wickra/bindings/python/tests/test_new_indicators.py

"""Streaming-vs-batch, shape and reference-value tests for the F1-F12 families.

Every indicator added since the original 25 is exercised here. The central
contract is the same as the rest of the suite: ``batch(...)`` must equal
repeated streaming ``update(...)`` across the whole warmup -> steady-state
transition, and batch shapes must match the input length.
"""

from __future__ import annotations

import math

import numpy as np
import pytest

import wickra as ta


def _eq_nan(a: np.ndarray, b: np.ndarray, tol: float = 1e-9) -> bool:
    """Compare two float arrays treating NaN positions as equal."""
    a = np.asarray(a, dtype=np.float64)
    b = np.asarray(b, dtype=np.float64)
    if a.shape != b.shape:
        return False
    both_nan = np.isnan(a) & np.isnan(b)
    return bool(np.all(np.where(both_nan, 0.0, np.abs(a - b)) <= tol))


@pytest.fixture
def ohlcv() -> tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]:
    """Synthetic high / low / close / volume series, 200 bars."""
    t = np.arange(200, dtype=np.float64)
    close = 100.0 + np.sin(t * 0.15) * 8.0 + np.cos(t * 0.32) * 3.0
    spread = 0.5 + np.abs(np.sin(t * 0.07))
    high = close + spread
    low = close - spread
    volume = 1000.0 + (t % 7) * 50.0
    return high, low, close, volume


# --- Scalar (f64 -> f64) indicators ---------------------------------------

SCALAR = [
    (ta.SMMA, (14,)),
    (ta.TRIMA, (20,)),
    (ta.ZLEMA, (14,)),
    (ta.ALMA, (9, 0.85, 6.0)),
    (ta.McGinleyDynamic, (10,)),
    (ta.FRAMA, (16,)),
    (ta.VIDYA, (14, 9)),
    (ta.JMA, (14, 0.0, 2)),
    (ta.T3, (5, 0.7)),
    (ta.MOM, (10,)),
    (ta.CMO, (14,)),
    (ta.TSI, (25, 13)),
    (ta.PMO, (35, 20)),
    (ta.StochRSI, (14, 14)),
    (ta.PPO, (12, 26)),
    (ta.APO, (12, 26)),
    (ta.CFO, (14,)),
    (ta.ElderImpulse, (13, 12, 26, 9)),
    (ta.STC, (23, 50, 10, 0.5)),
    (ta.DPO, (20,)),
    (ta.Coppock, (14, 11, 10)),
    (ta.StdDev, (20,)),
    (ta.UlcerIndex, (14,)),
    (ta.HistoricalVolatility, (20, 252)),
    (ta.BollingerBandwidth, (20, 2.0)),
    (ta.PercentB, (20, 2.0)),
    (ta.LinearRegression, (14,)),
    (ta.LinRegSlope, (14,)),
    (ta.VerticalHorizontalFilter, (28,)),
    (ta.ZScore, (20,)),
    (ta.LinRegAngle, (14,)),
    (ta.LaguerreRSI, (0.5,)),
    (ta.ConnorsRSI, (3, 2, 100)),
    (ta.RVIVolatility, (10,)),
]


@pytest.mark.parametrize("cls, args", SCALAR, ids=[c.__name__ for c, _ in SCALAR])
def test_scalar_streaming_matches_batch(cls, args, sine_prices):
    batch = cls(*args).batch(sine_prices)
    assert batch.shape == sine_prices.shape
    assert batch.dtype == np.float64

    streamer = cls(*args)
    streamed = []
    for p in sine_prices:
        v = streamer.update(float(p))
        streamed.append(math.nan if v is None else float(v))
    assert _eq_nan(batch, np.array(streamed, dtype=np.float64))


# --- Candle-input, single-output indicators -------------------------------
#
# Each entry is (factory, batch-call). Streaming always feeds the full
# 6-tuple candle; the batch helper takes only the columns it needs.

