polars-ta 0.5.4__py3-none-any.whl → 0.5.5__py3-none-any.whl

polars_ta/_version.py

@@ -1 +1 @@
-__version__ = "0.5.4"
+__version__ = "0.5.5"

polars_ta/prefix/vec.py

@@ -0,0 +1,17 @@
+# this code is auto generated by tools/prefix_vec.py
+
+from polars_ta.wq.vector import vec_avg as cs_vec_avg  # noqa
+from polars_ta.wq.vector import vec_choose as cs_vec_choose  # noqa
+from polars_ta.wq.vector import vec_count as cs_vec_count  # noqa
+from polars_ta.wq.vector import vec_ir as cs_vec_ir  # noqa
+from polars_ta.wq.vector import vec_kurtosis as cs_vec_kurtosis  # noqa
+from polars_ta.wq.vector import vec_l2_norm as cs_vec_l2_norm  # noqa
+from polars_ta.wq.vector import vec_max as cs_vec_max  # noqa
+from polars_ta.wq.vector import vec_min as cs_vec_min  # noqa
+from polars_ta.wq.vector import vec_norm as cs_vec_norm  # noqa
+from polars_ta.wq.vector import vec_percentage as cs_vec_percentage  # noqa
+from polars_ta.wq.vector import vec_powersum as cs_vec_powersum  # noqa
+from polars_ta.wq.vector import vec_range as cs_vec_range  # noqa
+from polars_ta.wq.vector import vec_skewness as cs_vec_skewness  # noqa
+from polars_ta.wq.vector import vec_stddev as cs_vec_stddev  # noqa
+from polars_ta.wq.vector import vec_sum as cs_vec_sum  # noqa

polars_ta/ta/overlap.py

@@ -39,7 +39,7 @@ def EMA(close: Expr, timeperiod: int = 30) -> Expr:
 
     """
     # 相当于alpha=2/(1+timeperiod)
-    return close.ewm_mean(span=timeperiod, adjust=False, min_periods=timeperiod)
+    return close.ewm_mean(span=timeperiod, adjust=False, min_samples=timeperiod)
 
 
 def KAMA(close: Expr, timeperiod: int = 30) -> Expr:
@@ -78,7 +78,7 @@ def RMA(close: Expr, timeperiod: int = 30) -> Expr:
     https://github.com/twopirllc/pandas-ta/blob/main/pandas_ta/overlap/rma.py
 
     """
-    return close.ewm_mean(alpha=1 / timeperiod, adjust=False, min_periods=timeperiod)
+    return close.ewm_mean(alpha=1 / timeperiod, adjust=False, min_samples=timeperiod)
 
 
 def TEMA(close: Expr, timeperiod: int = 30) -> Expr:

polars_ta/tdx/reference.py

@@ -85,7 +85,7 @@ def DMA(close: Expr, alpha: float = 0.5) -> Expr:
 
     求X的动态移动平均.
     算法:Y=A*X+(1-A)*Y',其中Y'表示上一周期Y值,A必须大于0且小于1.A支持变量"""
-    return close.ewm_mean(alpha=alpha, adjust=False, min_periods=1)
+    return close.ewm_mean(alpha=alpha, adjust=False, min_samples=1)
 
 
 def EMA(close: Expr, N: int = 30) -> Expr:
@@ -113,7 +113,7 @@ def EXPMEMA(close: Expr, N: int = 30) -> Expr:
     """
     sma = MA(close, N)
     x = when(close.cum_count() < N).then(sma).otherwise(close)
-    return x.ewm_mean(span=N, adjust=False, min_periods=1)
+    return x.ewm_mean(span=N, adjust=False, min_samples=1)
 
 
 def HOD(close: Expr, N: int = 30) -> Expr:
@@ -156,7 +156,7 @@ def SMA_CN(X: Expr, N: int, M: int) -> Expr:
 
     !!!为防止与talib版SMA误用，这里去了默认值1
     """
-    return X.ewm_mean(alpha=M / N, adjust=False, min_periods=1)
+    return X.ewm_mean(alpha=M / N, adjust=False, min_samples=1)
 
 
 def SUMIF(condition: Expr, close: Expr, N: int = 30) -> Expr:

polars_ta/utils/withs.py

@@ -0,0 +1,44 @@
+import re
+
+import polars as pl
+
+
+def with_industry(df: pl.DataFrame, industry_name: str, drop_first: bool, keep_col: bool) -> pl.DataFrame:
+    """添加行业哑元变量
+
+    Parameters
+    ----------
+    df
+    industry_name:str
+        行业列名
+    drop_first
+        丢弃第一列
+    keep_col
+        是否保留源列
+
+    Returns
+    -------
+    pl.DataFrame
+
+    """
+    df = df.with_columns([
+        # 行业处理，由浮点改成整数
+        pl.col(industry_name).cast(pl.UInt32),
+    ])
+
+    # TODO 没有行业的也过滤，这会不会有问题？已经退市了，但引入了未来数据
+    df = df.filter(
+        pl.col(industry_name).is_not_null(),
+    )
+
+    if keep_col:
+        df = df.with_columns(df.to_dummies(industry_name, drop_first=False))
+    else:
+        df = df.to_dummies(industry_name, drop_first=False)
+
+    if drop_first:
+        # drop_first丢弃哪个字段是随机的，非常不友好，只能在行业中性化时动态修改代码
+        industry_columns = sorted(filter(lambda x: re.search(rf"^{industry_name}_\d+$", x), df.columns))
+        return df.drop(industry_columns[0])
+    else:
+        return df

polars_ta/wq/cross_sectional.py

@@ -56,7 +56,9 @@ def cs_one_side(x: Expr, is_long: bool = True) -> Expr:
 
 
 def cs_scale(x: Expr, scale_: float = 1, long_scale: float = 1, short_scale: float = 1) -> Expr:
-    """横截面上，将输入数据进行比例调整。此外，可通过向运算符添加额外参数，将多头头寸和空头头寸分别映射到独立的缩放比例上
+    """横截面上，将输入数据进行比例调整
+
+    此外，可通过向运算符添加额外参数，将多头头寸和空头头寸分别映射到独立的缩放比例上
 
     Scales input to booksize. We can also scale the long positions and short positions to separate scales by mentioning additional parameters to the operator.
 
@@ -211,6 +213,16 @@ def cs_fill_mean(x: Expr) -> Expr:
     return x.fill_null(strategy='mean')
 
 
+def cs_fill_max(x: Expr) -> Expr:
+    """横截面上，填充`null`为最大值"""
+    return x.fill_null(strategy='max')
+
+
+def cs_fill_min(x: Expr) -> Expr:
+    """横截面上，填充`null`为最小值"""
+    return x.fill_null(strategy='min')
+
+
 def cs_fill_null(x: Expr, value: float = 0) -> Expr:
     """横截面上，填充`null`为`value`"""
     return x.fill_null(value)
@@ -227,7 +239,7 @@ def cs_regression_proj(y: Expr, x: Expr) -> Expr:
 
 
 def cs_rank(x: Expr, pct: bool = True) -> Expr:
-    """横截面排名。
+    """横截面排名
 
     Ranks the input among all the instruments and returns an equally distributed number between 0.0 and 1.0. For precise sort, use the rate as 0.
 

polars_ta/wq/preprocess.py

@@ -1,9 +1,18 @@
+"""
+补空值 → 去极值 → 标准化 → 中性化 → 标准化（可选二次标准化）
+
+# 对数市值。去极值
+MC_LOG = cs_quantile(log1p(market_cap), 0.01, 0.99)
+# 对数市值。标准化。供其他因子市值中性化时使用
+MC_NORM = cs_zscore(MC_LOG)
+# 对数市值。行业中性化。直接作为因子使用
+MC_NEUT = cs_zscore(cs_resid(MC_NORM, CS_SW_L1, ONE))
+
+"""
 import polars_ols as pls
 from polars import Expr, when
 from polars_ols.least_squares import OLSKwargs
 
-from polars_ta.wq.cross_sectional import cs_rank
-
 
 # ======================
 # standardize
@@ -23,7 +32,7 @@ def cs_minmax(x: Expr) -> Expr:
 
 # ======================
 # winsorize
-def cs_quantile(x: Expr, low_limit: float = 0.025, up_limit: float = 0.995) -> Expr:
+def cs_quantile(x: Expr, low_limit: float = 0.025, up_limit: float = 0.975) -> Expr:
     """横截面分位数去极值"""
     a = x.quantile(low_limit)
     b = x.quantile(up_limit)
@@ -81,6 +90,11 @@ def cs_resid(y: Expr, *more_x: Expr) -> Expr:
     return pls.compute_least_squares(y, *more_x, mode='residuals', ols_kwargs=_ols_kwargs)
 
 
+def cs_zscore_resid(y: Expr, *more_x: Expr) -> Expr:
+    """横截面标准化、中性化"""
+    return cs_resid(cs_zscore(y), *more_x)
+
+
 def cs_mad_zscore(y: Expr) -> Expr:
     """横截面去极值、标准化"""
     return cs_zscore(cs_mad(y))
@@ -91,27 +105,6 @@ def cs_mad_zscore_resid(y: Expr, *more_x: Expr) -> Expr:
     return cs_resid(cs_zscore(cs_mad(y)), *more_x)
 
