featcopilot 0.1.0__tar.gz → 0.2.0__tar.gz

{featcopilot-0.1.0 → featcopilot-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: featcopilot
-Version: 0.1.0
+Version: 0.2.0
 Summary: Next-generation LLM-powered auto feature engineering framework with GitHub Copilot SDK
 Author: FeatCopilot Contributors
 License: MIT
@@ -28,11 +28,26 @@ 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"
+Requires-Dist: nest_asyncio>=1.5.0; extra == "llm"
+Provides-Extra: litellm
+Requires-Dist: litellm>=1.0.0; extra == "litellm"
+Requires-Dist: nest_asyncio>=1.5.0; extra == "litellm"
 Provides-Extra: timeseries
 Requires-Dist: statsmodels>=0.13.0; extra == "timeseries"
+Provides-Extra: feast
+Requires-Dist: feast>=0.30.0; extra == "feast"
 Provides-Extra: full
 Requires-Dist: github-copilot-sdk>=0.1.0; extra == "full"
+Requires-Dist: litellm>=1.0.0; extra == "full"
 Requires-Dist: statsmodels>=0.13.0; extra == "full"
+Requires-Dist: feast>=0.30.0; extra == "full"
+Requires-Dist: nest_asyncio>=1.5.0; extra == "full"
+Provides-Extra: benchmark
+Requires-Dist: github-copilot-sdk>=0.1.0; extra == "benchmark"
+Requires-Dist: statsmodels>=0.13.0; extra == "benchmark"
+Requires-Dist: flaml[automl,blendsearch]>=2.0.0; extra == "benchmark"
+Requires-Dist: autogluon.tabular>=1.0.0; extra == "benchmark"
+Requires-Dist: h2o>=3.40.0; extra == "benchmark"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
@@ -44,9 +59,9 @@ Requires-Dist: pre-commit>=3.6.0; extra == "dev"
 
 # FeatCopilot 🚀
 
-**Next-Generation LLM-Powered Auto Feature Engineering with GitHub Copilot SDK**
+**Next-Generation LLM-Powered Auto Feature Engineering Framework**
 
-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.
+FeatCopilot automatically generates, selects, and explains predictive features using semantic understanding. It analyzes column meanings, applies domain-aware transformations, and provides human-readable explanations—turning raw data into ML-ready features in seconds.
 
 ## 📊 Benchmark Highlights
 
@@ -59,7 +74,7 @@ FeatCopilot is a unified feature engineering framework that combines the best ap
 | Classification | +0.54% | +4.35% |
 | Regression | +0.65% | +5.57% |
 
-### LLM Engine (With Copilot - 30-60s)
+### LLM Engine (With LiteLLM - 30-60s)
 
 | Task Type | Average Improvement | Best Case |
 |-----------|--------------------:|----------:|
@@ -87,7 +102,7 @@ FeatCopilot is a unified feature engineering framework that combines the best ap
 # Basic installation
 pip install featcopilot
 
-# With LLM capabilities (requires GitHub Copilot)
+# With LLM capabilities
 pip install featcopilot[llm]
 
 # Full installation
@@ -111,7 +126,7 @@ X_transformed = engineer.fit_transform(X, y)  # <1 second
 print(f"Features: {X.shape[1]} -> {X_transformed.shape[1]}")
 ```
 
-### LLM Mode (With Copilot)
+### LLM Mode (With LiteLLM)
 
 ```python
 from featcopilot import AutoFeatureEngineer
@@ -164,16 +179,24 @@ engine = TimeSeriesEngine(
 ```
 
 ### LLM Engine
-Uses GitHub Copilot SDK for intelligent feature generation.
+Uses GitHub Copilot SDK (default) or LiteLLM (100+ providers) for intelligent feature generation.
 
