refactor(factorminer): 禁用 npz 信号缓存并将库 I/O 对接本地 DSL
- 为 Factor 数据类新增 metadata 字段，用于标记未实现算子（unsupported） - save_library 废弃 save_signals 参数，内部强制忽略，仅持久化 JSON 元数据，不再写入 .npz - load_library 删除 .npz 恢复逻辑；加载时自动将 # TODO 公式的 unsupported 标记设为 True - import_from_paper() 直接基于已本地化的 PAPER_FACTORS 构建库，并同步标记 TODO 公式 - 新增 tests/test_factorminer_library_io.py，覆盖序列化、加载及 paper factors 导入
This commit is contained in:
@@ -39,6 +39,7 @@ class Factor:
|
||||
signals: Optional[np.ndarray] = field(default=None, repr=False) # (M, T)
|
||||
research_metrics: dict = field(default_factory=dict)
|
||||
provenance: dict = field(default_factory=dict)
|
||||
metadata: dict = field(default_factory=dict)
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
if not self.admission_date:
|
||||
@@ -59,6 +60,7 @@ class Factor:
|
||||
"admission_date": self.admission_date,
|
||||
"research_metrics": self.research_metrics,
|
||||
"provenance": self.provenance,
|
||||
"metadata": self.metadata,
|
||||
}
|
||||
|
||||
@classmethod
|
||||
@@ -77,6 +79,7 @@ class Factor:
|
||||
admission_date=d.get("admission_date", ""),
|
||||
research_metrics=d.get("research_metrics", {}),
|
||||
provenance=d.get("provenance", {}),
|
||||
metadata=d.get("metadata", {}),
|
||||
)
|
||||
|
||||
|
||||
@@ -172,7 +175,7 @@ class FactorLibrary:
|
||||
# Pearson on ranks == Spearman
|
||||
ra_c = ra - ra.mean()
|
||||
rb_c = rb - rb.mean()
|
||||
denom = np.sqrt((ra_c ** 2).sum() * (rb_c ** 2).sum())
|
||||
denom = np.sqrt((ra_c**2).sum() * (rb_c**2).sum())
|
||||
if denom < 1e-12:
|
||||
continue
|
||||
corr_sum += abs((ra_c * rb_c).sum() / denom)
|
||||
@@ -206,9 +209,7 @@ class FactorLibrary:
|
||||
(admitted, reason) : Tuple[bool, str]
|
||||
"""
|
||||
if candidate_ic < self.ic_threshold:
|
||||
return False, (
|
||||
f"IC {candidate_ic:.4f} below threshold {self.ic_threshold}"
|
||||
)
|
||||
return False, (f"IC {candidate_ic:.4f} below threshold {self.ic_threshold}")
|
||||
|
||||
if self.size == 0:
|
||||
return True, "First factor in library"
|
||||
@@ -221,9 +222,7 @@ class FactorLibrary:
|
||||
f"{self.correlation_threshold} with existing library factor"
|
||||
)
|
||||
|
||||
return True, (
|
||||
f"Admitted: IC={candidate_ic:.4f}, max_corr={max_corr:.4f}"
|
||||
)
|
||||
return True, (f"Admitted: IC={candidate_ic:.4f}, max_corr={max_corr:.4f}")
|
||||
|
||||
def check_replacement(
|
||||
self,
|
||||
@@ -258,8 +257,10 @@ class FactorLibrary:
|
||||
(should_replace, factor_to_replace_id, reason) : Tuple[bool, Optional[int], str]
|
||||
"""
|
||||
if candidate_ic < ic_min:
|
||||
return False, None, (
|
||||
f"IC {candidate_ic:.4f} below replacement floor {ic_min}"
|
||||
return (
|
||||
False,
|
||||
None,
|
||||
(f"IC {candidate_ic:.4f} below replacement floor {ic_min}"),
|
||||
)
|
||||
|
||||
if self.size == 0:
|
||||
@@ -277,21 +278,33 @@ class FactorLibrary:
|
||||
correlated_factors.append((fid, corr, factor.ic_mean))
|
||||
|
||||
if len(correlated_factors) != 1:
|
||||
return False, None, (
|
||||
return (
|
||||
False,
|
||||
None,
|
||||
(
|
||||
f"Found {len(correlated_factors)} correlated factors "
|
||||
f"(need exactly 1 for replacement)"
|
||||
),
|
||||
)
|
||||
|
||||
fid, corr, existing_ic = correlated_factors[0]
|
||||
if candidate_ic < ic_ratio * existing_ic:
|
||||
return False, None, (
|
||||
return (
|
||||
False,
|
||||
None,
|
||||
(
|
||||
f"IC {candidate_ic:.4f} < {ic_ratio} * {existing_ic:.4f} = "
|
||||
f"{ic_ratio * existing_ic:.4f}"
|
||||
),
|
||||
)
|
||||
|
||||
return True, fid, (
|
||||
return (
|
||||
True,
|
||||
fid,
|
||||
(
|
||||
f"Replace factor {fid}: candidate IC {candidate_ic:.4f} > "
|
||||
f"{ic_ratio} * {existing_ic:.4f}, corr={corr:.4f}"
|
||||
),
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
@@ -321,8 +334,11 @@ class FactorLibrary:
|
||||
|
||||
logger.info(
|
||||
"Admitted factor %d '%s' (IC=%.4f, max_corr=%.4f, category=%s)",
|
||||
factor.id, factor.name, factor.ic_mean,
|
||||
factor.max_correlation, factor.category,
|
||||
factor.id,
|
||||
factor.name,
|
||||
factor.ic_mean,
|
||||
factor.max_correlation,
|
||||
factor.category,
|
||||
)
|
||||
return factor.id
|
||||
|
||||
@@ -360,7 +376,10 @@ class FactorLibrary:
|
||||
|
||||
logger.info(
|
||||
"Replaced factor %d with %d '%s' (IC=%.4f)",
|
||||
old_id, new_factor.id, new_factor.name, new_factor.ic_mean,
|
||||
old_id,
|
||||
new_factor.id,
|
||||
new_factor.name,
|
||||
new_factor.ic_mean,
|
||||
)
|
||||
|
||||
def remove_factor(self, factor_id: int) -> None:
|
||||
@@ -381,9 +400,7 @@ class FactorLibrary:
|
||||
# Correlation matrix management
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _max_correlation_with_library(
|
||||
self, candidate_signals: np.ndarray
|
||||
) -> float:
|
||||
def _max_correlation_with_library(self, candidate_signals: np.ndarray) -> float:
|
||||
"""Compute max |rho| between candidate and all library factors."""
|
||||
max_corr = 0.0
|
||||
for factor in self.factors.values():
|
||||
@@ -453,9 +470,7 @@ class FactorLibrary:
|
||||
self.correlation_matrix[idx, other_idx] = 0.0
|
||||
self.correlation_matrix[other_idx, idx] = 0.0
|
||||
continue
|
||||
corr = self._compute_correlation_vectorized(
|
||||
factor.signals, other.signals
|
||||
)
|
||||
corr = self._compute_correlation_vectorized(factor.signals, other.signals)
|
||||
self.correlation_matrix[idx, other_idx] = corr
|
||||
self.correlation_matrix[other_idx, idx] = corr
|
||||
|
||||
@@ -509,10 +524,7 @@ class FactorLibrary:
|
||||
|
||||
def get_factors_by_category(self, category: str) -> List[Factor]:
|
||||
"""Return all factors matching a given category."""
|
||||
return [
|
||||
f for f in self.factors.values()
|
||||
if f.category == category
|
||||
]
|
||||
return [f for f in self.factors.values() if f.category == category]
|
||||
|
||||
def get_diagnostics(self) -> dict:
|
||||
"""Library diagnostics: avg |rho|, max tail correlations, per-category counts, saturation.
|
||||
@@ -539,8 +551,7 @@ class FactorLibrary:
|
||||
|
||||
diag["category_counts"] = dict(cat_counts)
|
||||
diag["category_avg_ic"] = {
|
||||
cat: cat_ic_sums[cat] / cat_counts[cat]
|
||||
for cat in cat_counts
|
||||
cat: cat_ic_sums[cat] / cat_counts[cat] for cat in cat_counts
|
||||
}
|
||||
|
||||
# Correlation statistics
|
||||
@@ -575,9 +586,7 @@ class FactorLibrary:
|
||||
Returns a lightweight dictionary suitable for inclusion in LLM prompts
|
||||
or memory store entries.
