for this app:
+EMBED_MODEL_ID = "sentence-transformers/all-MiniLM-L6-v2"  # fast & good quality
+EMB_INDEX = EmbeddingIndex(CATALOG["doc"].tolist(), EMBED_MODEL_ID)
+
+# ---------------- Query building ----------------
+def expand_with_synonyms(tokens: List[str]) -> List[str]:
+    out = []
+    for t in tokens:
+        t = t.strip().lower()
+        if not t: continue
+        out.append(t)
+        out.extend(SYNONYMS.get(t, []))
+    return out
+
+def profile_to_query(profile: Dict) -> str:
+    """
+    Weighted, doc-aligned query (interests + synonyms) + occasion + age.
+    Repeats interests to give them more weight.
+    """
+    interests = [t.strip().lower() for t in profile.get("interests", []) if t.strip()]
+    expanded = expand_with_synonyms(interests)
+    expanded = expanded + expanded  # weight x2
+    occasion = (profile.get("occasion", "") or "").lower()
+    age = profile.get("age_range", "any")
+    parts = []
+    if expanded: parts.append(", ".join(expanded))
+    if occasion: parts.append(occasion)
+    if age and age != "any": parts.append(age)
+    return " | ".join(parts).strip()
+
+def recommend_topk(profile: Dict, k: int=3) -> pd.DataFrame:
+    query = profile_to_query(profile)
+
+    # Global search on full catalog
+    sims, idxs = EMB_INDEX.search(query, topn=min(max(k*50, k), len(CATALOG)))
+
+    # Filter down to business subset
+    df_f = filter_business(
+        CATALOG,
+        budget_min=profile.get("budget_min"),
+        budget_max=profile.get("budget_max"),
+        occasion=profile.get("occasion"),
+        age_range=profile.get("age_range","any"),
+    )
+    if df_f.empty:
+        df_f = CATALOG
+
+    order = np.argsort(-sims)
+    seen, picks = set(), []
+    for gi in idxs[order]:
+        gi = int(gi)
+        if gi not in df_f.index:
+            continue
+        nm = CATALOG.loc[gi, "name"]
+        if nm in seen:
+            continue
+        seen.add(nm)
+        picks.append(gi)
+        if len(picks) >= k:
+            break
+
+    if not picks:
+        res = df_f.head(k).copy()
+        res["similarity"] = np.nan
+        return res[["name","short_desc","price_usd","occasion_tags","persona_fit","age_range","image_url","similarity"]]
+
+    gi_to_sim = {int(i): float(s) for i, s in zip(idxs, sims)}
+    res = CATALOG.loc[picks].copy()
+    res["similarity"] = [gi_to_sim.get(int(i), np.nan) for i in picks]
+    return res[["name","short_desc","price_usd","occasion_tags","persona_fit","age_range","image_url","similarity"]]
+
+# ---------------- Generative item + message ----------------
+def generate_item(profile: Dict) -> Dict:
+    random.seed(42)  # stable demo
+    interests = profile.get("interests", [])
+    occasion  = profile.get("occasion","birthday")
+    budget    = profile.get("budget_max", profile.get("budget_usd", 50)) or 50
+    age       = profile.get("age_range","any")
+    core = (interests[0] if interests else "hobby").strip() or "hobby"
+    style = random.choice(["personalized","experience","bundle"])
+    if style == "personalized":
+        base_name = f"Custom {core} accessory with initials"
+        base_desc = f"Thoughtful personalized {core} accessory tailored to their taste."
+    elif style == "experience":
+        base_name = f"{core.title()} workshop voucher"
+        base_desc = f"A guided intro session to explore {core} in a fun, hands-on way."
+    else:
+        base_name = f"{core.title()} starter bundle"
+        base_desc = f"A curated set to kickstart their {core} passion."
+    if age == "kids":
+        base_desc += " Suitable for kids with safe, age-appropriate materials."
+    elif age == "teens":
+        base_desc += " Trendy pick that suits young enthusiasts."
+    elif age == "senior":
+        base_desc += " Comfortable and easy to use."
+    price = float(np.clip(float(budget), 10, 300))
+    return {
+        "name": f"{base_name} ({occasion})",
+        "short_desc": base_desc,
+        "price_usd": price,
+        "occasion_tags": occasion,
+        "persona_fit": ", ".join(interests) or "general",
+        "age_range": age,
+        "image_url": ""
+    }
+
+def generate_message(profile: Dict) -> str:
+    name = profile.get("recipient_name","Friend")
+    occasion = profile.get("occasion","birthday")
+    tone = profile.get("tone","warm and friendly")
+    return (f"Dear {name},\n"
+            f"Happy {occasion}! Wishing you health, joy, and wonderful memories. "
+            f"May your goals come true. With {tone}.")
