featcopilot 0.1.0__py3-none-any.whl

featcopilot/utils/parallel.py

@@ -0,0 +1,109 @@
+"""Parallel processing utilities."""
+
+from typing import Any, Callable, Optional
+
+import pandas as pd
+
+
+def parallel_apply(
+    func: Callable,
+    data: pd.DataFrame,
+    n_jobs: int = -1,
+    batch_size: Optional[int] = None,
+    verbose: bool = False,
+) -> list[Any]:
+    """
+    Apply a function in parallel across DataFrame rows.
+
+    Parameters
+    ----------
+    func : callable
+        Function to apply to each row
+    data : DataFrame
+        Input data
+    n_jobs : int, default=-1
+        Number of parallel jobs (-1 for all CPUs)
+    batch_size : int, optional
+        Batch size for processing
+    verbose : bool, default=False
+        Show progress
+
+    Returns
+    -------
+    results : list
+        Results from applying function to each row
+    """
+    try:
+        from joblib import Parallel, delayed
+
+        if n_jobs == -1:
+            import os
+
+            n_jobs = os.cpu_count() or 1
+
+        if batch_size is None:
+            batch_size = max(1, len(data) // (n_jobs * 4))
+
+        results = Parallel(n_jobs=n_jobs, verbose=1 if verbose else 0)(delayed(func)(row) for _, row in data.iterrows())
+
+        return results
+
+    except ImportError:
+        # Fallback to sequential processing
+        if verbose:
+            print("joblib not available, using sequential processing")
+
+        return [func(row) for _, row in data.iterrows()]
+
+
+def parallel_transform(
+    transformers: list[tuple], X: pd.DataFrame, n_jobs: int = -1, verbose: bool = False
+) -> pd.DataFrame:
+    """
+    Apply multiple transformers in parallel.
+
+    Parameters
+    ----------
+    transformers : list
+        List of (name, transformer) tuples
+    X : DataFrame
+        Input data
+    n_jobs : int, default=-1
+        Number of parallel jobs
+    verbose : bool, default=False
+        Show progress
+
+    Returns
+    -------
+    X_combined : DataFrame
+        Combined transformed data
+    """
+    try:
+        from joblib import Parallel, delayed
+
+        def apply_transformer(name, transformer, X):
+            return name, transformer.transform(X)
+
+        results = Parallel(n_jobs=n_jobs, verbose=1 if verbose else 0)(
+            delayed(apply_transformer)(name, t, X) for name, t in transformers
+        )
+
+        # Combine results
+        combined = X.copy()
+        for _, transformed in results:
+            new_cols = [c for c in transformed.columns if c not in combined.columns]
+            for col in new_cols:
+                combined[col] = transformed[col]
+
+        return combined
+
+    except ImportError:
+        # Sequential fallback
+        combined = X.copy()
+        for _, transformer in transformers:
+            transformed = transformer.transform(X)
+            new_cols = [c for c in transformed.columns if c not in combined.columns]
+            for col in new_cols:
+                combined[col] = transformed[col]
+
+        return combined