 
-def cs_mad_rank(y: Expr) -> Expr:
-    """横截面去极值、排名"""
-    return cs_rank(cs_mad(y))
-
-
-def cs_mad_rank2(y: Expr, m: float) -> Expr:
-    """横截面去极值，排名，移动峰或谷到零点，然后平方。非线性处理
-
-    适合于分层收益V型或倒V的情况"""
-    return (cs_rank(cs_mad(y)) - m) ** 2
-
-
-def cs_mad_rank2_resid(y: Expr, m: float, *more_x: Expr) -> Expr:
-    """横截面去极值，排名，移动峰或谷到零点，然后平方。回归取残差。非线性处理
-
-    适合于分层收益V型或倒V的情况"""
-    return cs_resid((cs_rank(cs_mad(y)) - m) ** 2, *more_x)
-
-
-def cs_rank2(y: Expr, m: float) -> Expr:
-    """横截面移动峰或谷到零点，然后平方。非线性处理
-
-    适合于分层收益V型或倒V的情况"""
-    return (cs_rank(y) - m) ** 2
+def cs_mad_zscore_resid_zscore(y: Expr, *more_x: Expr) -> Expr:
+    """横截面去极值、标准化、中性化、二次标准化"""
+    return cs_zscore(cs_resid(cs_zscore(cs_mad(y)), *more_x))

polars_ta/wq/time_series.py

@@ -12,7 +12,9 @@ from polars_ta.wq._nb import roll_argmax, roll_argmin, roll_co_kurtosis, roll_co
 
 
 def ts_arg_max(x: Expr, d: int = 5, reverse: bool = True, min_samples: Optional[int] = None) -> Expr:
-    """窗口内最大值出现的相对位置，最近的一天记为第 0 天，最远的一天为第 d-1 天
+    """最大值相对位置
+
+    最近的一天记为第 0 天，最远的一天为第 d-1 天
 
     Returns the relative index of the max value in the time series for the past d days.
     If the current day has the max value for the past d days, it returns 0.
@@ -63,7 +65,9 @@ def ts_arg_max(x: Expr, d: int = 5, reverse: bool = True, min_samples: Optional[
 
 
 def ts_arg_min(x: Expr, d: int = 5, reverse: bool = True, min_samples: Optional[int] = None) -> Expr:
-    """窗口内最小值出现的相对位置，最近的一天记为第 0 天，最远的一天为第 d-1 天
+    """最小值相对位置
+
+    最近的一天记为第 0 天，最远的一天为第 d-1 天
 
     Parameters
     ----------
@@ -753,7 +757,7 @@ def ts_returns(x: Expr, d: int = 1) -> Expr:
 
 
 def ts_scale(x: Expr, d: int = 5, min_samples: Optional[int] = None) -> Expr:
-    """时序滚动缩放
+    """时序滚动缩放。相当于ts_minmax
 
     Returns (x – ts_min(x, d)) / (ts_max(x, d) – ts_min(x, d)) + constant
 

{polars_ta-0.5.4.dist-info → polars_ta-0.5.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: polars_ta
-Version: 0.5.4
+Version: 0.5.5
 Summary: polars expressions
 Author-email: wukan <wu-kan@163.com>
 License: MIT License
@@ -91,7 +91,7 @@ df = df.with_columns([
 ])
 ```
 
-When both `min_periods` and `MIN_SAMPLES` are set, `min_periods` takes precedence. default value is `None`.
+When both `min_samples` and `MIN_SAMPLES` are set, `min_samples` takes precedence. default value is `None`.
 
 ```python
 import polars_ta
@@ -194,7 +194,7 @@ df = df.with_columns([
 ])
 ```
 
-当`min_periods`和`MIN_SAMPLES`都设置时，以`min_periods`为准，默认值为`None`
+当`min_samples`和`MIN_SAMPLES`都设置时，以`min_samples`为准，默认值为`None`
 
