bitcoin-model/tests/test_models.py

import numpy as np
import pandas as pd
import pytest

from btcmodel import data
from btcmodel.evaluate import backtest
from btcmodel.halving import HALVINGS, cycle_position
from btcmodel.models import MODELS, CycleDrift


def synthetic_prices(daily_return, start="2011-01-01", end="2024-11-26", noise=0.0, seed=0):
    """Prices whose daily log return is `daily_return(cycle_day)` plus optional noise."""
    dates = pd.date_range(start, end, freq="D", name="date")
    _, day = cycle_position(dates)
    r = daily_return(day) + noise * np.random.default_rng(seed).standard_normal(len(dates))
    return pd.DataFrame({"close": 100 * np.exp(np.cumsum(r))}, index=dates)


def test_cycle_position():
    index, day = cycle_position(pd.DatetimeIndex(["2009-01-03", "2012-11-27", *HALVINGS]))
    assert list(index) == [0, 0, 1, 2, 3, 4]
    assert list(day) == [0, 1424, 0, 0, 0, 0]
    # A projected halving about four years after the last one starts cycle 5.
    index, _ = cycle_position(pd.DatetimeIndex(["2028-06-01"]))
    assert index[0] == 5


def test_cycle_model_recovers_a_cycle_shaped_drift():
    # Up for the first half of each cycle, down in the second half.
    def shape(day):
        return np.where(day < 700, 0.002, -0.001)

    prices = synthetic_prices(shape)
    drift = CycleDrift(prior_days=0).by_cycle_day(prices)
    assert drift[300] == pytest.approx(0.002, abs=2e-4)
    assert drift[1100] == pytest.approx(-0.001, abs=2e-4)


def test_cycle_model_weights_recent_cycles_more():
    # The same day of the cycle returns less in each later cycle.
    prices = synthetic_prices(lambda day: np.zeros_like(day, dtype=float))
    cycle, _ = cycle_position(prices.index)
    r = 0.004 / 2.0**cycle
    prices["close"] = 100 * np.exp(np.cumsum(r))
    drift = CycleDrift(recency_half_life=0.25).by_cycle_day(prices)
    equal = CycleDrift(recency_half_life=1e9).by_cycle_day(prices)
    latest_complete = 0.004 / 2.0**3
    assert abs(drift[900] - latest_complete) < abs(equal[900] - latest_complete)


@pytest.mark.parametrize("name", list(MODELS))
def test_models_produce_valid_forecasts(name):
    prices = synthetic_prices(lambda day: 0.001 + 0 * day, noise=0.03)
    horizons = np.array([1, 30, 365, 1460])
    f = MODELS[name].forecast(prices, horizons)
    assert f.log_quantiles.shape == (4, 100)
    assert np.all(np.diff(f.log_quantiles, axis=1) >= 0)
    lo, hi = f.interval(0.8)
    assert np.all(np.diff(hi - lo) > 0), "uncertainty should grow with horizon"


def test_backtest_never_shows_models_the_future():
    prices = synthetic_prices(lambda day: 0.001 + 0 * day, noise=0.03)

    class Spy:
        name = "random_walk"

        def forecast(self, history, horizons):
            origin = history.index[-1]
            assert history.index.max() == origin
            assert (origin + pd.Timedelta(days=int(horizons.min()))) > history.index.max()
            return MODELS["random_walk"].forecast(history, horizons)

    scores = backtest([Spy()], prices)
    assert len(scores) > 0
    targets = scores.origin + pd.to_timedelta(scores.horizon, unit="D")
    assert targets.max() <= prices.index[-1]


def test_development_data_stops_at_cutoff():
    prices = data.load_prices(until=data.DEV_CUTOFF)
    assert prices.index[0] == data.DATA_START
    assert prices.index[-1] == data.DEV_CUTOFF