guardrailed-llm-agent — Step 4: Discretizing into Market States (snippet 1)

step_4_discretizing_into_market_states_1.py

# Trend: above/below zero
trend_bucket = np.where(feat['trend'] >= 0, 'TREND_UP', 'TREND_DOWN')

# Volatility: above/below rolling median (adaptive threshold)
vol_med    = feat['vol'].rolling(252, min_periods=60).median()
vol_bucket = np.where(feat['vol'] > vol_med, 'VOL_HIGH', 'VOL_LOW')

# Z-score: three buckets: oversold / neutral / overbought
z = feat['z']
z_bucket = np.where(z <= -Z_EDGE, 'Z_LOW',
           np.where(z >= Z_EDGE,  'Z_HIGH', 'Z_MID'))

# Combine into one interpretable state string
feat['state'] = [
    f'{trend_bucket[i]}|{vol_bucket[i]}|{z_bucket[i]}'
    for i in range(len(feat))
]

# Example states:
# 'TREND_UP|VOL_LOW|Z_HIGH'   → uptrend, calm market, overbought
# 'TREND_DOWN|VOL_HIGH|Z_LOW' → downtrend, stressed market, oversold