 ```python
 import polars_ta

{polars_ta-0.5.4.dist-info → polars_ta-0.5.5.dist-info}/RECORD

@@ -1,5 +1,5 @@
 polars_ta/__init__.py,sha256=ig6f6c1AMSpntwKjqaX3msBzVIwkI7J776IujEmiuvA,123
-polars_ta/_version.py,sha256=DITpct-LrdIsTgwx2NgH5Ghx5y8Xgz1YMimy1ZV5RTY,22
+polars_ta/_version.py,sha256=78mfpLewKVki6c9UONSUdlVme_JsN9ZwIfp4Hf4jmG0,22
 polars_ta/noise.py,sha256=LJHubBqnWlU3Bz84z07N1JB-b-hAMW2rgBF1BT4m0FE,1471
 polars_ta/candles/__init__.py,sha256=AW68IuFC0gD4_OyjwLP3p22WSzSIYqlSrsS9fW_15xw,141
 polars_ta/candles/cdl1.py,sha256=RnRu1QzpqEt5y0-1hlfZRUvza1no-Gj4x_dx2QWxr5A,3130
@@ -18,6 +18,7 @@ polars_ta/prefix/reports.py,sha256=B2QgdfX6RbZu9ytgaINv3Aq-ZAh_m3cr2pgbpFyL35A,4
 polars_ta/prefix/ta.py,sha256=qIb3oRmexNZ6LTQ35V194QTLqj8UgzjaYl5ASwqN5pc,4167
 polars_ta/prefix/talib.py,sha256=6JsrkgDIUsR2bIA7jVywxgWwxiiFuzsCPvbDeAt4qBA,9392
 polars_ta/prefix/tdx.py,sha256=EttaExzqoA3Y3lD-YKA32-5GfJ6jgKjt-nRuoeuK0wQ,11429
+polars_ta/prefix/vec.py,sha256=jQ0w3ECn60j5Uefxe_-4bD1d_iQIvwOfXoXpcP1Bp4E,1055
 polars_ta/prefix/wq.py,sha256=PpSLQQ3vD0Mf3Tiz_AFSi--q8p7CkLg9CHh_ayMfoYo,35
 polars_ta/reports/__init__.py,sha256=KEATtWxhdaO6XScHYN2XE4WkYbYpQvDOEyXgyc2z22g,45
 polars_ta/reports/cicc.py,sha256=ZpNzHo5h855Xo9IeKeOzlUjjwE5tR8opb11UoJVxGkg,707
@@ -25,7 +26,7 @@ polars_ta/ta/README.md,sha256=XuDf1sMxNrq9QDEiwBaP8cp-skTK3Jr5VClxhsNiYJ4,647
 polars_ta/ta/__init__.py,sha256=GRI1suzvmLxfyfXAik4zsxqLaijq5MRCO-fUx3qaCl0,351
 polars_ta/ta/momentum.py,sha256=-W-wZ1oQE9QiUiVgEx7fvnCEkWJnW6j9CxA7Mc-WMGg,5623
 polars_ta/ta/operators.py,sha256=H_ORq1SeFKLj58vrOTAIa-X135evZNyo4ZE7gaH_7VM,3711
-polars_ta/ta/overlap.py,sha256=Q2A8BSF9tcTdEg269LQ97ia55H0LaY_vxfBYG6j2EQE,3023
+polars_ta/ta/overlap.py,sha256=imoEVrFrv_P1ueg5KbPBTDEnsekNaxunL5U9BzDNxKE,3023
 polars_ta/ta/price.py,sha256=ME26yPPZk1kf7XDna53mmUrX7P1NDNq3trrZ_sCbZ_A,1013
 polars_ta/ta/statistic.py,sha256=dS5dPBszbdlroJ9u5aXBniJmKgPQnuh9zE7miYKzICs,968
 polars_ta/ta/transform.py,sha256=c4s5l6khVqIer50g6oScdZ1EEPWYANeKm64AkBkPrtY,1789
@@ -47,7 +48,7 @@ polars_ta/tdx/over_bought_over_sold.py,sha256=zB5W10TZBpKrMdzZlH9jmiVqLhrkcXdNI0
 polars_ta/tdx/pattern.py,sha256=jB0a5Ro0SQ25R5B_mkQWl9Hz7aB9n-DUns1OSxPeHxI,1636
 polars_ta/tdx/pattern_feature.py,sha256=D3_nyntC2UnvYL3smBYbADoxyh1oGkpWAI4E6Uqh8ZM,8746
 polars_ta/tdx/pressure_support.py,sha256=Lk_6nXImyWLuloP4rBwarp5LEVZjgr6_5ekxIksZPr8,1085
-polars_ta/tdx/reference.py,sha256=5F6ezUyjUobTXwd7dniOmDoDJsw3uo5HzaHSS9-R0CI,6298