CANDLE_SCALAR = {
    "VWMA": (lambda: ta.VWMA(20), lambda ind, h, l, c, v: ind.batch(c, v)),
    "RVI": (
        # extract_candle pulls the open price from index 0 of the tuple; the
        # streaming test below already builds candles with open == close, so
        # match that here by passing close as the open column.
        lambda: ta.RVI(10),
        lambda ind, h, l, c, v: ind.batch(c, h, l, c),
    ),
    "Inertia": (
        lambda: ta.Inertia(14, 20),
        lambda ind, h, l, c, v: ind.batch(c, h, l, c),
    ),
    "PGO": (lambda: ta.PGO(14), lambda ind, h, l, c, v: ind.batch(h, l, c)),
    "SMI": (lambda: ta.SMI(5, 3, 3), lambda ind, h, l, c, v: ind.batch(h, l, c)),
    "EVWMA": (lambda: ta.EVWMA(20), lambda ind, h, l, c, v: ind.batch(c, v)),
    "UltimateOscillator": (
        lambda: ta.UltimateOscillator(7, 14, 28),
        lambda ind, h, l, c, v: ind.batch(h, l, c),
    ),
    "AroonOscillator": (
        lambda: ta.AroonOscillator(14),
        lambda ind, h, l, c, v: ind.batch(h, l),
    ),
    "NATR": (lambda: ta.NATR(14), lambda ind, h, l, c, v: ind.batch(h, l, c)),
    "MassIndex": (lambda: ta.MassIndex(9, 25), lambda ind, h, l, c, v: ind.batch(h, l)),
    "ADL": (lambda: ta.ADL(), lambda ind, h, l, c, v: ind.batch(h, l, c, v)),
    "VolumePriceTrend": (
        lambda: ta.VolumePriceTrend(),
        lambda ind, h, l, c, v: ind.batch(c, v),
    ),
    "ChaikinMoneyFlow": (
        lambda: ta.ChaikinMoneyFlow(20),
        lambda ind, h, l, c, v: ind.batch(h, l, c, v),
    ),
    "ChaikinOscillator": (
        lambda: ta.ChaikinOscillator(3, 10),
        lambda ind, h, l, c, v: ind.batch(h, l, c, v),
    ),
    "ForceIndex": (
        lambda: ta.ForceIndex(13),
        lambda ind, h, l, c, v: ind.batch(c, v),
    ),
    "EaseOfMovement": (
        lambda: ta.EaseOfMovement(14),
        lambda ind, h, l, c, v: ind.batch(h, l, v),
    ),
    "AtrTrailingStop": (
        lambda: ta.AtrTrailingStop(14, 3.0),
        lambda ind, h, l, c, v: ind.batch(h, l, c),
    ),
    "TypicalPrice": (
        lambda: ta.TypicalPrice(),
        lambda ind, h, l, c, v: ind.batch(h, l, c),
    ),
    "MedianPrice": (
        lambda: ta.MedianPrice(),
        lambda ind, h, l, c, v: ind.batch(h, l),
    ),
    "WeightedClose": (
        lambda: ta.WeightedClose(),
        lambda ind, h, l, c, v: ind.batch(h, l, c),
    ),
    "AcceleratorOscillator": (
        lambda: ta.AcceleratorOscillator(5, 34, 5),
        lambda ind, h, l, c, v: ind.batch(h, l),
    ),
    "AwesomeOscillatorHistogram": (
        lambda: ta.AwesomeOscillatorHistogram(5, 34, 5),
        lambda ind, h, l, c, v: ind.batch(h, l),
    ),
    "BalanceOfPower": (
        # The streaming 6-tuple feeds open == close, so batch matches with
        # the close column standing in for open.
        lambda: ta.BalanceOfPower(),
        lambda ind, h, l, c, v: ind.batch(c, h, l, c),
    ),
    "ChoppinessIndex": (
        lambda: ta.ChoppinessIndex(14),
        lambda ind, h, l, c, v: ind.batch(h, l, c),
    ),
    "TrueRange": (
        lambda: ta.TrueRange(),
        lambda ind, h, l, c, v: ind.batch(h, l, c),
    ),
    "ChaikinVolatility": (
        lambda: ta.ChaikinVolatility(10, 10),
        lambda ind, h, l, c, v: ind.batch(h, l),
    ),
    "ParkinsonVolatility": (
        lambda: ta.ParkinsonVolatility(20, 252),
        lambda ind, h, l, c, v: ind.batch(h, l),
    ),
    "GarmanKlassVolatility": (
        # The streaming 6-tuple feeds open == close, so batch matches with
        # the close column standing in for open.
        lambda: ta.GarmanKlassVolatility(20, 252),
        lambda ind, h, l, c, v: ind.batch(c, h, l, c),
    ),
    "RogersSatchellVolatility": (
        lambda: ta.RogersSatchellVolatility(20, 252),
        lambda ind, h, l, c, v: ind.batch(c, h, l, c),
    ),
    "YangZhangVolatility": (
        lambda: ta.YangZhangVolatility(20, 252),
        lambda ind, h, l, c, v: ind.batch(c, h, l, c),
    ),
}


