Delete app_new.py

app_new.py

@@ -1,286 +0,0 @@
-
-# app_new.py — RideSearch (brand-correct trims, cross-brand, smart fallbacks, optional photos)
-# Drop into your Hugging Face Space and set as the app file.
-
-import os, glob, urllib.parse
-import numpy as np
-import pandas as pd
-from sklearn.metrics.pairwise import cosine_similarity
-from sklearn.preprocessing import StandardScaler
-import gradio as gr
-
-def load_df():
-    if os.path.exists('RideSearch_dataset.csv'):
-        return pd.read_csv('RideSearch_dataset.csv')
-    parts = sorted(glob.glob('RideSearch_part*_small.csv'))
-    if not parts:
-        raise FileNotFoundError("Upload RideSearch_dataset.csv OR the 10 parts RideSearch_part*_small.csv.")
-    df = pd.concat([pd.read_csv(p) for p in parts], ignore_index=True)
-    df.to_csv('RideSearch_dataset.csv', index=False)
-    return df
-
-DF = load_df()
-
-NUM_COLS = [
-    'horsepower','zero_to_100_kmh_s','seats','cargo_liters','price_usd',
-    'popularity_score','comfort_score','reliability_score','tech_score',
-    'ownership_cost_score','safety_rating'
-]
-
-def ensure_emb():
-    txt_ok = os.path.exists('emb_text.npy')
-    num_ok = os.path.exists('emb_num.npy')
-    if txt_ok and num_ok:
-        return np.load('emb_text.npy'), np.load('emb_num.npy')
-    from sentence_transformers import SentenceTransformer
-    m = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
-    texts = DF['text_record'].astype(str).tolist()
-    Etext = m.encode(texts, batch_size=256, show_progress_bar=True, normalize_embeddings=True)
-    Etext = np.asarray(Etext, dtype='float32'); np.save('emb_text.npy', Etext)
-    X = DF[NUM_COLS].copy()
-    if 'zero_to_100_kmh_s' in X.columns:
-        # lower time is better -> invert so higher is better
-        X['zero_to_100_kmh_s'] = -X['zero_to_100_kmh_s'].astype('float32')
-    Xs = StandardScaler().fit_transform(X.values.astype('float32'))
-    Enum = Xs.astype('float32'); np.save('emb_num.npy', Enum)
-    return Etext, Enum
-
-# ---- trims mapping (loaded from trims_map.json if present) ----
-import json
-TRIM_CHOICES = {}
-TRIM_ALIAS_TO_GENERIC = {}
-if os.path.exists('trims_map.json'):
-    with open('trims_map.json','r',encoding='utf-8') as f:
-        data = json.load(f)
-        TRIM_CHOICES = {tuple(k.split('||')): v['display'] for k, v in data.items()}
-        TRIM_ALIAS_TO_GENERIC = {}
-        for k, v in data.items():
-            for alias, generic in v['alias_to_generic'].items():
-                TRIM_ALIAS_TO_GENERIC[alias] = generic
-else:
-    # minimal fallback so the app still runs
-    TRIM_CHOICES = {("BMW","3 Series"): ["320i","330i","330e","340i","M3"]}
-    TRIM_ALIAS_TO_GENERIC = {"320i":"Base","330i":"Sport","330e":"Sport","340i":"Premium","M3":"Performance"}
-
-def generic_to_display(make, model, generic_trim):
-    if not generic_trim:
-        return ""
-    if (make, model) not in TRIM_CHOICES:
-        return str(generic_trim)
-    for alias in TRIM_CHOICES[(make, model)]:
-        if TRIM_ALIAS_TO_GENERIC.get(alias) == generic_trim:
-            return alias
-    return str(generic_trim)
-
-def models_for(make):
-    if not make:
-        return gr.update(choices=[], value=None)
-    opts = sorted(DF.loc[DF['make'].eq(make), 'model'].dropna().unique().tolist())
-    return gr.update(choices=opts, value=None)
-
-def trim_year(make, model):
-    if make and model and (make, model) in TRIM_CHOICES:
-        trims = TRIM_CHOICES[(make, model)]
-    else:
-        sub = DF
-        if make:  sub = sub[sub['make'] == make]
-        if model: sub = sub[sub['model'] == model]
-        trims = sorted(sub['trim'].astype(str).dropna().unique().tolist())[:20]
-    if make and model:
-        years = sorted(
-            DF.loc[(DF['make'].eq(make)) & (DF['model'].eq(model)), 'year']
-              .dropna().astype(int).unique().tolist()
-        )
-    else:
-        years = []
-    return trims, years
-
-def on_model_change(make, model):
-    trims, years = trim_year(make, model)
-    return gr.update(choices=trims, value=None), gr.update(choices=years, value=None)
-
-def apply_filters(df, body, fuel, y_min, y_max, p_min, p_max, safety, reliab):
-    out = df.copy()