featcopilot-0.1.0.dist-info/METADATA

@@ -0,0 +1,218 @@
+Metadata-Version: 2.4
+Name: featcopilot
+Version: 0.1.0
+Summary: Next-generation LLM-powered auto feature engineering framework with GitHub Copilot SDK
+Author: FeatCopilot Contributors
+License: MIT
+Project-URL: Homepage, https://github.com/thinkall/featcopilot
+Project-URL: Documentation, https://github.com/thinkall/featcopilot#readme
+Project-URL: Repository, https://github.com/thinkall/featcopilot
+Keywords: machine-learning,feature-engineering,automl,llm,copilot,data-science
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: numpy>=1.21.0
+Requires-Dist: pandas>=1.3.0
+Requires-Dist: scipy>=1.7.0
+Requires-Dist: scikit-learn>=1.0.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: joblib>=1.1.0
+Provides-Extra: llm
+Requires-Dist: github-copilot-sdk>=0.1.0; extra == "llm"
+Provides-Extra: timeseries
+Requires-Dist: statsmodels>=0.13.0; extra == "timeseries"
+Provides-Extra: full
+Requires-Dist: github-copilot-sdk>=0.1.0; extra == "full"
+Requires-Dist: statsmodels>=0.13.0; extra == "full"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Requires-Dist: pre-commit>=3.6.0; extra == "dev"
+
+# FeatCopilot 🚀
+
+**Next-Generation LLM-Powered Auto Feature Engineering with GitHub Copilot SDK**
+
+FeatCopilot is a unified feature engineering framework that combines the best approaches from existing libraries (Featuretools, TSFresh, AutoFeat, OpenFE) with novel LLM-powered capabilities via GitHub Copilot SDK.
+
+## 📊 Benchmark Highlights
+
+### Tabular Engine (Fast Mode - <1s)
+
+| Task Type | Average Improvement | Best Case |
+|-----------|--------------------:|----------:|
+| **Text Classification** | **+12.44%** | +49.02% (News Headlines) |
+| Time Series | +1.51% | +12.12% (Retail Demand) |
+| Classification | +0.54% | +4.35% |
+| Regression | +0.65% | +5.57% |
+
+### LLM Engine (With Copilot - 30-60s)
+
+| Task Type | Average Improvement | Best Case |
+|-----------|--------------------:|----------:|
+| **Regression** | **+7.79%** | +19.66% (Retail Demand) |
+| Classification | +2.38% | +2.87% |
+
+- ✅ **12/12 wins** on text classification (tabular mode)
+- 🧠 **+19.66% max improvement** with LLM-powered features
+- ⚡ **<1 second** (tabular) or **30-60s** (with LLM) processing time
+- 📈 Largest gains with simple models (LogisticRegression, Ridge)
+
+[View Full Benchmark Results](https://thinkall.github.io/featcopilot/user-guide/benchmarks/)
+
+## Key Features
+
+- 🔧 **Multi-Engine Architecture**: Tabular, time series, relational, and text feature engines
+- 🤖 **LLM-Powered Intelligence**: Semantic feature discovery, domain-aware generation, and code synthesis
+- 📊 **Intelligent Selection**: Statistical testing, importance ranking, and redundancy elimination
+- 🔌 **Scikit-learn Compatible**: Drop-in replacement for sklearn transformers
+- 📝 **Interpretable**: Every feature comes with human-readable explanations
+
+## Installation
+
+```bash
+# Basic installation
+pip install featcopilot
+
+# With LLM capabilities (requires GitHub Copilot)
+pip install featcopilot[llm]
+
+# Full installation
+pip install featcopilot[full]
+```
+
+## Quick Start
+
+### Fast Mode (Tabular Only)
+
+```python
+from featcopilot import AutoFeatureEngineer
+
+# Sub-second feature engineering
+engineer = AutoFeatureEngineer(
+    engines=['tabular'],
+    max_features=50
+)
+
+X_transformed = engineer.fit_transform(X, y)  # <1 second
+print(f"Features: {X.shape[1]} -> {X_transformed.shape[1]}")
+```
+
+### LLM Mode (With Copilot)
+
+```python
+from featcopilot import AutoFeatureEngineer
+
+# LLM-powered semantic features (+19.66% max improvement)
+engineer = AutoFeatureEngineer(
+    engines=['tabular', 'llm'],
+    max_features=50
+)
+
+X_transformed = engineer.fit_transform(
+    X, y,
+    column_descriptions={
+        'age': 'Customer age in years',
+        'income': 'Annual household income in USD',
+        'tenure': 'Months as customer',
+    },
+    task_description="Predict customer churn"
+)  # 30-60 seconds
+
+# Get LLM-generated explanations
+for feature, explanation in engineer.explain_features().items():
+    print(f"{feature}: {explanation}")
+```
+
+## Engines
+
+### Tabular Engine
+Generates polynomial features, interaction terms, and mathematical transformations.
+
+```python
+from featcopilot.engines import TabularEngine
+
+engine = TabularEngine(
+    polynomial_degree=2,
+    interaction_only=False,
+    include_transforms=['log', 'sqrt', 'square']
+)
+```
+
+### Time Series Engine
+Extracts statistical, frequency, and temporal features from time series data.
+
+```python
+from featcopilot.engines import TimeSeriesEngine
+
+engine = TimeSeriesEngine(
+    features=['mean', 'std', 'skew', 'autocorr', 'fft_coefficients']
+)
+```
+
+### LLM Engine
+Uses GitHub Copilot SDK for intelligent feature generation.
+
+```python
+from featcopilot.llm import SemanticEngine
+
+engine = SemanticEngine(
+    model='gpt-5',
+    max_suggestions=20,
+    validate_features=True
+)
+```
+
+## Feature Selection
+
+```python
+from featcopilot.selection import FeatureSelector
+
+selector = FeatureSelector(
+    methods=['mutual_info', 'importance', 'correlation'],
+    max_features=30,
+    correlation_threshold=0.95
+)
+
+X_selected = selector.fit_transform(X, y)
+```
+
+## Comparison with Existing Libraries
+
+| Feature | FeatCopilot | Featuretools | TSFresh | AutoFeat | OpenFE | CAAFE |
+|---------|-------------|--------------|---------|----------|--------|-------|
+| Tabular Features | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ |
+| Time Series | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ |
+| Relational | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ |
+| LLM-Powered | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ |
+| Semantic Understanding | ✅ | ❌ | ❌ | ❌ | ❌ | ⚠️ |
+| Code Generation | ✅ | ❌ | ❌ | ❌ | ❌ | ⚠️ |
+| Sklearn Compatible | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ |
+| Interpretable | ✅ | ⚠️ | ⚠️ | ⚠️ | ❌ | ✅ |
+
+## Documentation
+
+📖 **Full Documentation**: [https://thinkall.github.io/featcopilot/](https://thinkall.github.io/featcopilot/)
+
+## Requirements
+
+- Python 3.9+
+- NumPy, Pandas, Scikit-learn
+- GitHub Copilot CLI (for LLM features)
+
+## License
+
+MIT License