|
||||
"""
|
||||
factors_sorted = sorted(
|
||||
self.factors.values(), key=lambda f: f.id, reverse=True
|
||||
)
|
||||
factors_sorted = sorted(self.factors.values(), key=lambda f: f.id, reverse=True)
|
||||
recent = factors_sorted[:5] # Last 5 admissions
|
||||
|
||||
categories = defaultdict(int)
|
||||
|
||||
@@ -23,26 +23,22 @@ logger = logging.getLogger(__name__)
|
||||
# Save / Load
|
||||
# ======================================================================
|
||||
|
||||
|
||||
def save_library(
|
||||
library: FactorLibrary,
|
||||
path: Union[str, Path],
|
||||
save_signals: bool = True,
|
||||
) -> None:
|
||||
"""Save a FactorLibrary to disk.
|
||||
|
||||
Creates two files:
|
||||
- ``<path>.json`` -- factor metadata and library configuration
|
||||
- ``<path>_signals.npz`` -- binary signal cache (if save_signals=True
|
||||
and any factors have signals)
|
||||
"""Save a FactorLibrary to disk (仅保存 JSON 元数据).
|
||||
|
||||
Parameters
|
||||
----------
|
||||
library : FactorLibrary
|
||||
path : str or Path
|
||||
Base path (without extension). E.g. ``"output/my_library"`` produces
|
||||
``output/my_library.json`` and ``output/my_library_signals.npz``.
|
||||
``output/my_library.json``.
|
||||
save_signals : bool
|
||||
Whether to write the binary signal cache.
|
||||
已废弃，始终忽略，不再写入 .npz 信号缓存。
|
||||
"""
|
||||
path = Path(path)
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
@@ -63,20 +59,10 @@ def save_library(
|
||||
json.dump(meta, fp, indent=2)
|
||||
logger.info("Saved library metadata to %s (%d factors)", json_path, library.size)
|
||||
|
||||
# -- Binary signal cache --
|
||||
# -- Binary signal cache (已禁用) --
|
||||
print("[library_io] 信号缓存已禁用，仅保存 JSON 元数据")
|
||||
if save_signals:
|
||||
signal_arrays: Dict[str, np.ndarray] = {}
|
||||
for f in library.list_factors():
|
||||
if f.signals is not None:
|
||||
signal_arrays[f"factor_{f.id}"] = f.signals
|
||||
|
||||
if signal_arrays:
|
||||
npz_path = Path(str(path) + "_signals.npz")
|
||||
np.savez_compressed(npz_path, **signal_arrays)
|
||||
logger.info(
|
||||
"Saved signal cache to %s (%d arrays)",
|
||||
npz_path, len(signal_arrays),
|
||||
)
|
||||
logger.info("save_signals 参数已废弃，信号缓存不再写入")
|
||||
|
||||
|
||||
def load_library(path: Union[str, Path]) -> FactorLibrary:
|
||||
@@ -85,8 +71,7 @@ def load_library(path: Union[str, Path]) -> FactorLibrary:
|
||||
Parameters
|
||||
----------
|
||||
path : str or Path
|
||||
Base path (without extension). Will look for ``<path>.json`` and
|
||||
optionally ``<path>_signals.npz``.
|
||||
Base path (without extension). Will look for ``<path>.json``.
|
||||
|
||||
Returns
|
||||
-------
|
||||
@@ -107,6 +92,8 @@ def load_library(path: Union[str, Path]) -> FactorLibrary:
|
||||
# Restore factors
|
||||
for fd in meta.get("factors", []):
|
||||
factor = Factor.from_dict(fd)
|
||||
if factor.formula.strip().startswith("# TODO"):
|
||||
factor.metadata["unsupported"] = True
|
||||
library.factors[factor.id] = factor
|
||||
|
||||
# Restore correlation matrix
|
||||
@@ -117,24 +104,9 @@ def load_library(path: Union[str, Path]) -> FactorLibrary:
|
||||
|
||||
# Restore id-to-index mapping
|
||||
if "id_to_index" in meta:
|
||||
library._id_to_index = {
|
||||
int(k): v for k, v in meta["id_to_index"].items()
|
||||
}
|
||||
library._id_to_index = {int(k): v for k, v in meta["id_to_index"].items()}
|
||||
|
||||
# Load signal cache if present
|
||||
npz_path = Path(str(path) + "_signals.npz")
|
||||
if npz_path.exists():
|
||||
data = np.load(npz_path)
|
||||
for f in library.factors.values():
|
||||
key = f"factor_{f.id}"
|
||||
if key in data:
|
||||
f.signals = data[key]
|
||||
data.close()
|
||||
logger.info("Loaded signal cache from %s", npz_path)
|
||||
|
||||
logger.info(
|
||||
"Loaded library from %s (%d factors)", json_path, library.size
|
||||
)
|
||||
logger.info("Loaded library from %s (%d factors)", json_path, library.size)
|
||||
return library
|
||||
|
||||
|
||||
@@ -142,6 +114,7 @@ def load_library(path: Union[str, Path]) -> FactorLibrary:
|
||||
# Export utilities
|
||||
# ======================================================================
|
||||
|
||||
|
||||
def export_csv(library: FactorLibrary, path: Union[str, Path]) -> None:
|
||||
"""Export the factor table to CSV.
|
||||
|
||||
@@ -152,15 +125,24 @@ def export_csv(library: FactorLibrary, path: Union[str, Path]) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
fieldnames = [
|
||||
"ID", "Name", "Formula", "Category", "IC_Mean", "ICIR",
|
||||
"IC_Win_Rate", "Max_Correlation", "Batch", "Admission_Date",
|
||||
"ID",
|
||||
"Name",
|
||||
"Formula",
|
||||
"Category",
|
||||
"IC_Mean",
|
||||
"ICIR",
|
||||
"IC_Win_Rate",
|
||||
"Max_Correlation",
|
||||
"Batch",
|
||||
"Admission_Date",
|
||||
]
|
||||
|
||||
with open(path, "w", newline="") as fp:
|
||||
writer = csv.DictWriter(fp, fieldnames=fieldnames)
|
||||
writer.writeheader()
|
||||
for f in library.list_factors():
|
||||
writer.writerow({
|
||||
writer.writerow(
|
||||
{
|
||||
"ID": f.id,
|
||||
"Name": f.name,
|
||||
"Formula": f.formula,
|
||||
@@ -171,7 +153,8 @@ def export_csv(library: FactorLibrary, path: Union[str, Path]) -> None:
|
||||
"Max_Correlation": f"{f.max_correlation:.4f}",
|
||||
"Batch": f.batch_number,
|
||||
"Admission_Date": f.admission_date,
|
||||
})
|
||||
}
|
||||
)
|
||||
|
||||
logger.info("Exported %d factors to %s", library.size, path)
|
||||
|
||||
@@ -204,49 +187,49 @@ def export_formulas(library: FactorLibrary, path: Union[str, Path]) -> None:
|
||||
# Each entry: (name, formula, category)
|
||||
PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
{
|
||||
"name": 'Intraday Range Position',
|
||||
"formula": '(-cs_rank(((close - ts_min(close, 48)) / ((ts_max(close, 48) - ts_min(close, 48)) + 1e-8))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Intraday Range Position",
|
||||
"formula": "(-cs_rank(((close - ts_min(close, 48)) / ((ts_max(close, 48) - ts_min(close, 48)) + 1e-8))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Volume-Weighted Momentum',
|
||||
"formula": '(-cs_rank((ts_pct_change(close, 5) * (vol / ts_mean(vol, 20)))))',
|
||||
"category": 'Momentum',
|
||||
"name": "Volume-Weighted Momentum",
|
||||
"formula": "(-cs_rank((ts_pct_change(close, 5) * (vol / ts_mean(vol, 20)))))",
|
||||
"category": "Momentum",
|
||||
},
|
||||
{
|
||||
"name": 'Residual Volatility',
|
||||
"formula": '(-cs_rank(ts_std((close - ts_ema(close, 10)), 20)))',
|
||||
"category": 'Volatility',
|
||||
"name": "Residual Volatility",
|
||||
"formula": "(-cs_rank(ts_std((close - ts_ema(close, 10)), 20)))",
|
||||
"category": "Volatility",
|
||||
},
|
||||
{
|
||||
"name": 'Intraday Amplitude Ratio',
|
||||
"formula": '(-cs_rank(((high - low) / (close + 1e-8))))',
|
||||
"category": 'Volatility',
|
||||
"name": "Intraday Amplitude Ratio",
|
||||
"formula": "(-cs_rank(((high - low) / (close + 1e-8))))",
|
||||
"category": "Volatility",
