138 lines
7.8 KiB
Python
138 lines
7.8 KiB
Python
"""Connect raw daily bars to market context, PIT breadth, features and RS."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
from .config import RelativeStrengthWeights, ResearchSettings
|
|
from .indicators import (breadth_series, equal_weight_index, market_regimes, mcclellan,
|
|
price_features, relative_strength)
|
|
from .setups import candidate_features
|
|
from .universe import PointInTimeUniverse
|
|
|
|
|
|
def _equal_weight_bars(bars_by_symbol: dict[str, pd.DataFrame], closes: pd.DataFrame,
|
|
members_by_date: dict[pd.Timestamp, list[str]], base: float = 100.0) -> pd.DataFrame:
|
|
columns = {field: [] for field in ("open", "high", "low", "close", "volume")}
|
|
level = base
|
|
previous_close = closes.shift(1)
|
|
for date in closes.index:
|
|
members = [symbol for symbol in members_by_date.get(pd.Timestamp(date), []) if symbol in bars_by_symbol]
|
|
valid = [s for s in members if date in bars_by_symbol[s].index and date in previous_close.index
|
|
and pd.notna(previous_close.loc[date, s]) and previous_close.loc[date, s] > 0]
|
|
if not valid:
|
|
daily_open = daily_high = daily_low = daily_close = 0.0
|
|
volume = 0.0
|
|
else:
|
|
fields = {field: [] for field in ("open", "high", "low", "close")}
|
|
volume = 0.0
|
|
for symbol in valid:
|
|
bar = bars_by_symbol[symbol].loc[date]
|
|
previous = float(previous_close.loc[date, symbol])
|
|
for field in fields:
|
|
fields[field].append(float(bar[field]) / previous - 1)
|
|
volume += float(bar.get("volume", 0.0))
|
|
daily_open, daily_high, daily_low, daily_close = (float(np.nanmean(fields[field])) for field in ("open", "high", "low", "close"))
|
|
daily_high = max(daily_high, daily_open, daily_close)
|
|
daily_low = min(daily_low, daily_open, daily_close)
|
|
if columns["close"]:
|
|
opening, high, low, close = (level * (1 + value) for value in (daily_open, daily_high, daily_low, daily_close))
|
|
level = close
|
|
else:
|
|
opening = high = low = close = level
|
|
columns["open"].append(opening)
|
|
columns["high"].append(max(high, opening, close))
|
|
columns["low"].append(min(low, opening, close))
|
|
columns["close"].append(close)
|
|
columns["volume"].append(volume)
|
|
return pd.DataFrame(columns, index=closes.index)
|
|
|
|
|
|
def build_market_context(bars_by_symbol: dict[str, pd.DataFrame], set_bars: pd.DataFrame,
|
|
membership: PointInTimeUniverse | None = None,
|
|
current_members: list[str] | None = None,
|
|
*, accurate: bool = False,
|
|
research: ResearchSettings | None = None) -> tuple[pd.DataFrame, pd.Series, pd.DataFrame]:
|
|
"""Build SET, equal-weight proxy, breadth/MCO/MCSI and deterministic regime."""