+
+# ---------------- Rendering helpers ----------------
+def md_escape(text: str) -> str:
+    return str(text).replace("|","\\|").replace("*","\\*").replace("_","\\_")
+
+def render_top3_md(df: pd.DataFrame) -> str:
+    if df is None or df.empty:
+        return "_No results found._"
+    lines = ["**Top-3 recommendations:**\n"]
+    for _, r in df.iterrows():
+        name = md_escape(r.get("name",""))
+        desc = md_escape(r.get("short_desc",""))
+        price = r.get("price_usd")
+        sim = r.get("similarity")
+        age = r.get("age_range","any")
+        img = r.get("image_url","")
+        if img:
+            lines.append(f"![ ]({img})")
+        price_str = f"${price:.0f}" if pd.notna(price) else "N/A"
+        sim_str = f"{sim:.3f}" if pd.notna(sim) else "—"
+        lines.append(f"**{name}**  \n{desc}  \nPrice: **{price_str}** · Age: `{age}` · Similarity: `{sim_str}`\n")
+    return "\n".join(lines)
+
+# ---------------- Gradio UI ----------------
+EXAMPLES = [
+    [["tech","music"], "birthday", 20, 60, "Noa", "adult (18–64)", "warm and friendly"],
+    [["home","cooking","practical"], "housewarming", 25, 45, "Daniel", "adult (18–64)", "warm"],
+    [["games","photography"], "birthday", 30, 120, "Omer", "teen (13–17)", "fun"],
+    [["reading","design","aesthetic"], "thank_you", 15, 35, "Maya", "any", "friendly"],
+]
+
+def ui_predict(interests_list: List[str], occasion: str, budget_min: float, budget_max: float,
+               recipient_name: str, age_label: str, tone: str):
+    try:
+        # budget sanity
+        if budget_min is None: budget_min = 20.0
+        if budget_max is None: budget_max = 60.0
+        if budget_min > budget_max:
+            budget_min, budget_max = budget_max, budget_min
+
+        age_range = AGE_OPTIONS.get(age_label, "any")
+        profile = {
+            "recipient_name": recipient_name or "Friend",
+            "interests": interests_list or [],
+            "occasion": occasion or "birthday",
+            "budget_min": float(budget_min),
+            "budget_max": float(budget_max),
+            "budget_usd": float(budget_max),
+            "age_range": age_range,
+            "tone": tone or "warm and friendly",
+        }
+
+        top3 = recommend_topk(profile, k=3)
+        gen  = generate_item(profile)
+        msg  = generate_message(profile)
+
+        top3_md = render_top3_md(top3)
+        gen_md  = f"**{md_escape(gen['name'])}**\n\n{md_escape(gen['short_desc'])}\n\n~${gen['price_usd']:.0f}"
+        return top3_md, gen_md, msg
+    except Exception as e:
+        return f":warning: Error: {e}", "", ""
+
+with gr.Blocks() as demo:
+    gr.Markdown(TITLE)
+
+    with gr.Row():
+        interests = gr.CheckboxGroup(
+            label="Interests (select a few)",
+            choices=INTEREST_OPTIONS,
+            value=["tech","music"],
+            interactive=True
+        )
+    with gr.Row():
+        occasion = gr.Dropdown(label="Occasion", choices=OCCASION_OPTIONS, value="birthday")
+        age = gr.Dropdown(label="Age group", choices=list(AGE_OPTIONS.keys()), value="adult (18–64)")
+
+    # Two sliders (compatible with older Gradio)
+    with gr.Row():
+        budget_min = gr.Slider(label="Min budget (USD)", minimum=5, maximum=500, step=1, value=20)
+        budget_max = gr.Slider(label="Max budget (USD)", minimum=5, maximum=500, step=1, value=60)
+
+    with gr.Row():
+        recipient_name = gr.Textbox(label="Recipient name", value="Noa")
+        tone = gr.Textbox(label="Message tone", value="warm and friendly")
+
+    go = gr.Button("Get GIfty 🎯")
+
+    out_top3 = gr.Markdown(label="Top-3 recommendations")
+    out_gen  = gr.Markdown(label="Generated item")
+    out_msg  = gr.Markdown(label="Personalized message")
+
+    gr.Examples(
+        EXAMPLES,
+        [interests, occasion, budget_min, budget_max, recipient_name, age, tone],
+        label="Quick examples",
+    )
+
+    go.click(
+        ui_predict,
+        [interests, occasion, budget_min, budget_max, recipient_name, age, tone],
+        [out_top3, out_gen, out_msg]
+    )
+
+if __name__ == "__main__":
+    demo.launch()