gendesign/site-finder/08_enrich_economics.py

"""Recompute district economics using per-flat (Поквартирные/Лоты) data.

Per-flat is way richer than monthly Сводные:
  - real velocity: registered DDU per month (last 12 mo)
  - real median price: from individual sold lots
  - real average area sold
  - готовность distribution
  - bank diversity (mortgage market attractiveness)
  - sold-out ratio (продано / total in projects with sales started)
  - sales freshness (median days since contract for last 90d)

Replaces values in district_economics with `*_real` columns.
"""
import sqlite3, pathlib, datetime as dt
DB = pathlib.Path(__file__).parent / "analysis.db"

EXTRA = """
ALTER TABLE district_economics ADD COLUMN real_n_lots INTEGER;
ALTER TABLE district_economics ADD COLUMN real_n_sold INTEGER;
ALTER TABLE district_economics ADD COLUMN real_sold_pct REAL;
ALTER TABLE district_economics ADD COLUMN real_median_price_m2 REAL;
ALTER TABLE district_economics ADD COLUMN real_p25_price_m2 REAL;
ALTER TABLE district_economics ADD COLUMN real_p75_price_m2 REAL;
ALTER TABLE district_economics ADD COLUMN real_avg_area_sold REAL;
ALTER TABLE district_economics ADD COLUMN real_velocity_per_month REAL;
ALTER TABLE district_economics ADD COLUMN real_n_banks INTEGER;
ALTER TABLE district_economics ADD COLUMN real_top_bank TEXT;
ALTER TABLE district_economics ADD COLUMN real_top_bank_share REAL;
ALTER TABLE district_economics ADD COLUMN real_avg_readiness_pct REAL;
"""

def safe_alter(conn, sql):
    for stmt in sql.strip().split(";"):
        s = stmt.strip()
        if not s: continue
        try: conn.execute(s)
        except sqlite3.OperationalError as e:
            if "duplicate column" not in str(e): raise

def percentile(vals, p):
    if not vals: return None
    vals = sorted(vals)
    k = (len(vals) - 1) * p
    f = int(k); c = min(f+1, len(vals)-1)
    return vals[f] + (vals[c]-vals[f]) * (k - f)

def main():
    conn = sqlite3.connect(DB)
    safe_alter(conn, EXTRA)
    conn.commit()

    # n_lots, n_sold, prices, areas, banks, readiness — all per district
    rows = conn.execute("""
        SELECT district, status, sold, price_per_m2, area_pd, bank,
               readiness_pct, register_date
        FROM objective_lots
        WHERE district IS NOT NULL AND district!=''
    """).fetchall()
    by_d = {}
    for d, st, sold, price, area, bank, ready, reg in rows:
        by_d.setdefault(d, []).append((st, sold, price, area, bank, ready, reg))

    today = dt.date.today()
    cutoff_12mo = today - dt.timedelta(days=365)

    for d, items in by_d.items():
        n_lots = len(items)
        sold_items = [it for it in items if (it[1] or '').strip().lower() == 'да']
        n_sold = len(sold_items)
        sold_pct = 100.0 * n_sold / n_lots if n_lots else None

        prices = [it[2] for it in sold_items if it[2] and it[2] > 0]
        med = percentile(prices, 0.5) / 1000 if prices else None  # → тыс ₽/м²
        p25 = percentile(prices, 0.25) / 1000 if prices else None
        p75 = percentile(prices, 0.75) / 1000 if prices else None

        areas = [it[3] for it in sold_items if it[3] and it[3] > 0]
        avg_area = sum(areas)/len(areas) if areas else None

        # velocity: registered deals in last 12 mo / 12 / n_corpuses_in_district
        reg_dates = []
        for it in sold_items:
            r = it[6]
            if not r: continue
            try:
                rd = dt.date.fromisoformat(r[:10])
                if rd >= cutoff_12mo: reg_dates.append(rd)
            except: pass
        # Distinct corpuses in district (from per-flat data)
        n_corp = len({(it[0],) for it in items if it[0]})  # crude — but we want corpuses
        n_corp_real = len({(it,) for it in conn.execute(
            "SELECT DISTINCT project, corpus FROM objective_lots WHERE district=?", (d,)).fetchall()}) or 1
        velocity = len(reg_dates) / 12.0 / n_corp_real if reg_dates else 0

        banks = [it[4] for it in items if it[4] and it[4].strip()]
        unique_banks = set(banks)
        top_bank, top_share = None, None
        if banks:
            from collections import Counter
            c = Counter(banks)
            top_bank, top_n = c.most_common(1)[0]
            top_share = top_n / len(banks)

        ready_vals = [it[5] for it in items if it[5] is not None]
        avg_ready = sum(ready_vals)/len(ready_vals) if ready_vals else None

        conn.execute("""UPDATE district_economics SET
            real_n_lots=?, real_n_sold=?, real_sold_pct=?,
            real_median_price_m2=?, real_p25_price_m2=?, real_p75_price_m2=?,
            real_avg_area_sold=?, real_velocity_per_month=?,
            real_n_banks=?, real_top_bank=?, real_top_bank_share=?,
            real_avg_readiness_pct=?
            WHERE district=?""",
            (n_lots, n_sold, sold_pct, med, p25, p75, avg_area, velocity,
             len(unique_banks), top_bank, top_share, avg_ready, d))
    conn.commit()

    print(f"{'район':<22}{'лот':>6}{'прод':>7}{'sold%':>7}{'медцена':>9}{'площ':>6}{'vel':>6}{'банки':>6}{'top_bank':>22}{'%':>5}{'готовн':>7}")
    for r in conn.execute("""SELECT district, real_n_lots, real_n_sold, real_sold_pct,
                                    real_median_price_m2, real_avg_area_sold,
                                    real_velocity_per_month, real_n_banks,
                                    real_top_bank, real_top_bank_share, real_avg_readiness_pct
                             FROM district_economics
                             WHERE real_n_lots>0
                             ORDER BY real_median_price_m2 DESC NULLS LAST""").fetchall():
        d, nl, ns, sp, mp, aa, v, nb, tb, ts, rd = r
        print(f"{d:<22}{nl:>6}{ns:>7}{sp or 0:>6.1f}%{mp or 0:>9.1f}{aa or 0:>6.1f}{v:>6.2f}{nb or 0:>6}{(tb or '—')[:20]:>22}{(ts or 0)*100:>4.0f}%{rd or 0:>6.0f}%")

    conn.close()

if __name__ == "__main__":
    main()