featcopilot-0.1.0.dist-info/RECORD

@@ -0,0 +1,29 @@
+featcopilot/__init__.py,sha256=Ljn4cK5Emw_Rh8rg-T1EqDoyuWz_GXCAkiaZ_amz-cA,708
+featcopilot/core/__init__.py,sha256=TX_AsPRsVDY1ZKO-ApK7qBFhbgngQbYNamhzYU9P3P8,338
+featcopilot/core/base.py,sha256=lN1zfV6GHCNy2XSNV9OH2dXtvwrZZsu376kT_ExrZto,6090
+featcopilot/core/feature.py,sha256=YGE-xDj7cRZDA50Oa5W-USXiEZ1NrX3WagZueRQiZbk,7361
+featcopilot/core/registry.py,sha256=EK4lleLShhMkGRXI1evv6SsVO81rpLLkzJbjImHryJE,4030
+featcopilot/engines/__init__.py,sha256=bXY5eiEQTZ9IxPY1fTESw4v1-nXFkegSs8p4VYGr7TQ,360
+featcopilot/engines/relational.py,sha256=0zr8OhCRg-jvch1HRaxR6RgQFti3McDPvdco-onsUTc,8311
+featcopilot/engines/tabular.py,sha256=M5cynbfNzkFilxV2rPG5kIcEwni-wc_HtjGNuGiSXGU,10781
+featcopilot/engines/text.py,sha256=I9OGN0Rwf2SW1V9shaJDmmud1eymnx5xLdSmLfCzKhU,7396
+featcopilot/engines/timeseries.py,sha256=76YE5QAD-yzXdajeP3wP3cfqtRSOZglz-E-OVSnvvs8,13553
+featcopilot/llm/__init__.py,sha256=75MgMNw8cAggNOUAJV8ib1uV_UCTjA04tdYbqWNwumU,468
+featcopilot/llm/code_generator.py,sha256=dAn5n3fp-sWj3DhQ9I-ZME5bYSXRVSe4Blx5P-W484Q,9715
+featcopilot/llm/copilot_client.py,sha256=BLAENfNjkyOvgeVWQt-94mkTtxcdz5esk0ro6iaUCPM,17328
+featcopilot/llm/explainer.py,sha256=fztidSmLX5dmbPRMcLmgXNv7AvDEJjXM5OzD6NFtQjQ,6142
+featcopilot/llm/semantic_engine.py,sha256=U4CQ-OsWEr_c2Q8HF6yN7jXhKpTaSR6lft-lEacBzXo,12554
+featcopilot/selection/__init__.py,sha256=pjoos64ym3CR7Hk75qq2dY0NN4OT0Sn3hiBSG_h44SE,406
+featcopilot/selection/importance.py,sha256=GzSHTwKIeHJt42mzb1x8ClGFnqU9_2MxV1kOce9SODg,5481
+featcopilot/selection/redundancy.py,sha256=bz47JQtEBKoz9eMIMB3YMOxH_1s7q1OsEUE_Ob3t0xg,5301
+featcopilot/selection/statistical.py,sha256=POuWuMoyggJt1bCML10I6C7gKZoUP7Yc4nMsKBwECYs,6184
+featcopilot/selection/unified.py,sha256=UPrTJ0svTjy6SnqQVeyiAGNjkgTRbXO_AzbucGZNUjc,6273
+featcopilot/transformers/__init__.py,sha256=pHHSivxNVyC9AmKzdA8UJS0B-b9V1B4eI1QgTP0Z8uw,234
+featcopilot/transformers/sklearn_compat.py,sha256=z5oA_y8YENQaGTTnR13u7CWhJpIhNmUoQP-DNVIgPeA,13536
+featcopilot/utils/__init__.py,sha256=PH-fC1WYJYevcMVI4CCoXIUTJlb5lPXwKeKNj56vs_k,198
+featcopilot/utils/cache.py,sha256=CYIVXQU9dpVdrLkemhjVAoCzXRMRzuQ-U36-q_8zDoc,6489
+featcopilot/utils/parallel.py,sha256=MjLAYWYgoeu02IoWNWEZ82sCcRDi5bICJVcSq7dXmN4,2874
+featcopilot-0.1.0.dist-info/METADATA,sha256=EI1MSGG2KkICOCRnLX1CI5-v91N40pmRS6oyAVgk1w4,6804
+featcopilot-0.1.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+featcopilot-0.1.0.dist-info/top_level.txt,sha256=Lf6lB8VBDX71TBzSXW3qq44RO5hIUKQ6DMi_dL8G_Ak,12
+featcopilot-0.1.0.dist-info/RECORD,,

featcopilot-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.10.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

featcopilot-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+featcopilot