|
||||
},
|
||||
{
|
||||
"name": 'Volume Surprise',
|
||||
"formula": '(-cs_rank(((vol - ts_mean(vol, 20)) / (ts_std(vol, 20) + 1e-8))))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume Surprise",
|
||||
"formula": "(-cs_rank(((vol - ts_mean(vol, 20)) / (ts_std(vol, 20) + 1e-8))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'VWAP Deviation',
|
||||
"formula": '(-((close - (amount / vol)) / (amount / vol)))',
|
||||
"category": 'VWAP',
|
||||
"name": "VWAP Deviation",
|
||||
"formula": "(-((close - (amount / vol)) / (amount / vol)))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Short-term Reversal',
|
||||
"formula": '(-cs_rank(ts_pct_change(close, 3)))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Short-term Reversal",
|
||||
"formula": "(-cs_rank(ts_pct_change(close, 3)))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Turnover Momentum',
|
||||
"formula": '(-cs_rank(ts_delta((amount / (vol + 1e-8)), 5)))',
|
||||
"category": 'Turnover',
|
||||
"name": "Turnover Momentum",
|
||||
"formula": "(-cs_rank(ts_delta((amount / (vol + 1e-8)), 5)))",
|
||||
"category": "Turnover",
|
||||
},
|
||||
{
|
||||
"name": 'High-Low Midpoint Reversion',
|
||||
"formula": '(-cs_rank((close - ((high + low) / 2))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "High-Low Midpoint Reversion",
|
||||
"formula": "(-cs_rank((close - ((high + low) / 2))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
# {
|
||||
# "name": 'Rolling Beta Residual',
|
||||
@@ -259,69 +242,69 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'VWAP',
|
||||
# },
|
||||
{
|
||||
"name": 'Accumulation-Distribution',
|
||||
"formula": '(-cs_rank(ts_sum(((((2 * close) - (high + low)) / ((high - low) + 1e-8)) * vol), 10)))',
|
||||
"category": 'Volume',
|
||||
"name": "Accumulation-Distribution",
|
||||
"formula": "(-cs_rank(ts_sum(((((2 * close) - (high + low)) / ((high - low) + 1e-8)) * vol), 10)))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Relative Strength Index Deviation',
|
||||
"formula": '(-cs_rank((ts_mean(max_(ts_delta(close, 1), 0), 14) - ts_mean(abs(min_(ts_delta(close, 1), 0)), 14))))',
|
||||
"category": 'Momentum',
|
||||
"name": "Relative Strength Index Deviation",
|
||||
"formula": "(-cs_rank((ts_mean(max_(ts_delta(close, 1), 0), 14) - ts_mean(abs(min_(ts_delta(close, 1), 0)), 14))))",
|
||||
"category": "Momentum",
|
||||
},
|
||||
{
|
||||
"name": 'Price-Volume Correlation',
|
||||
"formula": '(-ts_corr(close, vol, 10))',
|
||||
"category": 'Volume',
|
||||
"name": "Price-Volume Correlation",
|
||||
"formula": "(-ts_corr(close, vol, 10))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Skewness of Returns',
|
||||
"formula": '(-cs_rank(ts_skew((close / ts_delay(close, 1) - 1), 20)))',
|
||||
"category": 'Higher-moment',
|
||||
"name": "Skewness of Returns",
|
||||
"formula": "(-cs_rank(ts_skew((close / ts_delay(close, 1) - 1), 20)))",
|
||||
"category": "Higher-moment",
|
||||
},
|
||||
{
|
||||
"name": 'Kurtosis of Returns',
|
||||
"formula": '(-cs_rank(ts_kurt((close / ts_delay(close, 1) - 1), 20)))',
|
||||
"category": 'Higher-moment',
|
||||
"name": "Kurtosis of Returns",
|
||||
"formula": "(-cs_rank(ts_kurt((close / ts_delay(close, 1) - 1), 20)))",
|
||||
"category": "Higher-moment",
|
||||
},
|
||||
{
|
||||
"name": 'Volume-Weighted Return',
|
||||
"formula": '(-cs_rank((ts_sum(((close / ts_delay(close, 1) - 1) * vol), 10) / (ts_sum(vol, 10) + 1e-8))))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume-Weighted Return",
|
||||
"formula": "(-cs_rank((ts_sum(((close / ts_delay(close, 1) - 1) * vol), 10) / (ts_sum(vol, 10) + 1e-8))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Close-to-High Ratio',
|
||||
"formula": '(-cs_rank(((high - close) / (high + 1e-8))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Close-to-High Ratio",
|
||||
"formula": "(-cs_rank(((high - close) / (high + 1e-8))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Delayed Correlation Shift',
|
||||
"formula": '(-cs_rank((ts_corr(close, vol, 10) - ts_corr(ts_delay(close, 5), vol, 10))))',
|
||||
"category": 'Volume',
|
||||
"name": "Delayed Correlation Shift",
|
||||
"formula": "(-cs_rank((ts_corr(close, vol, 10) - ts_corr(ts_delay(close, 5), vol, 10))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Exponential Momentum',
|
||||
"formula": '(-cs_rank((close - ts_ema(close, 20))))',
|
||||
"category": 'Momentum',
|
||||
"name": "Exponential Momentum",
|
||||
"formula": "(-cs_rank((close - ts_ema(close, 20))))",
|
||||
"category": "Momentum",
|
||||
},
|
||||
{
|
||||
"name": 'Range-Adjusted Volume',
|
||||
"formula": '(-cs_rank((vol / ((high - low) + 1e-8))))',
|
||||
"category": 'Volume',
|
||||
"name": "Range-Adjusted Volume",
|
||||
"formula": "(-cs_rank((vol / ((high - low) + 1e-8))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Cumulative Return Rank',
|
||||
"formula": '(-cs_rank(ts_sum((close / ts_delay(close, 1) - 1), 10)))',
|
||||
"category": 'Momentum',
|
||||
"name": "Cumulative Return Rank",
|
||||
"formula": "(-cs_rank(ts_sum((close / ts_delay(close, 1) - 1), 10)))",
|
||||
"category": "Momentum",
|
||||
},
|
||||
{
|
||||
"name": 'VWAP Momentum',
|
||||
"formula": '(-cs_rank(ts_pct_change((amount / vol), 5)))',
|
||||
"category": 'VWAP',
|
||||
"name": "VWAP Momentum",
|
||||
"formula": "(-cs_rank(ts_pct_change((amount / vol), 5)))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Bollinger Band Position',
|
||||
"formula": '(-cs_rank(((close - ts_mean(close, 20)) / (ts_std(close, 20) + 1e-8))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Bollinger Band Position",
|
||||
"formula": "(-cs_rank(((close - ts_mean(close, 20)) / (ts_std(close, 20) + 1e-8))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
# {
|
||||
# "name": 'Volume Decay Weighted',
|
||||
@@ -329,64 +312,64 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'Volume',
|
||||
# },
|
||||
{
|
||||
"name": 'Overnight Return',
|
||||
"formula": '(-cs_rank(((open - ts_delay(close, 1)) / (ts_delay(close, 1) + 1e-8))))',
|
||||
"category": 'Overnight',
|
||||
"name": "Overnight Return",
|
||||
"formula": "(-cs_rank(((open - ts_delay(close, 1)) / (ts_delay(close, 1) + 1e-8))))",
|
||||
"category": "Overnight",
|
||||
},
|
||||
{
|
||||
"name": 'Intraday Return',
|
||||
"formula": '(-cs_rank(((close - open) / (open + 1e-8))))',
|
||||
"category": 'Intraday',
|
||||
"name": "Intraday Return",
|
||||
"formula": "(-cs_rank(((close - open) / (open + 1e-8))))",
|
||||
"category": "Intraday",
|
||||
},
|
||||
{
|
||||
"name": 'Max Drawdown',
|
||||
"formula": '(-cs_rank(((close - ts_max(close, 20)) / (ts_max(close, 20) + 1e-8))))',
|
||||
"category": 'Risk',
|
||||
"name": "Max Drawdown",
|
||||
"formula": "(-cs_rank(((close - ts_max(close, 20)) / (ts_max(close, 20) + 1e-8))))",
|
||||
"category": "Risk",
|
||||
},
|
||||
{
|
||||
"name": 'Hurst Exponent Proxy',
|
||||
