Yuxuan Yan
1caa63faeb
Replace the old signal/strategy/backtest modules with a decoupled
data → alpha → combo pipeline (parquet between phases, .pq extension).
Alphas:
- BaseAlpha + @register_alpha factory/plugin registry; one file per
built-in (reversal, reversal_vol, momentum); external alphas via
--alpha-module. Alphas are z-scored position weights, not predictors.
Data:
- baostock primary / akshare fallback, treated consistently.
- New --universe all (~5000 A-shares via query_all_stock, filtered).
- login-once batch downloader; empty-string OHLCV coerced to NaN.
- Month-partitioned dataset {output_dir}/{universe}/month=YYYY-MM/*.pq
with chunked durability flushes; --data-path is the dataset dir.
CLI logs at INFO by default (--log-level) so progress is visible.
Docs (README, CLAUDE.md) updated incl. pipeline diagram and roadmap
TODOs for portfolio construction / backtest / paper trading.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
86 lines
2.6 KiB
Python
86 lines
2.6 KiB
Python
"""Combine multiple alphas into a single combined weight.
|
||
|
||
Future combination methods can be registered below.
|
||
"""
|
||
|
||
import logging
|
||
from typing import Callable
|
||
|
||
import pandas as pd
|
||
|
||
from pipeline.common.schema import COMBO_COLUMNS
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
|
||
def _equal_weight(alpha_dfs: list[pd.DataFrame]) -> pd.DataFrame:
|
||
"""Equal-weight combination: mean of all alpha weights per (symbol_id, date).
|
||
|
||
If any alpha has NaN for a symbol/date, that alpha is skipped for that row.
|
||
"""
|
||
# Stack all alphas with (symbol_id, date, alpha_name) as key
|
||
combined = pd.concat(alpha_dfs, ignore_index=True)
|
||
# Group by symbol_id + date, take mean of weights
|
||
result = combined.groupby(["symbol_id", "date"])["weight"].mean().reset_index()
|
||
return result
|
||
|
||
|
||
# Registry of combo methods — add new functions + register them here
|
||
COMBO_METHODS: dict[str, Callable] = {
|
||
"equal_weight": _equal_weight,
|
||
}
|
||
|
||
|
||
def combine_alphas(
|
||
alpha_paths: list[str],
|
||
combo_name: str,
|
||
method: str = "equal_weight",
|
||
) -> pd.DataFrame:
|
||
"""Load alphas from parquet, combine, and return combo weights.
|
||
|
||
Args:
|
||
alpha_paths: List of paths to alpha parquet files.
|
||
combo_name: Name identifier for this combo.
|
||
method: Combination method ('equal_weight').
|
||
|
||
Returns:
|
||
DataFrame with COMBO_COLUMNS.
|
||
|
||
Raises:
|
||
ValueError: If method is unknown or alpha grids don't align.
|
||
"""
|
||
if method not in COMBO_METHODS:
|
||
raise ValueError(
|
||
f"Unknown combo method: {method}. Options: {list(COMBO_METHODS)}"
|
||
)
|
||
|
||
alpha_dfs = []
|
||
for path in alpha_paths:
|
||
df = pd.read_parquet(path)
|
||
alpha_dfs.append(df)
|
||
logger.info("Loaded alpha: %s (%d rows)", path, len(df))
|
||
|
||
# Verify alignment: all alphas must share the same (symbol_id, date) pairs
|
||
keys = [set(zip(df["symbol_id"], pd.to_datetime(df["date"]).astype(str))) for df in alpha_dfs]
|
||
common = keys[0]
|
||
for i, k in enumerate(keys[1:], 1):
|
||
if k != common:
|
||
logger.warning("Alpha %d has different (symbol_id, date) grid — intersection used", i)
|
||
common = common.intersection(k)
|
||
|
||
combine_fn = COMBO_METHODS[method]
|
||
result = combine_fn(alpha_dfs)
|
||
result["combo_name"] = combo_name
|
||
result = result[COMBO_COLUMNS]
|
||
result = result.sort_values(["symbol_id", "date"]).reset_index(drop=True)
|
||
|
||
logger.info(
|
||
"Combo '%s': %d symbols × %d dates, weight range [%.4f, %.4f]",
|
||
combo_name,
|
||
result["symbol_id"].nunique(),
|
||
result["date"].nunique(),
|
||
result["weight"].min(),
|
||
result["weight"].max(),
|
||
)
|
||
return result
|