 ```python
 from featcopilot.llm import SemanticEngine
 
+# Default: GitHub Copilot SDK
 engine = SemanticEngine(
-    model='gpt-5',
+    model='gpt-5.2',
     max_suggestions=20,
     validate_features=True
 )
+
+# Alternative: LiteLLM backend
+engine = SemanticEngine(
+    model='gpt-4o',
+    backend='litellm',
+    max_suggestions=20
+)
 ```
 
 ## Feature Selection
@@ -211,7 +234,7 @@ X_selected = selector.fit_transform(X, y)
 
 - Python 3.9+
 - NumPy, Pandas, Scikit-learn
-- GitHub Copilot CLI (for LLM features)
+- GitHub Copilot SDK (default) or LiteLLM (for 100+ LLM providers)
 
 ## License
 

{featcopilot-0.1.0 → featcopilot-0.2.0}/README.md

@@ -1,8 +1,8 @@
 # FeatCopilot 🚀
 
-**Next-Generation LLM-Powered Auto Feature Engineering with GitHub Copilot SDK**
+**Next-Generation LLM-Powered Auto Feature Engineering Framework**
 
-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.
+FeatCopilot automatically generates, selects, and explains predictive features using semantic understanding. It analyzes column meanings, applies domain-aware transformations, and provides human-readable explanations—turning raw data into ML-ready features in seconds.
 
 ## 📊 Benchmark Highlights
 
@@ -15,7 +15,7 @@ FeatCopilot is a unified feature engineering framework that combines the best ap
 | Classification | +0.54% | +4.35% |
 | Regression | +0.65% | +5.57% |
 
-### LLM Engine (With Copilot - 30-60s)
+### LLM Engine (With LiteLLM - 30-60s)
 
 | Task Type | Average Improvement | Best Case |
 |-----------|--------------------:|----------:|
@@ -43,7 +43,7 @@ FeatCopilot is a unified feature engineering framework that combines the best ap
 # Basic installation
 pip install featcopilot
 
-# With LLM capabilities (requires GitHub Copilot)
+# With LLM capabilities
 pip install featcopilot[llm]
 
 # Full installation
@@ -67,7 +67,7 @@ X_transformed = engineer.fit_transform(X, y)  # <1 second
 print(f"Features: {X.shape[1]} -> {X_transformed.shape[1]}")
 ```
 
-### LLM Mode (With Copilot)
+### LLM Mode (With LiteLLM)
 
 ```python
 from featcopilot import AutoFeatureEngineer
@@ -120,16 +120,24 @@ engine = TimeSeriesEngine(
 ```
 
 ### LLM Engine
-Uses GitHub Copilot SDK for intelligent feature generation.
+Uses GitHub Copilot SDK (default) or LiteLLM (100+ providers) for intelligent feature generation.
 
 ```python
 from featcopilot.llm import SemanticEngine
 
+# Default: GitHub Copilot SDK
 engine = SemanticEngine(
-    model='gpt-5',
+    model='gpt-5.2',
     max_suggestions=20,
     validate_features=True
 )
+
+# Alternative: LiteLLM backend
+engine = SemanticEngine(
+    model='gpt-4o',
+    backend='litellm',
+    max_suggestions=20
+)
 ```
 
 ## Feature Selection
@@ -167,7 +175,7 @@ X_selected = selector.fit_transform(X, y)
 
 - Python 3.9+
 - NumPy, Pandas, Scikit-learn
-- GitHub Copilot CLI (for LLM features)
+- GitHub Copilot SDK (default) or LiteLLM (for 100+ LLM providers)
 
 ## License
 

{featcopilot-0.1.0 → featcopilot-0.2.0}/featcopilot/__init__.py

@@ -5,7 +5,9 @@ A unified feature engineering framework combining traditional approaches
 with novel LLM-powered capabilities via GitHub Copilot SDK.
 """
 
-__version__ = "0.1.0"
+from importlib.metadata import version
+
+__version__ = version("featcopilot")
 __author__ = "FeatCopilot Contributors"
 
 from featcopilot.core.base import BaseEngine, BaseSelector

{featcopilot-0.1.0 → featcopilot-0.2.0}/featcopilot/core/feature.py

@@ -7,6 +7,10 @@ from typing import Any, Optional
 import numpy as np
 import pandas as pd
 