"formula": '(-cs_rank((ts_std((close / ts_delay(close, 1) - 1), 20) / (ts_std((close / ts_delay(close, 1) - 1), 5) + 1e-8))))',
|
||||
"category": 'Volatility',
|
||||
"name": "Hurst Exponent Proxy",
|
||||
"formula": "(-cs_rank((ts_std((close / ts_delay(close, 1) - 1), 20) / (ts_std((close / ts_delay(close, 1) - 1), 5) + 1e-8))))",
|
||||
"category": "Volatility",
|
||||
},
|
||||
{
|
||||
"name": 'Volume Imbalance',
|
||||
"formula": '(-cs_rank((ts_mean(vol, 5) - ts_mean(vol, 20))))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume Imbalance",
|
||||
"formula": "(-cs_rank((ts_mean(vol, 5) - ts_mean(vol, 20))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Weighted Close Position',
|
||||
"formula": '(-cs_rank((((2 * close) - (high + low)) / ((high - low) + 1e-8))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Weighted Close Position",
|
||||
"formula": "(-cs_rank((((2 * close) - (high + low)) / ((high - low) + 1e-8))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Trend Intensity',
|
||||
"formula": '(-cs_rank((abs(ts_delta(close, 10)) / (ts_sum(abs(ts_delta(close, 1)), 10) + 1e-8))))',
|
||||
"category": 'Trend',
|
||||
"name": "Trend Intensity",
|
||||
"formula": "(-cs_rank((abs(ts_delta(close, 10)) / (ts_sum(abs(ts_delta(close, 1)), 10) + 1e-8))))",
|
||||
"category": "Trend",
|
||||
},
|
||||
{
|
||||
"name": 'Return Dispersion',
|
||||
"formula": '(-cs_rank(ts_std((close / ts_delay(close, 1) - 1), 5)))',
|
||||
"category": 'Volatility',
|
||||
"name": "Return Dispersion",
|
||||
"formula": "(-cs_rank(ts_std((close / ts_delay(close, 1) - 1), 5)))",
|
||||
"category": "Volatility",
|
||||
},
|
||||
{
|
||||
"name": 'VWAP Relative Strength',
|
||||
"formula": '(-cs_rank(((ts_mean(close, 5) - (amount / vol)) / ((amount / vol) + 1e-8))))',
|
||||
"category": 'VWAP',
|
||||
"name": "VWAP Relative Strength",
|
||||
"formula": "(-cs_rank(((ts_mean(close, 5) - (amount / vol)) / ((amount / vol) + 1e-8))))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Rank Reversal',
|
||||
"formula": '(-cs_rank((ts_rank(close, 10) - ts_rank(close, 30))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Rank Reversal",
|
||||
"formula": "(-cs_rank((ts_rank(close, 10) - ts_rank(close, 30))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Money Flow Index',
|
||||
"formula": '(-cs_rank((ts_sum((max_(ts_delta(close, 1), 0) * vol), 14) / (ts_sum((abs(ts_delta(close, 1)) * vol), 14) + 1e-8))))',
|
||||
"category": 'Volume',
|
||||
"name": "Money Flow Index",
|
||||
"formula": "(-cs_rank((ts_sum((max_(ts_delta(close, 1), 0) * vol), 14) / (ts_sum((abs(ts_delta(close, 1)) * vol), 14) + 1e-8))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Adaptive Momentum',
|
||||
"formula": '(-cs_rank((ts_pct_change(close, 10) * (ts_std((close / ts_delay(close, 1) - 1), 5) / (ts_std((close / ts_delay(close, 1) - 1), 20) + 1e-8)))))',
|
||||
"category": 'Momentum',
|
||||
"name": "Adaptive Momentum",
|
||||
"formula": "(-cs_rank((ts_pct_change(close, 10) * (ts_std((close / ts_delay(close, 1) - 1), 5) / (ts_std((close / ts_delay(close, 1) - 1), 20) + 1e-8)))))",
|
||||
"category": "Momentum",
|
||||
},
|
||||
# {
|
||||
# "name": 'Volume Trend',
|
||||
@@ -394,29 +377,29 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'Volume',
|
||||
# },
|
||||
{
|
||||
"name": 'Price Acceleration',
|
||||
"formula": '(-cs_rank((ts_delta(close, 5) - ts_delta(ts_delay(close, 5), 5))))',
|
||||
"category": 'Momentum',
|
||||
"name": "Price Acceleration",
|
||||
"formula": "(-cs_rank((ts_delta(close, 5) - ts_delta(ts_delay(close, 5), 5))))",
|
||||
"category": "Momentum",
|
||||
},
|
||||
{
|
||||
"name": 'Realized Volatility Ratio',
|
||||
"formula": '(-cs_rank((ts_std((close / ts_delay(close, 1) - 1), 10) / (ts_std((close / ts_delay(close, 1) - 1), 30) + 1e-8))))',
|
||||
"category": 'Volatility',
|
||||
"name": "Realized Volatility Ratio",
|
||||
"formula": "(-cs_rank((ts_std((close / ts_delay(close, 1) - 1), 10) / (ts_std((close / ts_delay(close, 1) - 1), 30) + 1e-8))))",
|
||||
"category": "Volatility",
|
||||
},
|
||||
{
|
||||
"name": 'Amount Concentration',
|
||||
"formula": '(-cs_rank((ts_max(amount, 5) / (ts_mean(amount, 20) + 1e-8))))',
|
||||
"category": 'Turnover',
|
||||
"name": "Amount Concentration",
|
||||
"formula": "(-cs_rank((ts_max(amount, 5) / (ts_mean(amount, 20) + 1e-8))))",
|
||||
"category": "Turnover",
|
||||
},
|
||||
{
|
||||
"name": 'Cross-Sectional Volume Rank',
|
||||
"formula": '(-cs_rank((vol / (ts_mean(vol, 60) + 1e-8))))',
|
||||
"category": 'Volume',
|
||||
"name": "Cross-Sectional Volume Rank",
|
||||
"formula": "(-cs_rank((vol / (ts_mean(vol, 60) + 1e-8))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Gap Momentum',
|
||||
"formula": '(-cs_rank(ts_sum(((open - ts_delay(close, 1)) / (ts_delay(close, 1) + 1e-8)), 5)))',
|
||||
"category": 'Overnight',
|
||||
"name": "Gap Momentum",
|
||||
"formula": "(-cs_rank(ts_sum(((open - ts_delay(close, 1)) / (ts_delay(close, 1) + 1e-8)), 5)))",
|
||||
"category": "Overnight",
|
||||
},
|
||||
# {
|
||||
# "name": 'VWAP Distance Decay',
|
||||
@@ -424,44 +407,44 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'VWAP',
|
||||
# },
|
||||
{
|
||||
"name": 'Tail Risk Indicator',
|
||||
"formula": '(-cs_rank((ts_min((close / ts_delay(close, 1) - 1), 20) / (ts_std((close / ts_delay(close, 1) - 1), 20) + 1e-8))))',
|
||||
"category": 'Risk',
|
||||
"name": "Tail Risk Indicator",
|
||||
"formula": "(-cs_rank((ts_min((close / ts_delay(close, 1) - 1), 20) / (ts_std((close / ts_delay(close, 1) - 1), 20) + 1e-8))))",
|
||||
"category": "Risk",
|
||||
},
|
||||
{
|
||||
"name": 'Volatility-Regime Reversal Divergence',
|
||||
"formula": 'if_((ts_std((close / ts_delay(close, 1) - 1), 12) > ts_mean(ts_std((close / ts_delay(close, 1) - 1), 12), 48)), (-cs_rank(ts_delta(close, 3))), (-cs_rank(((close - low) / ((high - low) + 0.0001)))))',
|
||||
"category": 'Regime-switching',
|
||||
"name": "Volatility-Regime Reversal Divergence",
|
||||
"formula": "if_((ts_std((close / ts_delay(close, 1) - 1), 12) > ts_mean(ts_std((close / ts_delay(close, 1) - 1), 12), 48)), (-cs_rank(ts_delta(close, 3))), (-cs_rank(((close - low) / ((high - low) + 0.0001)))))",
|
||||
"category": "Regime-switching",
|
||||
},
|
||||
{
|
||||
"name": 'Regime Volume Signal',
|
||||
"formula": 'if_((vol > ts_mean(vol, 20)), (-cs_rank((close / ts_delay(close, 1) - 1))), (-cs_rank(ts_pct_change(close, 5))))',
|
||||
"category": 'Regime-switching',
|
||||
"name": "Regime Volume Signal",
|
||||
"formula": "if_((vol > ts_mean(vol, 20)), (-cs_rank((close / ts_delay(close, 1) - 1))), (-cs_rank(ts_pct_change(close, 5))))",
|
||||
"category": "Regime-switching",
|
||||
},
|
||||
{
|
||||
"name": 'Liquidity-Adjusted Reversal',
|
||||
"formula": '(-cs_rank((ts_pct_change(close, 3) * (vol / (ts_mean(vol, 20) + 1e-8)))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Liquidity-Adjusted Reversal",
|
||||
