sam
cfc27a38de
Replace the 2024 model (model.py, ~2000 lines) with the btcmodel package, the baseline for future work: - Forecasts are quantiles of log price at each horizon, scored with CRPS in a walk-forward backtest (origins every 30 days from 2014, horizons 1 month to 4 years). Skill is relative to a zero-drift random walk, with circular block-bootstrap intervals and a count of independent windows. - Development data stops at 2024-11-26, the last day the 2024 model saw. Later outcomes are a holdout, scored only by `backtest --holdout`. - Models: random_walk, drift_rw, and cycle (the 2024 model's cycle-position drift, now kernel-smoothed and recency-weighted). On development data nothing beats the random walk with confidence; cycle loses at every horizon. - Prices: the Investing.com archive moves to data/ (cut at 2024-11-26; its last row was intraday) and is extended with Coinbase daily closes by `update`. Also: Nix flake dev shell (Python 3.13, pandas 3), ruff in place of black, pytest suite, and a rewritten README. NOTES.md is removed as inaccurate, and poetry is dropped.
48 lines
1.5 KiB
Python
48 lines
1.5 KiB
Python
"""Reference forecasts every other model has to beat."""
|
|
|
|
from dataclasses import dataclass
|
|
from typing import ClassVar
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
from ..data import log_returns
|
|
from ..forecast import Forecast
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class RandomWalk:
|
|
"""
|
|
Zero-drift random walk in log price: "it stays about here, give or take".
|
|
|
|
Volatility is the trailing standard deviation of daily log returns.
|
|
"""
|
|
|
|
name: ClassVar[str] = "random_walk"
|
|
vol_window: int = 365
|
|
|
|
def forecast(self, history: pd.DataFrame, horizons: np.ndarray) -> Forecast:
|
|
sigma = log_returns(history).iloc[-self.vol_window :].std()
|
|
mean = np.log(history["close"].iloc[-1])
|
|
return Forecast.normal(history.index[-1], horizons, mean, sigma * np.sqrt(horizons))
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class DriftRandomWalk:
|
|
"""
|
|
Random walk whose drift is the mean daily log return over the trailing
|
|
`drift_window` days (one halving cycle by default): "it keeps doing what it
|
|
did last cycle".
|
|
"""
|
|
|
|
name: ClassVar[str] = "drift_rw"
|
|
drift_window: int = 1460
|
|
vol_window: int = 365
|
|
|
|
def forecast(self, history: pd.DataFrame, horizons: np.ndarray) -> Forecast:
|
|
returns = log_returns(history)
|
|
mu = returns.iloc[-self.drift_window :].mean()
|
|
sigma = returns.iloc[-self.vol_window :].std()
|
|
mean = np.log(history["close"].iloc[-1]) + mu * horizons
|
|
return Forecast.normal(history.index[-1], horizons, mean, sigma * np.sqrt(horizons))
|