The seven deadly biases

import numpy as np
import pandas as pd
import qadata

prices = qadata.trending_prices()
rets = prices.pct_change().fillna(0.0)
rng = np.random.default_rng(42)

totals = []
for _ in range(50):                     # 50 strategies with NO edge at all
    coin = pd.Series(rng.integers(0, 2, len(prices)).astype(float),
                     index=prices.index)
    strat = coin.shift(1).fillna(0.0) * rets
    totals.append((1.0 + strat).cumprod().iloc[-1] - 1.0)

totals = pd.Series(totals)
best = totals.idxmax()
print(f"best coin  : #{best}, total {totals[best]:+.2%}")
print(f"median coin: {totals.median():+.2%}")
print(f"worst coin : {totals.min():+.2%}")
print(f"coins beating the honest 20d filter (+27.26%): {(totals > 0.2726).sum()} of 50")

import qadata

panel = qadata.universe()               # 20 assets, 5 years, planted drifts
totals = panel.iloc[-1] / panel.iloc[0] - 1.0

survivors = totals[totals > 0]          # what a survivor-only database keeps
print(f"all 20 assets, mean total return : {totals.mean():+.2%}")
print(f"the {len(survivors)} 'survivors' only        : {survivors.mean():+.2%}")
print(f"the {(totals <= 0).sum()} assets a survivor database forgets:")
print(totals[totals <= 0].round(3).to_string())

import numpy as np
import qadata

prices = qadata.trending_prices()
rets = prices.pct_change().fillna(0.0)

def zscore_full(p):                     # z-score with FULL-SAMPLE mean/std
    z = (p - p.mean()) / p.std()
    return (z > 0).astype(float)

def zscore_rolling(p):                  # same idea, trailing 20d window
    z = (p - p.rolling(20).mean()) / p.rolling(20).std()
    return (z > 0).astype(float)

for name, rule in [("full-sample z", zscore_full), ("rolling z", zscore_rolling)]:
    strat = rule(prices).shift(1).fillna(0.0) * rets   # shift discipline: intact!
    eq = (1.0 + strat).cumprod()
    print(f"{name:14}: total {eq.iloc[-1] - 1:+7.2%}, "
          f"Sharpe {strat.mean() / strat.std() * np.sqrt(252):.2f}")

try:
    qadata.assert_causal(zscore_full, prices)
except AssertionError as e:
    print(f"caught: {e}")
qadata.assert_causal(zscore_rolling, prices)
print("rolling z: causal")