"formula": "(-cs_rank((ts_pct_change(close, 3) * (vol / (ts_mean(vol, 20) + 1e-8)))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Cross-Sectional Volatility Rank',
|
||||
"formula": '(-cs_rank(cs_rank(ts_std((close / ts_delay(close, 1) - 1), 10))))',
|
||||
"category": 'Volatility',
|
||||
"name": "Cross-Sectional Volatility Rank",
|
||||
"formula": "(-cs_rank(cs_rank(ts_std((close / ts_delay(close, 1) - 1), 10))))",
|
||||
"category": "Volatility",
|
||||
},
|
||||
{
|
||||
"name": 'VWAP Bollinger',
|
||||
"formula": '(-cs_rank((((amount / vol) - ts_mean((amount / vol), 20)) / (ts_std((amount / vol), 20) + 1e-8))))',
|
||||
"category": 'VWAP',
|
||||
"name": "VWAP Bollinger",
|
||||
"formula": "(-cs_rank((((amount / vol) - ts_mean((amount / vol), 20)) / (ts_std((amount / vol), 20) + 1e-8))))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Smoothed Return Reversal',
|
||||
"formula": '(-cs_rank(ts_ema((close / ts_delay(close, 1) - 1), 5)))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Smoothed Return Reversal",
|
||||
"formula": "(-cs_rank(ts_ema((close / ts_delay(close, 1) - 1), 5)))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Volume-Price Divergence',
|
||||
"formula": '(-cs_rank((ts_rank(vol, 10) - ts_rank(close, 10))))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume-Price Divergence",
|
||||
"formula": "(-cs_rank((ts_rank(vol, 10) - ts_rank(close, 10))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
# {
|
||||
# "name": 'Decay Weighted Momentum',
|
||||
@@ -469,14 +452,14 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'Momentum',
|
||||
# },
|
||||
{
|
||||
"name": 'Range Percentile',
|
||||
"formula": '(-cs_rank(((close - ts_min(close, 20)) / ((ts_max(close, 20) - ts_min(close, 20)) + 1e-8))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Range Percentile",
|
||||
"formula": "(-cs_rank(((close - ts_min(close, 20)) / ((ts_max(close, 20) - ts_min(close, 20)) + 1e-8))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Volume Skewness',
|
||||
"formula": '(-cs_rank(ts_skew(vol, 20)))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume Skewness",
|
||||
"formula": "(-cs_rank(ts_skew(vol, 20)))",
|
||||
"category": "Volume",
|
||||
},
|
||||
# {
|
||||
# "name": 'Residual Momentum',
|
||||
@@ -484,54 +467,54 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'Momentum',
|
||||
# },
|
||||
{
|
||||
"name": 'VWAP Trend',
|
||||
"formula": '(-cs_rank(ts_delta(((close - (amount / vol)) / (amount / vol)), 5)))',
|
||||
"category": 'VWAP',
|
||||
"name": "VWAP Trend",
|
||||
"formula": "(-cs_rank(ts_delta(((close - (amount / vol)) / (amount / vol)), 5)))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Return Autocorrelation',
|
||||
"formula": '(-cs_rank(ts_corr((close / ts_delay(close, 1) - 1), ts_delay((close / ts_delay(close, 1) - 1), 1), 10)))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Return Autocorrelation",
|
||||
"formula": "(-cs_rank(ts_corr((close / ts_delay(close, 1) - 1), ts_delay((close / ts_delay(close, 1) - 1), 1), 10)))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Price Efficiency',
|
||||
"formula": '(-cs_rank((abs(ts_sum((close / ts_delay(close, 1) - 1), 10)) / (ts_sum(abs((close / ts_delay(close, 1) - 1)), 10) + 1e-8))))',
|
||||
"category": 'Trend',
|
||||
"name": "Price Efficiency",
|
||||
"formula": "(-cs_rank((abs(ts_sum((close / ts_delay(close, 1) - 1), 10)) / (ts_sum(abs((close / ts_delay(close, 1) - 1)), 10) + 1e-8))))",
|
||||
"category": "Trend",
|
||||
},
|
||||
{
|
||||
"name": 'Relative Volume Change',
|
||||
"formula": '(-cs_rank(ts_pct_change(vol, 5)))',
|
||||
"category": 'Volume',
|
||||
"name": "Relative Volume Change",
|
||||
"formula": "(-cs_rank(ts_pct_change(vol, 5)))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Weighted VWAP Position',
|
||||
"formula": '(-cs_rank(ts_wma(((close - (amount / vol)) / (amount / vol)), 10)))',
|
||||
"category": 'VWAP',
|
||||
"name": "Weighted VWAP Position",
|
||||
"formula": "(-cs_rank(ts_wma(((close - (amount / vol)) / (amount / vol)), 10)))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Regime Momentum Flip',
|
||||
"formula": 'if_((ts_mean((close / ts_delay(close, 1) - 1), 5) > 0), (-cs_rank(ts_pct_change(close, 10))), cs_rank(ts_pct_change(close, 3)))',
|
||||
"category": 'Regime-switching',
|
||||
"name": "Regime Momentum Flip",
|
||||
"formula": "if_((ts_mean((close / ts_delay(close, 1) - 1), 5) > 0), (-cs_rank(ts_pct_change(close, 10))), cs_rank(ts_pct_change(close, 3)))",
|
||||
"category": "Regime-switching",
|
||||
},
|
||||
{
|
||||
"name": 'High-Low Volatility',
|
||||
"formula": '(-cs_rank(ts_mean(((high - low) / (close + 1e-8)), 10)))',
|
||||
"category": 'Volatility',
|
||||
"name": "High-Low Volatility",
|
||||
"formula": "(-cs_rank(ts_mean(((high - low) / (close + 1e-8)), 10)))",
|
||||
"category": "Volatility",
|
||||
},
|
||||
{
|
||||
"name": 'Opening Gap Reversal',
|
||||
"formula": '(-cs_rank(((open - ts_delay(close, 1)) / (ts_std((close / ts_delay(close, 1) - 1), 10) + 1e-8))))',
|
||||
"category": 'Overnight',
|
||||
"name": "Opening Gap Reversal",
|
||||
"formula": "(-cs_rank(((open - ts_delay(close, 1)) / (ts_std((close / ts_delay(close, 1) - 1), 10) + 1e-8))))",
|
||||
"category": "Overnight",
|
||||
},
|
||||
{
|
||||
"name": 'Volume Momentum Spread',
|
||||
"formula": '(-cs_rank((ts_mean(vol, 5) - ts_mean(vol, 40))))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume Momentum Spread",
|
||||
"formula": "(-cs_rank((ts_mean(vol, 5) - ts_mean(vol, 40))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Regime Volume Reversal',
|
||||
"formula": 'if_(((vol / (ts_mean(vol, 20) + 1e-8)) > 1.5), (-cs_rank((close / ts_delay(close, 1) - 1))), (-cs_rank(ts_pct_change(close, 10))))',
|
||||
"category": 'Regime-switching',
|
||||
"name": "Regime Volume Reversal",
|
||||
"formula": "if_(((vol / (ts_mean(vol, 20) + 1e-8)) > 1.5), (-cs_rank((close / ts_delay(close, 1) - 1))), (-cs_rank(ts_pct_change(close, 10))))",
|
||||
"category": "Regime-switching",
|
||||
},
|
||||
# {
|
||||
# "name": 'Slope Reversal',
|
||||
@@ -544,9 +527,9 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'VWAP',
|
||||
# },
|
||||
{
|
||||
"name": 'Turnover Rate Change',
|
||||
"formula": '(-cs_rank(ts_delta((amount / (vol + 1e-8)), 10)))',
|
||||
"category": 'Turnover',
|
||||
"name": "Turnover Rate Change",
|
||||
"formula": "(-cs_rank(ts_delta((amount / (vol + 1e-8)), 10)))",
|
||||
"category": "Turnover",
|
||||
},
|
||||
# {
|
||||
# "name": 'Return Quantile Signal',
|
||||
@@ -554,14 +537,14 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'Higher-moment',
|
||||
# },
|
||||
{
|
||||
"name": 'Double EMA Crossover',
|
||||
"formula": '(-cs_rank((ts_ema(close, 5) - ts_ema(close, 20))))',
|
||||
"category": 'Trend',
|
||||
"name": "Double EMA Crossover",
|
||||
"formula": "(-cs_rank((ts_ema(close, 5) - ts_ema(close, 20))))",
|
||||
"category": "Trend",
|
||||
},
|
||||
{
|
||||
"name": 'Conditional Volatility Return',
|
||||
