f/tests/test_tax.py

"""Unit tests for the after-tax model (tax.py) — synthetic, no data bundle.

Key regression: distributions are RAW per-share dollars, so the account
must hold RAW share units (valued on close prices). The old code valued
units on ADJ (total-return index) prices, which overstates every
distribution — and its tax — by the raw/adj ratio (e.g. a fund that has
paid many distributions: adj 11 vs raw 30 -> 2.7x overcharge).

Run:  .venv/bin/python tests/test_tax.py
"""
from __future__ import annotations

import sys
from pathlib import Path

import pandas as pd

sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import tax  # noqa: E402

PASS, FAIL = 0, 0


def check(name: str, ok: bool) -> None:
    global PASS, FAIL
    PASS += bool(ok)
    FAIL += not ok
    print(("  ok    " if ok else "  FAIL  ") + name)


def main() -> int:
    # One fund, raw prices 30 -> 34, ex-div 5.00 on day 6 (34 -> 29),
    # then 29.5. Account starts at 1.0 = 1/30 share.
    dates = pd.to_datetime(["2024-01-0%d" % i for i in range(1, 8)])
    close = pd.DataFrame({"f": [30.0, 31.0, 32.0, 33.0, 34.0, 29.0, 29.5]},
                         index=dates)
    div = pd.DataFrame({"f": [0, 0, 0, 0, 0, 0.0, 0.0]}, index=dates)
    capg = pd.DataFrame({"f": [0, 0, 0, 0, 0, 5.0, 0.0]}, index=dates)

    r = tax.after_tax_portfolio(close, div, capg, {"f": 1.0}, lt_rate=0.20,
                                st_rate=0.15, div_rate=0.15)
    t5 = dates[5]

    # --- the regression: tax on the distribution is 20% of 5/30 of the
    # account (the distribution as a fraction of the RAW price), i.e.
    # 3.333% — not 5/adj (which the old code implied, ~4% with this
    # adj path and up to 2.7x for high-history funds).
    check("cap-gain tax is 20% of (5/30) of the account",
          abs(r.taxes["capg_tax"][t5] - 0.2 * 5.0 / 30.0) < 1e-12)
    check("no dividend tax", r.taxes["div_tax"].abs().sum() == 0.0)

    # --- reinvestment: the after-tax remainder (5*0.8 of the 1/30 share)
    # is bought at the ex-div close 29, so MV on the event day is
    # (1/30)*(29 + 4) = 33/30. The tax is already inside the (smaller)
    # units — it must NOT also show up in equity as a second deduction.
    mv5 = r.equity[t5] + r.liq_tax[t5]   # no cash component on this day
    check("market value on ex-div day = 33/30 (after-tax reinvested)",
          abs(mv5 - 33.0 / 30.0) < 1e-9)

    # --- liquidation value: price drop (5/30) is exactly offset by the
    # distribution kept, so equity falls by the true tax cost only.
    # Day-5 equity = MV(33/30) - liq_tax(0: basis 1+4/30 > MV, a "loss"
    # under the after-tax basis rule).
    check("equity on ex-div day = 33/30 (tax cost lives in the units)",
          abs(r.equity[t5] - 33.0 / 30.0) < 1e-9)

    # --- pre-event day: plain ST-marked liquidation value.
    t4 = dates[4]
    check("equity day before = MV - 15% ST gain tax",
          abs(r.equity[t4] - (34.0 / 30.0) * (1 - 0.15 * (4.0 / 34.0))) < 1e-9)

    # --- cross-day consistency: equity(5)/equity(4) from the explicit
    # values (day 4 = 34/30 MV less 15% ST gain tax; day 5 = 33/30).
    check("ex-div equity step matches explicit values",
          abs(r.equity[t5] / r.equity[t4]
              - (33.0 / 30.0) / (34.0 / 30.0 - 0.15 * 4.0 / 30.0)) < 1e-9)

    # --- no rebalancing: one lot survives, units grew by the reinvested
    # net amount at the ex-div price.
    check("single lot outstanding", r.lots_outstanding == 1)

    # --- dividend leg taxed at div_rate, cap-gain leg at lt_rate:
    # split a 1.00 distribution 0.4 div / 0.6 capg on day 6.
    div2 = pd.DataFrame({"f": [0, 0, 0, 0, 0, 0.4, 0.0]}, index=dates)
    capg2 = pd.DataFrame({"f": [0, 0, 0, 0, 0, 0.6, 0.0]}, index=dates)
    r2 = tax.after_tax_portfolio(close, div2, capg2, {"f": 1.0}, lt_rate=0.20,
                                 st_rate=0.15, div_rate=0.10)
    check("split distribution taxed by component rate",
          abs(r2.taxes["capg_tax"][t5] - 0.20 * 0.6 / 30.0) < 1e-12
          and abs(r2.taxes["div_tax"][t5] - 0.10 * 0.4 / 30.0) < 1e-12)

    # --- state/local + NIIT: composite rates add to each component
    # (NY/NYC tax cap gains at ordinary rates — the caller passes the
    # composite sl_rate; the model must not preferentiate cap gains).
    r3 = tax.after_tax_portfolio(close, div2, capg2, {"f": 1.0}, lt_rate=0.20,
                                 st_rate=0.15, div_rate=0.10, niit=0.038,
                                 sl_rate=0.14)
    check("capg dist taxed at lt + NIIT + state/local",
          abs(r3.taxes["capg_tax"][t5] - (0.20 + 0.038 + 0.14) * 0.6 / 30.0) < 1e-12)
    check("div taxed at div + NIIT + state/local",
          abs(r3.taxes["div_tax"][t5] - (0.10 + 0.038 + 0.14) * 0.4 / 30.0) < 1e-12)
    # realized-gain leg: two symbols, daily rebalance forces ST sells;
    # every realized dollar is taxed at (st_rate + niit + sl_rate).
    d3 = pd.to_datetime(["2024-01-0%d" % i for i in (1, 2, 3)])
    close3 = pd.DataFrame({"a": [30.0, 34.0, 29.0], "b": [10.0, 10.0, 10.0]},
                          index=d3)
    zero3 = pd.DataFrame(0.0, index=d3, columns=["a", "b"])
    r4 = tax.after_tax_portfolio(close3, zero3, zero3, {"a": 0.5, "b": 0.5},
                                 rebalance="1D", lt_rate=0.20, st_rate=0.15,
                                 div_rate=0.10, niit=0.038, sl_rate=0.14)
    real_tax = float(r4.taxes["realized_tax"].sum())
    net_st = float(r4.realized["st_gain"].sum()) - \
        float(r4.realized["st_loss"].sum())
    check("realized ST gains/losses net-taxed at st + NIIT + state/local",
          float(r4.realized["st_gain"].sum()) > 0 and
          abs(real_tax - net_st * (0.15 + 0.038 + 0.14)) < 1e-9)

    print(f"\n{PASS} passed, {FAIL} failed")
    return 1 if FAIL else 0


if __name__ == "__main__":
    sys.exit(main())