claude_dev
3fbe6c9be5
- 添加 vnpy_v4.4.0/ 目录到版本控制 - 删除嵌入的 .git 目录避免嵌套仓库 - 添加 README_SANGUO.md 说明来源和用途 - 更新 .gitignore 移除 vnpy_v4.4.0/ 忽略规则 上游代码信息: - 项目: VeighNa 量化交易平台 - 版本: 4.4.0 - 来源: https://github.com/vnpy/vnpy 用途: 版本参考、代码学习、差异对比、离线开发 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
65 lines
1.7 KiB
Python
65 lines
1.7 KiB
Python
"""
|
|
Cross Section Operators
|
|
"""
|
|
|
|
import polars as pl
|
|
|
|
from .utility import DataProxy
|
|
|
|
|
|
def cs_rank(feature: DataProxy) -> DataProxy:
|
|
"""Perform cross-sectional ranking"""
|
|
df: pl.DataFrame = feature.df.select(
|
|
pl.col("datetime"),
|
|
pl.col("vt_symbol"),
|
|
pl.col("data").rank().over("datetime")
|
|
)
|
|
return DataProxy(df)
|
|
|
|
|
|
def cs_mean(feature: DataProxy) -> DataProxy:
|
|
"""Calculate cross-sectional mean"""
|
|
df: pl.DataFrame = feature.df.select(
|
|
pl.col("datetime"),
|
|
pl.col("vt_symbol"),
|
|
pl.col("data").mean().over("datetime")
|
|
)
|
|
return DataProxy(df)
|
|
|
|
|
|
def cs_std(feature: DataProxy) -> DataProxy:
|
|
"""Calculate cross-sectional standard deviation"""
|
|
df: pl.DataFrame = feature.df.select(
|
|
pl.col("datetime"),
|
|
pl.col("vt_symbol"),
|
|
pl.col("data").std().over("datetime")
|
|
)
|
|
return DataProxy(df)
|
|
|
|
|
|
def cs_sum(feature: DataProxy) -> DataProxy:
|
|
"""Calculate cross-sectional sum"""
|
|
df: pl.DataFrame = feature.df.select(
|
|
pl.col("datetime"),
|
|
pl.col("vt_symbol"),
|
|
pl.col("data").sum().over("datetime")
|
|
)
|
|
return DataProxy(df)
|
|
|
|
|
|
def cs_scale(feature: DataProxy) -> DataProxy:
|
|
"""Scale the feature by the sum of absolute values in the cross section"""
|
|
abs_feature = abs(feature)
|
|
sum_abs = cs_sum(abs_feature)
|
|
|
|
df_merged: pl.DataFrame = feature.df.join(sum_abs.df, on=["datetime", "vt_symbol"], suffix="_sum")
|
|
|
|
df: pl.DataFrame = df_merged.with_columns(
|
|
pl.when(pl.col("data_sum") != 0)
|
|
.then(pl.col("data") / pl.col("data_sum"))
|
|
.otherwise(0)
|
|
.alias("data")
|
|
).select(["datetime", "vt_symbol", "data"])
|
|
|
|
return DataProxy(df)
|