"formula": '(-cs_rank(((close / ts_delay(close, 1) - 1) / (ts_std((close / ts_delay(close, 1) - 1), 10) + 1e-8))))',
|
||||
"category": 'Risk',
|
||||
"name": "Conditional Volatility Return",
|
||||
"formula": "(-cs_rank(((close / ts_delay(close, 1) - 1) / (ts_std((close / ts_delay(close, 1) - 1), 10) + 1e-8))))",
|
||||
"category": "Risk",
|
||||
},
|
||||
# {
|
||||
# "name": 'Amplitude Trend',
|
||||
@@ -569,39 +552,39 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'Volatility',
|
||||
# },
|
||||
{
|
||||
"name": 'Volume-Weighted Range',
|
||||
"formula": '(-cs_rank(ts_mean((((high - low) / (close + 1e-8)) * vol), 10)))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume-Weighted Range",
|
||||
"formula": "(-cs_rank(ts_mean((((high - low) / (close + 1e-8)) * vol), 10)))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Intraday Efficiency Ratio',
|
||||
"formula": '(-cs_rank((abs((close - open)) / ((high - low) + 1e-8))))',
|
||||
"category": 'Intraday',
|
||||
"name": "Intraday Efficiency Ratio",
|
||||
"formula": "(-cs_rank((abs((close - open)) / ((high - low) + 1e-8))))",
|
||||
"category": "Intraday",
|
||||
},
|
||||
{
|
||||
"name": 'Cumulative Volume Signal',
|
||||
"formula": '(-cs_rank((ts_sum(((close / ts_delay(close, 1) - 1) * vol), 20) / (ts_sum(vol, 20) + 1e-8))))',
|
||||
"category": 'Volume',
|
||||
"name": "Cumulative Volume Signal",
|
||||
"formula": "(-cs_rank((ts_sum(((close / ts_delay(close, 1) - 1) * vol), 20) / (ts_sum(vol, 20) + 1e-8))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'VWAP Cross-Sectional Momentum',
|
||||
"formula": '(-cs_rank(cs_rank(ts_pct_change((amount / vol), 10))))',
|
||||
"category": 'VWAP',
|
||||
"name": "VWAP Cross-Sectional Momentum",
|
||||
"formula": "(-cs_rank(cs_rank(ts_pct_change((amount / vol), 10))))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Mean-Reversion Indicator',
|
||||
"formula": '(-cs_rank(((close - ts_mean(close, 10)) / (ts_mean(close, 10) + 1e-8))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Mean-Reversion Indicator",
|
||||
"formula": "(-cs_rank(((close - ts_mean(close, 10)) / (ts_mean(close, 10) + 1e-8))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Volume Regime Indicator',
|
||||
"formula": '(-cs_rank((ts_std(vol, 5) / (ts_std(vol, 20) + 1e-8))))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume Regime Indicator",
|
||||
"formula": "(-cs_rank((ts_std(vol, 5) / (ts_std(vol, 20) + 1e-8))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Return Persistence',
|
||||
"formula": '(-cs_rank((sign(ts_delta(close, 1)) * sign(ts_delta(close, 5)))))',
|
||||
"category": 'Momentum',
|
||||
"name": "Return Persistence",
|
||||
"formula": "(-cs_rank((sign(ts_delta(close, 1)) * sign(ts_delta(close, 5)))))",
|
||||
"category": "Momentum",
|
||||
},
|
||||
# {
|
||||
# "name": 'Regime Trend Strength',
|
||||
@@ -609,29 +592,29 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'Regime-switching',
|
||||
# },
|
||||
{
|
||||
"name": 'VWAP Dispersion',
|
||||
"formula": '(-cs_rank(ts_std(((close - (amount / vol)) / (amount / vol)), 10)))',
|
||||
"category": 'VWAP',
|
||||
"name": "VWAP Dispersion",
|
||||
"formula": "(-cs_rank(ts_std(((close - (amount / vol)) / (amount / vol)), 10)))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Smart Money Flow',
|
||||
"formula": '(-cs_rank(ts_sum((if_((close > ts_delay(close, 1)), vol, (-vol)) * ((high - low) / (close + 1e-8))), 10)))',
|
||||
"category": 'Volume',
|
||||
"name": "Smart Money Flow",
|
||||
"formula": "(-cs_rank(ts_sum((if_((close > ts_delay(close, 1)), vol, (-vol)) * ((high - low) / (close + 1e-8))), 10)))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Return Rank Dispersion',
|
||||
"formula": '(-cs_rank((ts_rank((close / ts_delay(close, 1) - 1), 5) - ts_rank((close / ts_delay(close, 1) - 1), 20))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Return Rank Dispersion",
|
||||
"formula": "(-cs_rank((ts_rank((close / ts_delay(close, 1) - 1), 5) - ts_rank((close / ts_delay(close, 1) - 1), 20))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Volume Acceleration',
|
||||
"formula": '(-cs_rank((ts_delta(vol, 5) - ts_delta(ts_delay(vol, 5), 5))))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume Acceleration",
|
||||
"formula": "(-cs_rank((ts_delta(vol, 5) - ts_delta(ts_delay(vol, 5), 5))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Close-Low Ratio Trend',
|
||||
"formula": '(-cs_rank(ts_mean(((close - low) / ((high - low) + 1e-8)), 5)))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Close-Low Ratio Trend",
|
||||
"formula": "(-cs_rank(ts_mean(((close - low) / ((high - low) + 1e-8)), 5)))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
# {
|
||||
# "name": 'Hull MA Deviation',
|
||||
@@ -644,69 +627,69 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'Momentum',
|
||||
# },
|
||||
{
|
||||
"name": 'Volume Profile Skew',
|
||||
"formula": '(-cs_rank(ts_skew((vol / (ts_mean(vol, 20) + 1e-8)), 10)))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume Profile Skew",
|
||||
"formula": "(-cs_rank(ts_skew((vol / (ts_mean(vol, 20) + 1e-8)), 10)))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Conditional VWAP Signal',
|
||||
"formula": 'if_((close > (amount / vol)), (-cs_rank(((close - (amount / vol)) / (amount / vol)))), cs_rank((((amount / vol) - close) / (amount / vol))))',
|
||||
"category": 'VWAP',
|
||||
"name": "Conditional VWAP Signal",
|
||||
"formula": "if_((close > (amount / vol)), (-cs_rank(((close - (amount / vol)) / (amount / vol)))), cs_rank((((amount / vol) - close) / (amount / vol))))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Extreme Volume Reversal',
|
||||
"formula": '(-cs_rank((if_((vol > (2 * ts_mean(vol, 20))), 1, 0) * (close / ts_delay(close, 1) - 1))))',
|
||||
"category": 'Volume',
|
||||
"name": "Extreme Volume Reversal",
|
||||
"formula": "(-cs_rank((if_((vol > (2 * ts_mean(vol, 20))), 1, 0) * (close / ts_delay(close, 1) - 1))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Range Expansion Signal',
|
||||
"formula": '(-cs_rank(((high - low) / (ts_mean((high - low), 20) + 1e-8))))',
|
||||
"category": 'Volatility',
|
||||
"name": "Range Expansion Signal",
|
||||
"formula": "(-cs_rank(((high - low) / (ts_mean((high - low), 20) + 1e-8))))",
|
||||
"category": "Volatility",
|
||||
},
|
||||
{
|
||||
"name": 'Short-Term IC Momentum',
|
||||
"formula": '(-cs_rank(ts_sum((sign((close / ts_delay(close, 1) - 1)) * abs((close / ts_delay(close, 1) - 1))), 5)))',
|
||||
"category": 'Momentum',
|
||||
"name": "Short-Term IC Momentum",
|
||||
"formula": "(-cs_rank(ts_sum((sign((close / ts_delay(close, 1) - 1)) * abs((close / ts_delay(close, 1) - 1))), 5)))",
|
||||
"category": "Momentum",
|
||||
},
|
||||
{
|
||||
"name": 'VWAP Curvature',
|
||||
"formula": '(-cs_rank(((((amount / vol) - ts_delay((amount / vol), 5)) / (ts_delay((amount / vol), 5) + 1e-8)) - ((ts_delay((amount / vol), 5) - ts_delay((amount / vol), 10)) / (ts_delay((amount / vol), 10) + 1e-8)))))',