@pytest.mark.parametrize("name", list(CANDLE_SCALAR))
def test_candle_scalar_streaming_matches_batch(name, ohlcv):
    high, low, close, volume = ohlcv
    make, batch_call = CANDLE_SCALAR[name]

    batch = batch_call(make(), high, low, close, volume)
    assert batch.shape == close.shape

    streamer = make()
    streamed = []
    for i in range(close.size):
        candle = (
            float(close[i]),
            float(high[i]),
            float(low[i]),
            float(close[i]),
            float(volume[i]),
            i,
        )
        v = streamer.update(candle)
        streamed.append(math.nan if v is None else float(v))
    assert _eq_nan(batch, np.array(streamed, dtype=np.float64)), f"{name} mismatch"


# --- Candle-input, multi-output indicators --------------------------------

MULTI = {
    "Vortex": (lambda: ta.Vortex(14), lambda ind, h, l, c, v: ind.batch(h, l, c)),
    "SuperTrend": (
        lambda: ta.SuperTrend(10, 3.0),
        lambda ind, h, l, c, v: ind.batch(h, l, c),
    ),
    "ChandelierExit": (
        lambda: ta.ChandelierExit(22, 3.0),
        lambda ind, h, l, c, v: ind.batch(h, l, c),
    ),
    "ChandeKrollStop": (
        lambda: ta.ChandeKrollStop(10, 1.0, 9),
        lambda ind, h, l, c, v: ind.batch(h, l, c),
    ),
}

# --- Scalar-input, multi-output indicators --------------------------------
#
# Same shape contract as MULTI (batch returns (n, 2)) but streaming feeds a
# single float instead of a candle tuple.

MULTI_SCALAR_INPUT = {
    "KST": (
        lambda: ta.KST(10, 15, 20, 30, 10, 10, 10, 15, 9),
        lambda ind, c: ind.batch(c),
    ),
}


@pytest.mark.parametrize("name", list(MULTI))
def test_multi_streaming_matches_batch(name, ohlcv):
    high, low, close, volume = ohlcv
    make, batch_call = MULTI[name]

    batch = batch_call(make(), high, low, close, volume)
    assert batch.shape == (close.size, 2)

    streamer = make()
    rows = []
    for i in range(close.size):
        candle = (
            float(close[i]),
            float(high[i]),
            float(low[i]),
            float(close[i]),
            float(volume[i]),
            i,
        )
        v = streamer.update(candle)
        rows.append([math.nan, math.nan] if v is None else list(v))
    assert _eq_nan(batch, np.array(rows, dtype=np.float64)), f"{name} mismatch"


@pytest.mark.parametrize("name", list(MULTI_SCALAR_INPUT))
def test_multi_scalar_streaming_matches_batch(name, ohlcv):
    _, _, close, _ = ohlcv
    make, batch_call = MULTI_SCALAR_INPUT[name]

    batch = batch_call(make(), close)
    assert batch.shape == (close.size, 2)

    streamer = make()
    rows = []
    for p in close:
        v = streamer.update(float(p))
        rows.append([math.nan, math.nan] if v is None else list(v))
    assert _eq_nan(batch, np.array(rows, dtype=np.float64)), f"{name} mismatch"


# --- ZeroLagMACD (scalar input, 3-tuple output: macd / signal / histogram) -


def test_zero_lag_macd_streaming_matches_batch(ohlcv):
    _, _, close, _ = ohlcv
    batch = ta.ZeroLagMACD(12, 26, 9).batch(close)
    assert batch.shape == (close.size, 3)

    streamer = ta.ZeroLagMACD(12, 26, 9)
    rows = []
    for p in close:
        v = streamer.update(float(p))
        rows.append([math.nan, math.nan, math.nan] if v is None else list(v))
    assert _eq_nan(batch, np.array(rows, dtype=np.float64)), "ZeroLagMACD mismatch"