+from featcopilot.utils.logger import get_logger
+
+logger = get_logger(__name__)
+
 
 class FeatureType(Enum):
     """Types of features."""
@@ -220,5 +224,5 @@ class FeatureSet:
                     result[feature.name] = feature.compute(df)
                 except Exception as e:
                     # Log warning but continue
-                    print(f"Warning: Could not compute feature {feature.name}: {e}")
+                    logger.warning(f"Could not compute feature {feature.name}: {e}")
         return result

{featcopilot-0.1.0 → featcopilot-0.2.0}/featcopilot/engines/relational.py

@@ -11,6 +11,9 @@ from pydantic import Field
 
 from featcopilot.core.base import BaseEngine, EngineConfig
 from featcopilot.core.feature import FeatureSet
+from featcopilot.utils.logger import get_logger
+
+logger = get_logger(__name__)
 
 
 class RelationalEngineConfig(EngineConfig):
@@ -141,7 +144,7 @@ class RelationalEngine(BaseEngine):
         self._primary_columns = X.columns.tolist()
 
         if self.config.verbose:
-            print(f"RelationalEngine: {len(self._relationships)} relationships defined")
+            logger.info(f"RelationalEngine: {len(self._relationships)} relationships defined")
 
         self._is_fitted = True
         return self
@@ -191,7 +194,7 @@ class RelationalEngine(BaseEngine):
         self._feature_names = [c for c in result.columns if c not in X.columns]
 
         if self.config.verbose:
-            print(f"RelationalEngine: Generated {len(self._feature_names)} features")
+            logger.info(f"RelationalEngine: Generated {len(self._feature_names)} features")
 
         return result
 

{featcopilot-0.1.0 → featcopilot-0.2.0}/featcopilot/engines/tabular.py

@@ -12,6 +12,9 @@ from pydantic import Field
 
 from featcopilot.core.base import BaseEngine, EngineConfig
 from featcopilot.core.feature import Feature, FeatureOrigin, FeatureSet, FeatureType
+from featcopilot.utils.logger import get_logger
+
+logger = get_logger(__name__)
 
 
 class TabularEngineConfig(EngineConfig):
@@ -124,7 +127,7 @@ class TabularEngine(BaseEngine):
         ]
 
         if self.config.verbose:
-            print(f"TabularEngine: Found {len(self._numeric_columns)} numeric columns")
+            logger.info(f"TabularEngine: Found {len(self._numeric_columns)} numeric columns")
 
         # Plan features to generate
         self._plan_features(X)
@@ -207,7 +210,7 @@ class TabularEngine(BaseEngine):
             self._feature_set.add(feature)
 
         if self.config.verbose:
-            print(f"TabularEngine: Planned {len(self._feature_set)} features")
+            logger.info(f"TabularEngine: Planned {len(self._feature_set)} features")
 
     def transform(self, X: Union[pd.DataFrame, np.ndarray], **kwargs) -> pd.DataFrame:
         """
@@ -284,7 +287,7 @@ class TabularEngine(BaseEngine):
         self._feature_names = [c for c in result.columns if c not in X.columns]
 
         if self.config.verbose:
-            print(f"TabularEngine: Generated {len(self._feature_names)} features")
+            logger.info(f"TabularEngine: Generated {len(self._feature_names)} features")
 
         return result
 

{featcopilot-0.1.0 → featcopilot-0.2.0}/featcopilot/engines/text.py

@@ -11,6 +11,9 @@ from pydantic import Field
 
 from featcopilot.core.base import BaseEngine, EngineConfig
 from featcopilot.core.feature import FeatureSet
+from featcopilot.utils.logger import get_logger
+
+logger = get_logger(__name__)
 
 
 class TextEngineConfig(EngineConfig):
@@ -106,7 +109,7 @@ class TextEngine(BaseEngine):
             ]
 
         if self.config.verbose:
-            print(f"TextEngine: Found {len(self._text_columns)} text columns")
+            logger.info(f"TextEngine: Found {len(self._text_columns)} text columns")
 