|
||||
"category": 'VWAP',
|
||||
"name": "VWAP Curvature",
|
||||
"formula": "(-cs_rank(((((amount / vol) - ts_delay((amount / vol), 5)) / (ts_delay((amount / vol), 5) + 1e-8)) - ((ts_delay((amount / vol), 5) - ts_delay((amount / vol), 10)) / (ts_delay((amount / vol), 10) + 1e-8)))))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Relative Strength',
|
||||
"formula": '(-cs_rank((ts_pct_change(close, 5) / (ts_pct_change(close, 20) + 1e-8))))',
|
||||
"category": 'Momentum',
|
||||
"name": "Relative Strength",
|
||||
"formula": "(-cs_rank((ts_pct_change(close, 5) / (ts_pct_change(close, 20) + 1e-8))))",
|
||||
"category": "Momentum",
|
||||
},
|
||||
{
|
||||
"name": 'Volume-Correlated Return',
|
||||
"formula": '(-cs_rank(ts_cov((close / ts_delay(close, 1) - 1), vol, 10)))',
|
||||
"category": 'Volume',
|
||||
"name": "Volume-Correlated Return",
|
||||
"formula": "(-cs_rank(ts_cov((close / ts_delay(close, 1) - 1), vol, 10)))",
|
||||
"category": "Volume",
|
||||
},
|
||||
{
|
||||
"name": 'Regime Volatility Band',
|
||||
"formula": 'if_((ts_std((close / ts_delay(close, 1) - 1), 5) > (1.5 * ts_std((close / ts_delay(close, 1) - 1), 20))), (-cs_rank(ts_pct_change(close, 1))), (-cs_rank(ts_pct_change(close, 10))))',
|
||||
"category": 'Regime-switching',
|
||||
"name": "Regime Volatility Band",
|
||||
"formula": "if_((ts_std((close / ts_delay(close, 1) - 1), 5) > (1.5 * ts_std((close / ts_delay(close, 1) - 1), 20))), (-cs_rank(ts_pct_change(close, 1))), (-cs_rank(ts_pct_change(close, 10))))",
|
||||
"category": "Regime-switching",
|
||||
},
|
||||
{
|
||||
"name": 'Open-Close Spread Momentum',
|
||||
"formula": '(-cs_rank(ts_mean(((close - open) / (open + 1e-8)), 5)))',
|
||||
"category": 'Intraday',
|
||||
"name": "Open-Close Spread Momentum",
|
||||
"formula": "(-cs_rank(ts_mean(((close - open) / (open + 1e-8)), 5)))",
|
||||
"category": "Intraday",
|
||||
},
|
||||
{
|
||||
"name": 'Volatility-Scaled Reversal',
|
||||
"formula": '(-cs_rank((ts_pct_change(close, 5) / (ts_std((close / ts_delay(close, 1) - 1), 20) + 1e-8))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Volatility-Scaled Reversal",
|
||||
"formula": "(-cs_rank((ts_pct_change(close, 5) / (ts_std((close / ts_delay(close, 1) - 1), 20) + 1e-8))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'VWAP Time-Weighted Signal',
|
||||
"formula": '(-cs_rank(ts_wma(((close - (amount / vol)) / ((amount / vol) + 1e-8)), 20)))',
|
||||
"category": 'VWAP',
|
||||
"name": "VWAP Time-Weighted Signal",
|
||||
"formula": "(-cs_rank(ts_wma(((close - (amount / vol)) / ((amount / vol) + 1e-8)), 20)))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Covariance Structure Shift',
|
||||
"formula": '(-cs_rank((ts_cov((close / ts_delay(close, 1) - 1), vol, 5) - ts_cov((close / ts_delay(close, 1) - 1), vol, 20))))',
|
||||
"category": 'Volume',
|
||||
"name": "Covariance Structure Shift",
|
||||
"formula": "(-cs_rank((ts_cov((close / ts_delay(close, 1) - 1), vol, 5) - ts_cov((close / ts_delay(close, 1) - 1), vol, 20))))",
|
||||
"category": "Volume",
|
||||
},
|
||||
# {
|
||||
# "name": 'Quadratic Regression Residual',
|
||||
@@ -714,34 +697,34 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'Higher-moment',
|
||||
# },
|
||||
{
|
||||
"name": 'VWAP Mean-Reversion Strength',
|
||||
"formula": '(-cs_rank((((close - (amount / vol)) / (amount / vol)) * (vol / (ts_mean(vol, 20) + 1e-8)))))',
|
||||
"category": 'VWAP',
|
||||
"name": "VWAP Mean-Reversion Strength",
|
||||
"formula": "(-cs_rank((((close - (amount / vol)) / (amount / vol)) * (vol / (ts_mean(vol, 20) + 1e-8)))))",
|
||||
"category": "VWAP",
|
||||
},
|
||||
{
|
||||
"name": 'Multi-Scale Momentum',
|
||||
"formula": '(-cs_rank((ts_pct_change(close, 5) + ts_pct_change(close, 20))))',
|
||||
"category": 'Momentum',
|
||||
"name": "Multi-Scale Momentum",
|
||||
"formula": "(-cs_rank((ts_pct_change(close, 5) + ts_pct_change(close, 20))))",
|
||||
"category": "Momentum",
|
||||
},
|
||||
{
|
||||
"name": 'Relative High Position',
|
||||
"formula": '(-cs_rank(((ts_max(high, 20) - close) / (ts_max(high, 20) + 1e-8))))',
|
||||
"category": 'Mean-reversion',
|
||||
"name": "Relative High Position",
|
||||
"formula": "(-cs_rank(((ts_max(high, 20) - close) / (ts_max(high, 20) + 1e-8))))",
|
||||
"category": "Mean-reversion",
|
||||
},
|
||||
{
|
||||
"name": 'Turnover Volatility',
|
||||
"formula": '(-cs_rank(ts_std((amount / (vol + 1e-8)), 10)))',
|
||||
"category": 'Turnover',
|
||||
"name": "Turnover Volatility",
|
||||
"formula": "(-cs_rank(ts_std((amount / (vol + 1e-8)), 10)))",
|
||||
"category": "Turnover",
|
||||
},
|
||||
{
|
||||
"name": 'Regime Correlation Signal',
|
||||
"formula": 'if_((abs(ts_corr(close, vol, 10)) > 0.5), (-cs_rank(ts_pct_change(close, 3))), (-cs_rank(ts_pct_change(close, 10))))',
|
||||
"category": 'Regime-switching',
|
||||
"name": "Regime Correlation Signal",
|
||||
"formula": "if_((abs(ts_corr(close, vol, 10)) > 0.5), (-cs_rank(ts_pct_change(close, 3))), (-cs_rank(ts_pct_change(close, 10))))",
|
||||
"category": "Regime-switching",
|
||||
},
|
||||
{
|
||||
"name": 'Intraday Momentum Reversal',
|
||||
"formula": '(-cs_rank(((close - open) / ((high - low) + 1e-8))))',
|
||||
"category": 'Intraday',
|
||||
"name": "Intraday Momentum Reversal",
|
||||
"formula": "(-cs_rank(((close - open) / ((high - low) + 1e-8))))",
|
||||
"category": "Intraday",
|
||||
},
|
||||
# {
|
||||
# "name": 'Volume-Weighted Slope',
|
||||
@@ -749,14 +732,13 @@ PAPER_FACTORS: List[Dict[str, str]] = [
|
||||
# "category": 'Volume',
|
||||
# },
|
||||
{
|
||||
"name": 'Adaptive Range Reversal',
|
||||
"formula": 'if_((ts_std((close / ts_delay(close, 1) - 1), 10) > ts_mean(ts_std((close / ts_delay(close, 1) - 1), 10), 40)), (-cs_rank(((close - ts_min(close, 10)) / ((ts_max(close, 10) - ts_min(close, 10)) + 1e-8)))), (-cs_rank(ts_pct_change(close, 5))))',
|
||||
"category": 'Regime-switching',
|
||||
"name": "Adaptive Range Reversal",
|
||||
"formula": "if_((ts_std((close / ts_delay(close, 1) - 1), 10) > ts_mean(ts_std((close / ts_delay(close, 1) - 1), 10), 40)), (-cs_rank(((close - ts_min(close, 10)) / ((ts_max(close, 10) - ts_min(close, 10)) + 1e-8)))), (-cs_rank(ts_pct_change(close, 5))))",
|
||||
"category": "Regime-switching",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
|
||||
def import_from_paper(
|
||||
path: Optional[Union[str, Path]] = None,
|
||||
) -> FactorLibrary:
|
||||
@@ -802,6 +784,8 @@ def import_from_paper(
|
||||
admission_date=entry.get("admission_date", ""),
|
||||
signals=None,
|
||||
)
|
||||
if factor.formula.strip().startswith("# TODO"):
|
||||
factor.metadata["unsupported"] = True
|
||||
library.admit_factor(factor)
|
||||
|
||||
logger.info(
|
||||
|
||||
157
tests/test_factorminer_library_io.py
Normal file
157
tests/test_factorminer_library_io.py
Normal file
@@ -0,0 +1,157 @@
|
||||
"""Tests for library I/O and paper factor imports."""