+polars_ta/tdx/reference.py,sha256=bij16Axl-ICVu4q9NQCQmXfZqcFAYxGCNb8_TSbmy2g,6298
 polars_ta/tdx/statistic.py,sha256=jdNLx3nV-uN4LrHRGxUUMhNOnlu8MOozjIHvshgMNPg,2588
 polars_ta/tdx/trend.py,sha256=n5HDHhb1Qak39DJjMFx27hFTYSttbNFeXJD7saRiTMo,3008
 polars_ta/tdx/trend_feature.py,sha256=uNc4Z46Kyd7Prl0Ftl2ljSAXztTzQtbO28p7gy8iMvM,9086
@@ -57,18 +58,19 @@ polars_ta/utils/helper.py,sha256=rqxBhmA-RhpHd1-qxdYi7OEZloQpPxR30Kz8fJ_hLic,625
 polars_ta/utils/numba_.py,sha256=P0z-81mabX_9zyJOX0Ib1CFmvPl9-SSatzki3dOciVA,5972
 polars_ta/utils/pandas_.py,sha256=codb51l45TUMngY55twQaUPUxnffjvj8UEOm35zFpNE,1989
 polars_ta/utils/pit.py,sha256=YNgUE6mbwhrtA-7wyOL0PCUDdwfTQouXwage-cK6efY,4312
+polars_ta/utils/withs.py,sha256=cMSRHTyoFoG0qN5NZgx8D2HjmSJzqkE1MZRNiylMPtY,1167
 polars_ta/utils/wrapper.py,sha256=jbR-ZQdzBf5iWvtnJ1HsN9HdepmDbU7fUj4w8Bt2BkU,3422
 polars_ta/wq/__init__.py,sha256=C3YYJc997XCUI7H_afGT_mj2m4UdHMcql4sboCVvrXU,327
 polars_ta/wq/_nb.py,sha256=9N7afRiABqdjO1QPnRlP1RIKJ98cQLpv6nF3dsqUA6k,11281
 polars_ta/wq/_slow.py,sha256=MfWg9FYX8NGNLWN4ezI_awf3pPTqhSq_zo0LOS4nCzw,937
 polars_ta/wq/arithmetic.py,sha256=NwyX-K8j9ul7XHHSNuGimBq6f3NvcOGQ4le5PQuaRPc,26346
-polars_ta/wq/cross_sectional.py,sha256=1unrHaPPDQIZACg0CepWn3CXvd_zmQWjNwbXzqZXke8,14518
+polars_ta/wq/cross_sectional.py,sha256=4HFs9QDx4Vfmxr3XfjmUwGZNc07D5Z2buKZmwD4x1rs,14768
 polars_ta/wq/logical.py,sha256=PfcPrY3iYoYFDTJ-B1IlCfpab1uTWV7GN1TdRtjauEk,2241
-polars_ta/wq/preprocess.py,sha256=Zpjv7zpU690Ugr5PNnq6CNlUn5qD9sH0SQr5q5AFtys,3444
-polars_ta/wq/time_series.py,sha256=KGVgFSQWiDAOpN7nW0rPE8UE81Q3Co9WwZiY1DWs3KQ,33164
+polars_ta/wq/preprocess.py,sha256=Wb-n5HccciexrfMmL8-WJvMkMeDXMGYAf0mrurXE3kI,3297
+polars_ta/wq/time_series.py,sha256=nywBEfkVrTsUgyUL7NCSMUSBoLm09e0ToCp9zwrxbvM,33155
 polars_ta/wq/transformational.py,sha256=HBnxQiS2Pw0fHnRW-aLqbznQVl1SSbZ9OqZG62igiJk,7266
 polars_ta/wq/vector.py,sha256=Qs-mHC2YsiWXoyMuXZZPzd5W5w_HL1ZgDCj9wRAnqmQ,1902
-polars_ta-0.5.4.dist-info/METADATA,sha256=YuA2qBXp9R4_9PbOLyk-ZhjiUdTnNLxXKQmZPvpIjc8,8839
-polars_ta-0.5.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-polars_ta-0.5.4.dist-info/licenses/LICENSE,sha256=nREFtfwxWCCYD-ZA1jMzhhxMyTz-wGWFlnkpgg0DCtQ,1062
-polars_ta-0.5.4.dist-info/RECORD,,
+polars_ta-0.5.5.dist-info/METADATA,sha256=XXh2IiEyvAH7YE4owO0HxmhM6Vczw1mSSftiCk7HXig,8839
+polars_ta-0.5.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+polars_ta-0.5.5.dist-info/licenses/LICENSE,sha256=nREFtfwxWCCYD-ZA1jMzhhxMyTz-wGWFlnkpgg0DCtQ,1062
+polars_ta-0.5.5.dist-info/RECORD,,