pyalloq-features 0.1.5__tar.gz

pyalloq_features-0.1.5/PKG-INFO

@@ -0,0 +1,40 @@
+Metadata-Version: 2.3
+Name: pyalloq-features
+Version: 0.1.5
+Summary: Feature Transformations and pipelines for pyalloq.
+Author: Siddeshkanth
+Author-email: Siddeshkanth <pyalloq-info@alloq-alpha.com>
+Requires-Dist: numpy>=1.24
+Requires-Dist: pandas>=2.0
+Requires-Dist: scikit-learn>=1.3.0
+Requires-Dist: scipy>=1.10.0
+Requires-Dist: ta-lib>=0.4.28
+Requires-Dist: pyalloq-core>=0.1.0
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+
+# pyalloq-features
+
+`pyalloq-features` provides feature engineering transformers, TA-Lib indicator integration, scaling utilities, and feature pipeline orchestration for **PyAlloq**.
+
+## Key Modules
+
+- **`BaseFeatureTransformer`**: Abstract base class for all feature transformation modules operating on `MarketData`.
+- **`TechnicalIndicator`**: Applies TA-Lib technical indicators (e.g., `SMA`, `RSI`, `MACD`, `ATR`, `BBANDS`) across asset columns of a 2D DataFrame and appends resulting features to `MarketData.features`.
+- **`FeaturePipeline`**: Sequential feature pipeline builder for chaining feature transformers.
+- **`scalers`**: Cross-sectional and time-series feature normalization and standardization utilities.
+
+## Quick Example
+
+```python
+from pyalloq_features.transformers.technical import TechnicalIndicator
+from pyalloq_features.core.pipeline import FeaturePipeline
+
+# Define feature engineering pipeline
+pipeline = FeaturePipeline()
+pipeline.add(TechnicalIndicator(indicator="RSI", timeperiod=14))
+pipeline.add(TechnicalIndicator(indicator="SMA", timeperiod=50))
+
+# Apply transformations directly to MarketData
+# updated_data = pipeline.run(market_data)
+```

pyalloq_features-0.1.5/README.md

@@ -0,0 +1,25 @@
+# pyalloq-features
+
+`pyalloq-features` provides feature engineering transformers, TA-Lib indicator integration, scaling utilities, and feature pipeline orchestration for **PyAlloq**.
+
+## Key Modules
+
+- **`BaseFeatureTransformer`**: Abstract base class for all feature transformation modules operating on `MarketData`.
+- **`TechnicalIndicator`**: Applies TA-Lib technical indicators (e.g., `SMA`, `RSI`, `MACD`, `ATR`, `BBANDS`) across asset columns of a 2D DataFrame and appends resulting features to `MarketData.features`.
+- **`FeaturePipeline`**: Sequential feature pipeline builder for chaining feature transformers.
+- **`scalers`**: Cross-sectional and time-series feature normalization and standardization utilities.
+
+## Quick Example
+
+```python
+from pyalloq_features.transformers.technical import TechnicalIndicator
+from pyalloq_features.core.pipeline import FeaturePipeline
+
+# Define feature engineering pipeline
+pipeline = FeaturePipeline()
+pipeline.add(TechnicalIndicator(indicator="RSI", timeperiod=14))
+pipeline.add(TechnicalIndicator(indicator="SMA", timeperiod=50))
+
+# Apply transformations directly to MarketData
+# updated_data = pipeline.run(market_data)
+```

pyalloq_features-0.1.5/pyproject.toml

@@ -0,0 +1,26 @@
+[build-system]
+requires = ["uv_build>=0.10.9,<0.11.0"]
+build-backend = "uv_build"
+
+[project]
+name = "pyalloq-features"
+version = "0.1.5"
+description = "Feature Transformations and pipelines for pyalloq."
+readme = "README.md"
+requires-python = ">=3.11"
+authors = [{ name = "Siddeshkanth", email = "pyalloq-info@alloq-alpha.com" }]
+
+dependencies = [
+  "numpy>=1.24",
+  "pandas>=2.0",
+  "scikit-learn>=1.3.0",
+  "scipy>=1.10.0",
+  "TA-Lib>=0.4.28",
+  "pyalloq-core>=0.1.0"
+]
+
+[dependency-groups]
+dev = ["pytest>=8", "ruff>=0.6", "mypy>=1.11"]
+
+[tool.setuptools.packages.find]
+where = ["src/"]

pyalloq_features-0.1.5/src/pyalloq_features/core/base.py

@@ -0,0 +1,17 @@
+from abc import ABC, abstractmethod
+from pyalloq_core.data import MarketData
+
+
+class BaseFeatureTransformer(ABC):
+    """
+    Abstract interface for all feature engineering modules.
+    Operates directly on the MarketData dataclass.
+    """
+
+    def fit(self, data: MarketData) -> "BaseFeatureTransformer":
+        return self
+
+    @abstractmethod
+    def transform(self, data: MarketData) -> MarketData:
+        """Applies transformation and strictly appends new columns."""
+        ...