# --- Alligator (3-tuple output) -------------------------------------------


def test_alligator_streaming_matches_batch(ohlcv):
    high, low, _, _ = ohlcv
    alligator = ta.Alligator(13, 8, 5)
    batch = alligator.batch(high, low)
    assert batch.shape == (high.size, 3)

    streamer = ta.Alligator(13, 8, 5)
    rows = []
    for i in range(high.size):
        candle = (float(low[i]), float(high[i]), float(low[i]), float(low[i]), 0.0, i)
        v = streamer.update(candle)
        rows.append([math.nan, math.nan, math.nan] if v is None else list(v))
    assert _eq_nan(batch, np.array(rows, dtype=np.float64)), "Alligator mismatch"


# --- Reference values -----------------------------------------------------


def test_typical_price_reference():
    # (high + low + close) / 3 = (12 + 6 + 9) / 3 = 9.
    assert ta.TypicalPrice().update((9.0, 12.0, 6.0, 9.0, 1.0, 0)) == pytest.approx(9.0)


def test_median_price_reference():
    # (high + low) / 2 = (12 + 8) / 2 = 10.
    assert ta.MedianPrice().update((10.0, 12.0, 8.0, 11.0, 1.0, 0)) == pytest.approx(10.0)


def test_weighted_close_reference():
    # (high + low + 2*close) / 4 = (12 + 8 + 22) / 4 = 10.5.
    assert ta.WeightedClose().update((10.0, 12.0, 8.0, 11.0, 1.0, 0)) == pytest.approx(
        10.5
    )


def test_chaikin_money_flow_reference():
    cmf = ta.ChaikinMoneyFlow(2)
    assert cmf.update((8.0, 10.0, 8.0, 10.0, 100.0, 0)) is None
    assert cmf.update((10.0, 12.0, 8.0, 10.0, 100.0, 1)) == pytest.approx(0.5)


def test_linear_regression_reference():
    out = ta.LinearRegression(3).batch(np.array([1.0, 2.0, 9.0]))
    assert math.isnan(out[0]) and math.isnan(out[1])
    assert out[2] == pytest.approx(8.0)


def test_linreg_slope_reference():
    out = ta.LinRegSlope(3).batch(np.array([1.0, 2.0, 9.0]))
    assert math.isnan(out[0]) and math.isnan(out[1])
    assert out[2] == pytest.approx(4.0)


def test_balance_of_power_reference():
    # (close - open) / (high - low) = (12 - 10) / (14 - 10) = 0.5.
    bop = ta.BalanceOfPower()
    assert bop.update((10.0, 14.0, 10.0, 12.0, 1.0, 0)) == pytest.approx(0.5)


def test_true_range_reference():
    tr = ta.TrueRange()
    assert tr.update((11.0, 12.0, 8.0, 11.0, 1.0, 0)) == pytest.approx(4.0)
    assert tr.update((9.5, 10.0, 9.0, 9.5, 1.0, 1)) == pytest.approx(2.0)


def test_linreg_angle_reference():
    # A series rising by 1 per step has slope 1, and atan(1) = 45 degrees.
    out = ta.LinRegAngle(5).batch(np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0]))
    assert out[4] == pytest.approx(45.0)


def test_z_score_reference():
    # Window [1, 3]: mean 2, population stddev 1; latest 3 -> z = 1.
    out = ta.ZScore(2).batch(np.array([1.0, 3.0]))
    assert math.isnan(out[0])
    assert out[1] == pytest.approx(1.0)


# --- Lifecycle ------------------------------------------------------------


def test_new_indicators_expose_lifecycle():
    instances = [make() for make, _ in CANDLE_SCALAR.values()]
    instances += [make() for make, _ in MULTI.values()]
    instances += [make() for make, _ in MULTI_SCALAR_INPUT.values()]
    instances += [cls(*args) for cls, args in SCALAR]
    instances.append(ta.Alligator(13, 8, 5))
    instances.append(ta.ZeroLagMACD(12, 26, 9))
    for ind in instances:
        assert ind.is_ready() is False
        assert ind.warmup_period() >= 1
        ind.reset()
        assert ind.is_ready() is False