         # Fit TF-IDF vectorizers if needed
         if "tfidf" in self.config.features:
@@ -135,7 +138,7 @@ class TextEngine(BaseEngine):
 
         except ImportError:
             if self.config.verbose:
-                print("TextEngine: sklearn not available for TF-IDF, skipping")
+                logger.warning("TextEngine: sklearn not available for TF-IDF, skipping")
 
     def transform(self, X: Union[pd.DataFrame, np.ndarray], **kwargs) -> pd.DataFrame:
         """
@@ -191,7 +194,7 @@ class TextEngine(BaseEngine):
         self._feature_names = [c for c in result.columns if c not in X.columns]
 
         if self.config.verbose:
-            print(f"TextEngine: Extracted {len(self._feature_names)} features")
+            logger.info(f"TextEngine: Extracted {len(self._feature_names)} features")
 
         return result
 

{featcopilot-0.1.0 → featcopilot-0.2.0}/featcopilot/engines/timeseries.py

@@ -12,6 +12,9 @@ from pydantic import Field
 
 from featcopilot.core.base import BaseEngine, EngineConfig
 from featcopilot.core.feature import FeatureSet
+from featcopilot.utils.logger import get_logger
+
+logger = get_logger(__name__)
 
 
 class TimeSeriesEngineConfig(EngineConfig):
@@ -123,7 +126,7 @@ class TimeSeriesEngine(BaseEngine):
         self._time_columns = X.select_dtypes(include=[np.number]).columns.tolist()
 
         if self.config.verbose:
-            print(f"TimeSeriesEngine: Found {len(self._time_columns)} numeric columns")
+            logger.info(f"TimeSeriesEngine: Found {len(self._time_columns)} numeric columns")
 
         self._is_fitted = True
         return self
@@ -177,7 +180,7 @@ class TimeSeriesEngine(BaseEngine):
         self._feature_names = list(result.columns)
 
         if self.config.verbose:
-            print(f"TimeSeriesEngine: Extracted {len(self._feature_names)} features")
+            logger.info(f"TimeSeriesEngine: Extracted {len(self._feature_names)} features")
 
         return result
 

{featcopilot-0.1.0 → featcopilot-0.2.0}/featcopilot/llm/__init__.py

@@ -1,15 +1,18 @@
 """LLM-powered feature engineering module.
 
-Uses GitHub Copilot SDK for intelligent feature generation.
+Uses GitHub Copilot SDK or LiteLLM for intelligent feature generation.
 """
 
 from featcopilot.llm.code_generator import FeatureCodeGenerator
 from featcopilot.llm.copilot_client import CopilotFeatureClient
 from featcopilot.llm.explainer import FeatureExplainer
+from featcopilot.llm.litellm_client import LiteLLMFeatureClient, SyncLiteLLMFeatureClient
 from featcopilot.llm.semantic_engine import SemanticEngine
 
 __all__ = [
     "CopilotFeatureClient",
+    "LiteLLMFeatureClient",
+    "SyncLiteLLMFeatureClient",
     "SemanticEngine",
     "FeatureExplainer",
     "FeatureCodeGenerator",

{featcopilot-0.1.0 → featcopilot-0.2.0}/featcopilot/llm/code_generator.py

@@ -10,6 +10,9 @@ import pandas as pd
 
 from featcopilot.core.feature import Feature, FeatureOrigin, FeatureType
 from featcopilot.llm.copilot_client import SyncCopilotFeatureClient
+from featcopilot.utils.logger import get_logger
+
+logger = get_logger(__name__)
 
 
 class FeatureCodeGenerator:
@@ -21,7 +24,7 @@ class FeatureCodeGenerator:
 
     Parameters
     ----------
-    model : str, default='gpt-5'
+    model : str, default='gpt-5.2'
         LLM model to use
     validate : bool, default=True
         Whether to validate generated code
@@ -35,7 +38,7 @@ class FeatureCodeGenerator:
     ... )
     """
 