|
|
research = research or ResearchSettings()
|
|
if not bars_by_symbol:
|
|
raise ValueError("at least one constituent price series is required")
|
|
dates = set_bars.index
|
|
stock_closes = pd.DataFrame({symbol: frame["close"].reindex(dates) for symbol, frame in bars_by_symbol.items()}, index=dates)
|
|
if accurate:
|
|
if membership is None:
|
|
raise ValueError("accurate mode requires a point-in-time membership file")
|
|
members_by_date = membership.members_by_date(dates)
|
|
elif membership is not None:
|
|
anchor = dates[-1]
|
|
members = membership.members(anchor)
|
|
if not members:
|
|
members = membership.members(max(row.end for row in membership.periods))
|
|
members_by_date = {pd.Timestamp(date): members for date in dates}
|
|
else:
|
|
if not current_members:
|
|
raise ValueError("fast mode requires a supplied constituent snapshot")
|
|
members = [symbol.upper().removesuffix(".BK") for symbol in current_members]
|
|
members_by_date = {pd.Timestamp(date): members for date in dates}
|
|
closes = stock_closes.copy()
|
|
breadth = breadth_series(closes, members_by_date)
|
|
ew_bars = _equal_weight_bars(bars_by_symbol, closes, members_by_date)
|
|
ew_features = price_features(ew_bars, slope_lookback=research.slope_lookback,
|
|
atr_period=research.atr_period, adr_period=research.adr_period)
|
|
ew = ew_features["close"].rename("set100ew_close")
|
|
set_features = price_features(set_bars, slope_lookback=research.slope_lookback,
|
|
atr_period=research.atr_period, adr_period=research.adr_period)
|
|
mco_mcsi = mcclellan(breadth, short_span=research.mco_short_span,
|
|
long_span=research.mco_long_span, z_window=research.mco_z_window)
|
|
context = set_features.join(breadth).join(mco_mcsi)
|
|
context["set100ew_close"] = ew
|
|
context["set100ew_ema21"] = ew_features["ema21_close"]
|
|
context["set100ew_trend_state"] = ew_features["trend_state"]
|
|
context["ew_trend_state"] = ew_features["trend_state"]
|
|
context = market_regimes(context, overbought_extension_atr=research.overbought_extension_atr,
|
|
repair_sigma=research.mco_repair_sigma)
|
|
context.attrs["members_by_date"] = members_by_date
|
|
return context, ew, breadth
|
|
|
|
|
|
def build_feature_panel(bars_by_symbol: dict[str, pd.DataFrame], set_bars: pd.DataFrame,
|
|
market: pd.DataFrame, *, rs_weights: RelativeStrengthWeights | None = None,
|
|
volume_ratio: float = 1.0,
|
|
research: ResearchSettings | None = None) -> dict[str, pd.DataFrame]:
|
|
research = research or ResearchSettings()
|
|
weights = rs_weights or RelativeStrengthWeights()
|
|
close_series = {symbol: frame["close"] for symbol, frame in bars_by_symbol.items()}
|
|
set100ew = market["set100ew_close"]
|
|
set_close = market["close"]
|
|
rs = relative_strength(close_series, set100ew,
|
|
weights={"1m": weights.one_month, "3m": weights.three_month,
|
|
"12m": weights.twelve_month, "52w": weights.high_52w},
|
|
set_benchmark=set_close,
|
|
high_prices={symbol: frame["high"] for symbol, frame in bars_by_symbol.items()},
|
|
members_by_date=market.attrs.get("members_by_date"))
|
|
market_columns = ["regime", "regime_reasons", "new_risk_allowed", "net_advances", "advancing",
|
|
"declining", "unchanged", "mco", "mco_mean", "mco_std", "mco_z", "mcsi",
|
|
"mcsi_10dma", "mcsi_state", "set100ew_close", "set100ew_ema21", "ew_trend_state"]
|
|
context_fields = market[[column for column in market_columns if column in market.columns]]
|
|
output: dict[str, pd.DataFrame] = {}
|
|
for symbol, bars in bars_by_symbol.items():
|
|
features = candidate_features(
|
|
price_features(bars, slope_lookback=research.slope_lookback,
|
|
atr_period=research.atr_period, adr_period=research.adr_period),
|
|
pullback_window=research.pullback_volume_window,
|
|
tightness_window=research.tightness_window,
|
|
volume_ratio=volume_ratio, pivot_left=research.pivot_left_bars,
|
|
pivot_right=research.pivot_right_bars)
|
|
features["symbol"] = symbol
|
|
rs_columns = [f"{symbol}_{suffix}" for suffix in (
|
|
"rs_percentile", "rs_1m", "rs_3m", "rs_12m", "rs_52w",
|
|
"rs_1m_vs_set", "rs_3m_vs_set", "rs_12m_vs_set",
|
|
"rs_1m_vs_set100ew", "rs_3m_vs_set100ew", "rs_12m_vs_set100ew", "52w_proximity_pct")]
|
|
rs_part = rs[[column for column in rs_columns if column in rs.columns]].rename(
|
|
columns={column: column.removeprefix(f"{symbol}_") for column in rs_columns if column in rs.columns})
|
|
features = features.join(rs_part.reindex(features.index))
|
|
features = features.join(context_fields.reindex(features.index))
|
|
output[symbol] = features
|
|
return output
|