pyalloq_features-0.1.5/src/pyalloq_features/core/pipeline.py

@@ -0,0 +1,18 @@
+from .base import BaseFeatureTransformer
+from pyalloq_core.data import MarketData
+
+
+class FeaturePipeline:
+    def __init__(self):
+        self.steps = []
+
+    def add(self, transformer: BaseFeatureTransformer) -> "FeaturePipeline":
+        self.steps.append(transformer)
+        return self
+
+    def run(self, data: MarketData) -> MarketData:
+        current_data = data
+        for step in self.steps:
+            current_data = step.transform(current_data)
+
+        return current_data

pyalloq_features-0.1.5/src/pyalloq_features/py.typed

@@ -0,0 +1 @@
+# Marker file for PEP 561

pyalloq_features-0.1.5/src/pyalloq_features/scalers/rolling.py

@@ -0,0 +1,27 @@
+from pyalloq_features.core.base import BaseFeatureTransformer
+from pyalloq_core.data import MarketData
+
+
+class RollingZScoreScaler(BaseFeatureTransformer):
+    """Point-in-Time Z-Score normalization utilizing backward-looking statistics."""
+
+    def __init__(self, target_feature: str, window: int = 252) -> None:
+        self.target_feature = target_feature
+        self.window = window
+        self.out_col = f"{target_feature}_zscore_{window}"
+
+    def transform(self, data: MarketData) -> MarketData:
+        df_feature = data.features[self.target_feature]
+
+        rolling_view = df_feature.rolling(
+            window=self.window, min_periods=self.window // 2
+        )
+        rolling_mean = rolling_view.mean()
+        rolling_std = rolling_view.std()
+
+        epsilon = 1e-8
+        data.features[self.out_col] = (df_feature - rolling_mean) / (
+            rolling_std + epsilon
+        )
+
+        return data

pyalloq_features-0.1.5/src/pyalloq_features/transformers/cross_sectional.py

@@ -0,0 +1,20 @@
+from pyalloq_features.core.base import BaseFeatureTransformer
+from pyalloq_core.data import MarketData
+
+
+class CrossSectionalRank(BaseFeatureTransformer):
+    """
+    Ranks a feature cross-sectionality across all available assets at timestamp T.
+    """
+
+    def __init__(self, target_feature: str) -> None:
+        self.target_feature = target_feature
+        self.out_col = f"{target_feature}_cs_rank"
+
+    def transform(self, data: MarketData) -> MarketData:
+        df_features = data.features[self.target_feature]
+
+        cs_rank = df_features.rank(axis=1, pct=True)
+        data.features[self.out_col] = cs_rank
+
+        return data

pyalloq_features-0.1.5/src/pyalloq_features/transformers/technical.py

@@ -0,0 +1,48 @@
+import talib
+from pyalloq_features.core.base import BaseFeatureTransformer
+from pyalloq_core.data import MarketData
+import pandas as pd
+import numpy as np
+
+
+class TechnicalIndicator(BaseFeatureTransformer):
+    """
+    Applies TA-Lib functions across the asset columns of a 2D DataFrame.
+    """
+
+    def __init__(
+        self,
+        indicator: str,
+        source: str = "prices",
+        **kwargs,
+    ) -> None:
+        self.indicator_name = indicator.upper()
+        self.source = source  # prices or a key in data.features
+        self.kwargs = kwargs
+        self._func = getattr(talib, self.indicator_name)
+
+        params_str = "_".join([str(v) for v in self.kwargs.values()])
+        self.out_col = (
+            f"{self.indicator_name}_{params_str}" if params_str else self.indicator_name
+        )
+
+    def transform(self, data: MarketData) -> MarketData:
+        if self.source == "prices":
+            df_source = data.prices
+        else:
+            df_source = data.features[self.source]
+
+        df_out = pd.DataFrame(
+            index=df_source.index, columns=df_source.columns, dtype=np.float64
+        )
+
+        for ticker in df_source.columns:
+            asset_series = df_source[ticker].to_numpy()
+            try:
+                df_out[ticker] = self._func(asset_series, **self.kwargs)
+            except Exception:
+                pass
+
+        data.features[self.out_col] = df_out
+
+        return data