-    def __init__(self, model: str = "gpt-5", validate: bool = True, verbose: bool = False):
+    def __init__(self, model: str = "gpt-5.2", validate: bool = True, verbose: bool = False):
         self.model = model
         self.validate = validate
         self.verbose = verbose
@@ -98,7 +101,7 @@ class FeatureCodeGenerator:
             )
             if not validation["valid"]:
                 if self.verbose:
-                    print(f"Code validation failed: {validation['error']}")
+                    logger.warning(f"Code validation failed: {validation['error']}")
                 # Try to fix common issues
                 code = self._fix_common_issues(code, validation["error"])
 
@@ -144,7 +147,7 @@ class FeatureCodeGenerator:
                 features.append(feature)
             except Exception as e:
                 if self.verbose:
-                    print(f"Failed to generate feature for '{desc}': {e}")
+                    logger.error(f"Failed to generate feature for '{desc}': {e}")
 
         return features
 

{featcopilot-0.1.0 → featcopilot-0.2.0}/featcopilot/llm/copilot_client.py

@@ -10,11 +10,15 @@ from typing import Any, Optional
 
 from pydantic import BaseModel, Field
 
+from featcopilot.utils.logger import get_logger
+
+logger = get_logger(__name__)
+
 
 class CopilotConfig(BaseModel):
     """Configuration for Copilot client."""
 
-    model: str = Field(default="gpt-5", description="Model to use")
+    model: str = Field(default="gpt-5.2", description="Model to use")
     temperature: float = Field(default=0.3, ge=0, le=1, description="Temperature for generation")
     max_tokens: int = Field(default=4096, description="Maximum tokens in response")
     timeout: float = Field(default=60.0, description="Timeout in seconds")
@@ -35,12 +39,12 @@ class CopilotFeatureClient:
     ----------
     config : CopilotConfig, optional
         Configuration for the client
-    model : str, default='gpt-5'
+    model : str, default='gpt-5.2'
         Model to use for generation
 
     Examples
     --------
-    >>> client = CopilotFeatureClient(model='gpt-5')
+    >>> client = CopilotFeatureClient(model='gpt-5.2')
     >>> await client.start()
     >>> suggestions = await client.suggest_features(
     ...     column_info={'age': 'int', 'income': 'float'},
@@ -49,7 +53,7 @@ class CopilotFeatureClient:
     >>> await client.stop()
     """
 
-    def __init__(self, config: Optional[CopilotConfig] = None, model: str = "gpt-5", **kwargs):
+    def __init__(self, config: Optional[CopilotConfig] = None, model: str = "gpt-5.2", **kwargs):
         self.config = config or CopilotConfig(model=model, **kwargs)
         self._client = None
         self._session = None
@@ -82,13 +86,13 @@ class CopilotFeatureClient:
             # Copilot SDK not installed - use mock mode
             self._copilot_available = False
             self._is_started = True
-            print("Warning: copilot-sdk not installed. Using mock LLM responses.")
+            logger.warning("copilot-sdk not installed. Using mock LLM responses.")
 
         except Exception as e:
             # Copilot not available - use mock mode
             self._copilot_available = False
             self._is_started = True
-            print(f"Warning: Could not connect to Copilot: {e}. Using mock LLM responses.")
+            logger.warning(f"Could not connect to Copilot: {e}. Using mock LLM responses.")
 
         return self
 
@@ -469,7 +473,37 @@ result = df['col1'] / (df['col2'] + 1e-8)
                 local_vars = {"df": df, "np": np, "pd": pd}
                 exec(
                     code,
-                    {"__builtins__": {"len": len, "sum": sum, "max": max, "min": min}},
+                    {
+                        "__builtins__": {
+                            "len": len,
+                            "sum": sum,
+                            "max": max,
+                            "min": min,
+                            "int": int,
+                            "float": float,
+                            "str": str,
+                            "bool": bool,
+                            "abs": abs,
+                            "round": round,
+                            "pow": pow,
+                            "range": range,
+                            "list": list,
+                            "dict": dict,
+                            "set": set,
+                            "tuple": tuple,
+                            "sorted": sorted,
+                            "reversed": reversed,
+                            "enumerate": enumerate,
+                            "zip": zip,
+                            "any": any,
+                            "all": all,
+                            "map": map,
+                            "filter": filter,
+                            "isinstance": isinstance,
+                            "hasattr": hasattr,
+                            "getattr": getattr,
+                        }
+                    },
                     local_vars,
                 )
 