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import pytest
|
||||
|
||||
from src.factorminer.core.factor_library import Factor, FactorLibrary
|
||||
from src.factorminer.core.library_io import (
|
||||
import_from_paper,
|
||||
load_library,
|
||||
save_library,
|
||||
)
|
||||
|
||||
|
||||
class TestSaveLoadLibrary:
|
||||
"""测试 FactorLibrary 的序列化与反序列化."""
|
||||
|
||||
def test_save_library_ignores_save_signals(self, tmp_path: Path) -> None:
|
||||
"""save_signals=True 也不应生成 .npz 文件."""
|
||||
library = FactorLibrary()
|
||||
factor = Factor(
|
||||
id=0,
|
||||
name="test_factor",
|
||||
formula="close / ts_delay(close, 1) - 1",
|
||||
category="Momentum",
|
||||
ic_mean=0.05,
|
||||
icir=0.5,
|
||||
ic_win_rate=0.55,
|
||||
max_correlation=0.1,
|
||||
batch_number=1,
|
||||
)
|
||||
# 即使给一个信号矩阵，也不应保存
|
||||
factor.signals = np.ones((10, 20))
|
||||
library.admit_factor(factor)
|
||||
|
||||
base_path = tmp_path / "test_lib"
|
||||
save_library(library, str(base_path), save_signals=True)
|
||||
|
||||
assert (base_path.with_suffix(".json")).exists()
|
||||
assert not (Path(str(base_path) + "_signals.npz")).exists()
|
||||
|
||||
def test_load_library_restores_metadata_and_unsupported(
|
||||
self, tmp_path: Path
|
||||
) -> None:
|
||||
"""加载 JSON 后应恢复 metadata，并对 # TODO 公式标记 unsupported."""
|
||||
library = FactorLibrary()
|
||||
f1 = Factor(
|
||||
id=0,
|
||||
name="ok_factor",
|
||||
formula="cs_rank(close)",
|
||||
category="Test",
|
||||
ic_mean=0.0,
|
||||
icir=0.0,
|
||||
ic_win_rate=0.0,
|
||||
max_correlation=0.0,
|
||||
batch_number=0,
|
||||
metadata={"author": "ai"},
|
||||
)
|
||||
f2 = Factor(
|
||||
id=0,
|
||||
name="todo_factor",
|
||||
formula="# TODO: Neg(CsRank(Decay(close, 10)))",
|
||||
category="Test",
|
||||
ic_mean=0.0,
|
||||
icir=0.0,
|
||||
ic_win_rate=0.0,
|
||||
max_correlation=0.0,
|
||||
batch_number=0,
|
||||
)
|
||||
library.admit_factor(f1)
|
||||
library.admit_factor(f2)
|
||||
|
||||
base_path = tmp_path / "meta_lib"
|
||||
save_library(library, str(base_path))
|
||||
|
||||
loaded = load_library(str(base_path))
|
||||
assert loaded.size == 2
|
||||
|
||||
f1_loaded = loaded.get_factor(1)
|
||||
assert f1_loaded.metadata.get("author") == "ai"
|
||||
assert not f1_loaded.metadata.get("unsupported", False)
|
||||
|
||||
f2_loaded = loaded.get_factor(2)
|
||||
assert f2_loaded.metadata.get("unsupported") is True
|
||||
|
||||
def test_factor_round_trip_with_metadata(self) -> None:
|
||||
"""Factor.to_dict / from_dict 应正确传递 metadata."""
|
||||
factor = Factor(
|
||||
id=1,
|
||||
name="round_trip",
|
||||
formula="ts_mean(close, 20)",
|
||||
category="Momentum",
|
||||
ic_mean=0.1,
|
||||
icir=1.0,
|
||||
ic_win_rate=0.6,
|
||||
max_correlation=0.2,
|
||||
batch_number=2,
|
||||
metadata={"unsupported": True, "tags": ["test"]},
|
||||
)
|
||||
d = factor.to_dict()
|
||||
restored = Factor.from_dict(d)
|
||||
assert restored.metadata == factor.metadata
|
||||
|
||||
|
||||
class TestImportFromPaper:
|
||||
"""测试从内置 paper catalog 导入因子."""
|
||||
|
||||
def test_import_from_paper_includes_all_translated_factors(self) -> None:
|
||||
"""内置 PAPER_FACTORS 应全部成功导入."""
|
||||
library = import_from_paper()
|
||||
assert library.size > 0
|
||||
# 当前 catalog 中已有因子应全部被 admit
|
||||
for factor in library.list_factors():
|
||||
assert factor.id > 0
|
||||
assert factor.name
|
||||
assert factor.formula
|
||||
assert factor.category
|
||||
|
||||
def test_import_from_paper_marks_todo_as_unsupported(self, tmp_path: Path) -> None:
|
||||
"""对 # TODO 公式应在 metadata 中标记 unsupported."""
|
||||
custom_path = tmp_path / "custom_factors.json"
|
||||
custom_data = [
|
||||
{
|
||||
"name": "Normal Factor",
|
||||
"formula": "cs_rank(close)",
|
||||
"category": "Test",
|
||||
},
|
||||
{
|
||||
"name": "Unsupported Factor",
|
||||
"formula": "# TODO: Neg(CsRank(Decay(close, 10)))",
|
||||
"category": "Test",
|
||||
},
|
||||
]
|
||||
custom_path.write_text(json.dumps(custom_data), encoding="utf-8")
|
||||
|
||||
library = import_from_paper(str(custom_path))
|
||||
assert library.size == 2
|
||||
|
||||
normal = library.list_factors()[0]
|
||||
todo = library.list_factors()[1]
|
||||
|
||||
assert normal.metadata.get("unsupported") is None
|
||||
assert todo.metadata.get("unsupported") is True
|
||||
|
||||
def test_import_from_paper_path_override(self, tmp_path: Path) -> None:
|
||||
"""通过 path 参数加载外部 JSON 列表."""
|
||||
custom_path = tmp_path / "override.json"
|
||||
custom_data = [
|
||||
{"name": "custom_1", "formula": "open + close", "category": "Custom"},
|
||||
]
|
||||
custom_path.write_text(json.dumps(custom_data), encoding="utf-8")
|
||||
|
||||
library = import_from_paper(str(custom_path))
|
||||
assert library.size == 1
|
||||
assert library.list_factors()[0].name == "custom_1"
|
||||
Reference in New Issue
Block a user