-    if body != 'Any': out = out[out['body_type'] == body]
-    if fuel != 'Any': out = out[out['fuel'] == fuel]
-    out = out[(out['year'] >= y_min) & (out['year'] <= y_max)]
-    out = out[(out['price_usd'] >= p_min) & (out['price_usd'] <= p_max)]
-    out = out[(out['safety_rating'] >= safety) & (out['reliability_score'] >= reliab)]
-    return out
-
-def placeholder_svg_data_uri(title):
-    svg = f\"\"\"<svg xmlns='http://www.w3.org/2000/svg' width='480' height='320'>
-      <rect width='100%' height='100%' fill='#e8eef7'/>
-      <text x='50%' y='50%' dominant-baseline='middle' text-anchor='middle'
-            font-family='Arial' font-size='26' fill='#223'>
-        {title}
-      </text>
-    </svg>\"\"\"
-    return "data:image/svg+xml;utf8," + urllib.parse.quote(svg)
-
-def build_gallery_html(df_rows):
-    cards = []
-    for _, r in df_rows.iterrows():
-        label = f"{r['make']} {r['model']} {generic_to_display(r['make'], r['model'], r['trim'])}"
-        img_src = ""
-        if 'image_url' in r and isinstance(r['image_url'], str) and r['image_url'].strip():
-            img_src = r['image_url'].strip()
-        else:
-            img_src = placeholder_svg_data_uri(f"{r['make']} {r['model']}")
-        cards.append(f\"\"\"
-        <div style="width:240px;margin:6px;border:1px solid #ddd;border-radius:12px;overflow:hidden;background:#fff;">
-          <img src="{img_src}" style="width:240px;height:160px;object-fit:cover;display:block" />
-          <div style="padding:8px 10px;font:14px/1.3 Arial,sans-serif;color:#111">{label}</div>
-        </div>
-        \"\"\")
-    return f"<div style='display:flex;flex-wrap:wrap'>{''.join(cards)}</div>"
-
-def find_anchor(make, model, trim_display, year):
-    # Map display trim to dataset generic using alias mapping if present
-    def norm(make, model, t):
-        if not t: return None
-        # if the alias exists globally, use its generic
-        return TRIM_ALIAS_TO_GENERIC.get(t, t)
-
-    trim_generic = norm(make, model, trim_display)
-
-    sub = DF.copy()
-    if make:  sub = sub[sub['make'] == make]
-    if model: sub = sub[sub['model'] == model]
-
-    def pick(df_):
-        if df_.empty: return None
-        return df_.sort_values('popularity_score', ascending=False).iloc[0]
-
-    exact = sub.copy()
-    if trim_generic: exact = exact[exact['trim'] == trim_generic]
-    if year:         exact = exact[exact['year'] == year]
-    if not exact.empty:
-        return pick(exact)
-
-    if year:
-        y_only = sub[sub['year'] == year]
-        if not y_only.empty: return pick(y_only)
-
-    if trim_generic:
-        t_only = sub[sub['trim'] == trim_generic]
-        if not t_only.empty: return pick(t_only)
-
-    return pick(sub)
-
-def recommend(make, model, trim_display, year, topk, alpha,
-              body, fuel, y_min, y_max, p_min, p_max, safety, reliab,
-              cross_brand_only=True, exclude_same_model=True):
-
-    a = find_anchor(make, model, trim_display, year)
-    if a is None:
-        return "No match for that combo.", None, "", None
-
-    pool = DF.copy()
-    if cross_brand_only:
-        pool = pool[pool['make'] != a['make']]
-    if exclude_same_model:
-        pool = pool[~((pool['make'] == a['make']) & (pool['model'] == a['model']))]
-
-    pool = apply_filters(pool, body, fuel, int(y_min), int(y_max), int(p_min), int(p_max), int(safety), int(reliab))
-    if pool.empty:
-        return "No cars after filters. Try widening year/price/safety.", None, "", None
-
-    Etext, Enum = ensure_emb()
-    idx_anchor = int(a.name)
-    cand_idx = pool.index.values
-
-    st = cosine_similarity(Etext[idx_anchor:idx_anchor+1], Etext[cand_idx])[0]
-    sn = cosine_similarity(Enum[idx_anchor:idx_anchor+1],  Enum[cand_idx])[0]
-    s = float(alpha)*st + (1-float(alpha))*sn
-
-    order = np.argsort(-s)
-    seen = set(); chosen = []
-    for j in order:
-        r = DF.loc[cand_idx[j]]
-        key = (r['make'], r['model'])
-        if key in seen: continue  # enforce cross-brand & unique model
-        seen.add(key)
-        chosen.append(cand_idx[j])
-        if len(chosen) >= int(topk): break
-
-    if not chosen:
-        return "No recommendations found after constraints.", None, "", None
-
-    sel = DF.loc[chosen].copy()
-    sel['trim_display'] = sel.apply(lambda r: generic_to_display(r['make'], r['model'], r['trim']), axis=1)
-
-    sim_lookup = {cand_idx[j]: round(float(s[j])*100, 1) for j in order}
-    sel['similarity_%'] = sel.index.map(lambda k: sim_lookup.get(k, 0.0))
-
-    cols = ['name','make','model','trim_display','year','body_type','fuel','engine_type',
-            'price_usd','horsepower','zero_to_100_kmh_s','popularity_score','comfort_score',
-            'reliability_score','tech_score','ownership_cost_score','safety_rating','similarity_%']
-
-    anchor_text = (f"**{a['make']} {a['model']} {generic_to_display(a['make'], a['model'], a['trim'])} "
-                   f"{int(a['year'])}**  \\n"
-                   f"Body: {a['body_type']} • Fuel: {a['fuel']} • Engine: {a['engine_type']}  \\n"
-                   f"HP: {int(a['horsepower'])} • 0–100: {a['zero_to_100_kmh_s']}s • Price: ${int(a['price_usd']):,}  \\n"
-                   f"Popularity {int(a['popularity_score'])}/10 • Comfort {int(a['comfort_score'])}/10 • "
-                   f"Reliability {int(a['reliability_score'])}/100 • Safety {int(a['safety_rating'])}★")
-
-    note = (f"α = {float(alpha):.2f} (text ↔ numeric) • Cross-brand only = {cross_brand_only} "
-            f"• Exclude same model = {exclude_same_model}")
-
-    gallery = build_gallery_html(sel)
-    return anchor_text, sel[cols], note, gallery
-
-def build_ui():
-    y_lo, y_hi = int(DF['year'].min()), int(DF['year'].max())
-    p_lo, p_hi = int(DF['price_usd'].min()), int(DF['price_usd'].max())
-
-    with gr.Blocks() as demo:
-        gr.Markdown("# RideSearch — cross-brand recommendations with real trims")
-
-        with gr.Tab("Pick & Recommend"):
-            with gr.Row():
-                mk = gr.Dropdown(sorted(DF['make'].dropna().unique().tolist()), label="Make", value=None)
-                md = gr.Dropdown([], label="Model", value=None)
-                tr = gr.Dropdown([], label="Trim (optional)", value=None)
-                yr = gr.Dropdown([], label="Year (optional)", value=None)
-            mk.change(models_for, mk, md)
-            md.change(lambda a,b: on_model_change(a,b), [mk, md], [tr, yr])
-
-            with gr.Row():
-                body = gr.Dropdown(['Any'] + sorted(DF['body_type'].dropna().unique().tolist()), value='Any', label='Body')
-                fuel = gr.Dropdown(['Any'] + sorted(DF['fuel'].dropna().unique().tolist()), value='Any', label='Fuel')
-            with gr.Row():
-                y_min = gr.Slider(y_lo, y_hi, value=y_lo, step=1, label='Year min')
-                y_max = gr.Slider(y_lo, y_hi, value=y_hi, step=1, label='Year max')
-            with gr.Row():
-                p_min = gr.Slider(p_lo, p_hi, value=p_lo, step=500, label='Price min (USD)')
-                p_max = gr.Slider(p_lo, p_hi, value=min(p_hi, 80000), step=500, label='Price max (USD)')
-            with gr.Row():
-                safety = gr.Slider(3, 5, value=4, step=1, label='Min Safety ★')
-                reliab = gr.Slider(55, 99, value=70, step=1, label='Min Reliability')
-            with gr.Row():
-                topk = gr.Slider(1, 10, value=5, step=1, label='Recommendations')
-                alpha = gr.Slider(0, 1, value=0.7, step=0.05, label='α — Text vs Numeric')
-            with gr.Row():
-                cross = gr.Checkbox(label="Cross-brand only", value=True)
-                xmodel = gr.Checkbox(label="Exclude same model family", value=True)
-
-            go = gr.Button("Recommend")
-            anchor_md = gr.Markdown()
-            table = gr.Dataframe(interactive=False)
-            note = gr.Markdown()
-            gallery = gr.HTML()
-
-            go.click(
-                recommend,
-                [mk, md, tr, yr, topk, alpha, body, fuel, y_min, y_max, p_min, p_max, safety, reliab, cross, xmodel],
-                [anchor_md, table, note, gallery]
-            )
-        gr.Markdown("Tip: Add an 'image_url' column in the CSV for real photos.")
-
-    return demo
-
-demo = build_ui()
-
-if __name__ == "__main__":
-    demo.queue().launch(server_name="0.0.0.0", server_port=7860)