@@ -489,33 +523,43 @@ class SyncCopilotFeatureClient:
 
     def __init__(self, **kwargs):
         self._async_client = CopilotFeatureClient(**kwargs)
-        self._loop = None
 
-    def _get_loop(self):
-        if self._loop is None or self._loop.is_closed():
+    def _run_async(self, coro):
+        """Run an async coroutine, handling nested event loops (e.g., Jupyter)."""
+        try:
+            # Check if we're in a running event loop (e.g., Jupyter)
+            loop = asyncio.get_running_loop()
+            # We're in a running loop - use nest_asyncio if available
             try:
-                self._loop = asyncio.get_event_loop()
-            except RuntimeError:
-                self._loop = asyncio.new_event_loop()
-                asyncio.set_event_loop(self._loop)
-        return self._loop
+                import nest_asyncio
+
+                nest_asyncio.apply()
+                return loop.run_until_complete(coro)
+            except ImportError:
+                # nest_asyncio not available, try alternative approach
+                import concurrent.futures
+
+                with concurrent.futures.ThreadPoolExecutor() as executor:
+                    future = executor.submit(asyncio.run, coro)
+                    return future.result()
+        except RuntimeError:
+            # No running event loop - safe to use asyncio.run
+            return asyncio.run(coro)
 
     def start(self):
-        return self._get_loop().run_until_complete(self._async_client.start())
+        return self._run_async(self._async_client.start())
 
     def stop(self):
-        return self._get_loop().run_until_complete(self._async_client.stop())
+        return self._run_async(self._async_client.stop())
 
     def suggest_features(self, **kwargs):
-        return self._get_loop().run_until_complete(self._async_client.suggest_features(**kwargs))
+        return self._run_async(self._async_client.suggest_features(**kwargs))
 
     def explain_feature(self, **kwargs):
-        return self._get_loop().run_until_complete(self._async_client.explain_feature(**kwargs))
+        return self._run_async(self._async_client.explain_feature(**kwargs))
 
     def generate_feature_code(self, **kwargs):
-        return self._get_loop().run_until_complete(self._async_client.generate_feature_code(**kwargs))
+        return self._run_async(self._async_client.generate_feature_code(**kwargs))
 
     def validate_feature_code(self, code: str, sample_data=None):
-        return self._get_loop().run_until_complete(
-            self._async_client.validate_feature_code(code=code, sample_data=sample_data)
-        )
+        return self._run_async(self._async_client.validate_feature_code(code=code, sample_data=sample_data))

{featcopilot-0.1.0 → featcopilot-0.2.0}/featcopilot/llm/explainer.py

@@ -9,6 +9,9 @@ import pandas as pd
 
 from featcopilot.core.feature import Feature, FeatureSet
 from featcopilot.llm.copilot_client import SyncCopilotFeatureClient
+from featcopilot.utils.logger import get_logger
+
+logger = get_logger(__name__)
 
 
 class FeatureExplainer:
@@ -20,7 +23,7 @@ class FeatureExplainer:
 
     Parameters
     ----------
-    model : str, default='gpt-5'
+    model : str, default='gpt-5.2'
         LLM model to use
 
     Examples
@@ -29,7 +32,7 @@ class FeatureExplainer:
     >>> explanations = explainer.explain_features(feature_set, task='predict churn')
     """
 
-    def __init__(self, model: str = "gpt-5", verbose: bool = False):
+    def __init__(self, model: str = "gpt-5.2", verbose: bool = False):
         self.model = model
         self.verbose = verbose
         self._client: Optional[SyncCopilotFeatureClient] = None
@@ -115,7 +118,7 @@ class FeatureExplainer:
 
             except Exception as e:
                 if self.verbose:
-                    print(f"Could not explain {feature.name}: {e}")
+                    logger.error(f"Could not explain {feature.name}: {e}")
                 explanations[feature.name] = f"Feature based on: {', '.join(feature.source_columns)}"
 
         return explanations